feat: markdown-formatter plugin (pilot migration)#3
Merged
Conversation
Add .editorconfig (LF, 2-space, shfmt shell keys) and .shellcheckrc (external-sources, source-path=SCRIPTDIR, selective optional checks), mirroring the standards/medley drop-in configs. Governs authoring and linting of this repo's own shell sources only; not shipped to plugin consumers. Long-term these should be consumed from the standards repo. Co-Authored-By: Claude <noreply@anthropic.com>
PostToolUse hook that auto-formats and lints Markdown on edit via markdownlint-cli2 --fix, using the consuming repo's own markdownlint config (ships none). Lifted and genericized from melodic-software/medley's in-repo markdown-format hook: telemetry/observability coupling removed, medley-policy wrapper prose dropped, file-anchored repo-root cd preserved for config discovery, kill switch HOOK_MARKDOWN_FORMAT_ENABLED retained. No userConfig. Bundles a trimmed hook-utils subset and a black-box contract test (12 cases). Verified: claude plugin validate --strict; --plugin-dir load in a clean non-medley repo; source-repo parity vs the in-repo hook (byte-identical --fix output, MD024 finding-line identity, zero plugin telemetry). Co-Authored-By: Claude <noreply@anthropic.com>
Add the markdown-formatter entry to .claude-plugin/marketplace.json so the already-committed plugin is installable, and surface it in the README catalog. Drop metadata.pluginRoot: claude plugin validate --strict rejects the bare plugin source it is meant to enable (plugins.N.source: Invalid input), despite the marketplaces-doc example. Entries use the explicit ./plugins/<name> form. Playbook step 10 now records the ./-prefixed-source requirement and the need to validate the catalog manifest itself (the entry error surfaces only there). Co-Authored-By: Claude <noreply@anthropic.com>
![chatgpt-codex-connector[bot]](https://avatars.githubusercontent.com/in/1144995?s=60&v=4){kind=small}
There was a problem hiding this comment.
💡 Codex Review
Here are some automated review suggestions for this pull request.
Reviewed commit: b970d0c306
ℹ️ About Codex in GitHub
Your team has set up Codex to review pull requests in this repo. Reviews are triggered when you
- Open a pull request for review
- Mark a draft as ready
- Comment "@codex review".
If Codex has suggestions, it will comment; otherwise it will react with 👍.
Codex can also answer questions or update the PR. Try commenting "@codex address that feedback".
| local norm_file norm_project | ||
| norm_file=$(hook::normalize_path "$file") | ||
| norm_project=$(hook::normalize_path "${CLAUDE_PROJECT_DIR}") | ||
| if [[ "$norm_file" != "$norm_project"* ]]; then |
There was a problem hiding this comment.
When CLAUDE_PROJECT_DIR is /repo/app, this raw prefix check also accepts /repo/app-backup/file.md. The guard is supposed to skip files outside the current project, but with similarly named sibling directories a Write/Edit to that path will still run markdownlint-cli2 --fix outside the project; compare against $norm_project/ or use a relative-path check with a real boundary.
Useful? React with 👍 / 👎.
Comment on lines
+28
to
+29
| elif command -v npx >/dev/null 2>&1; then | ||
| MDLINT=(npx markdownlint-cli2) |
There was a problem hiding this comment.
In repos where npx exists but markdownlint-cli2 is not installed locally/globally and the npm registry is unavailable or blocked, this branch still runs npx markdownlint-cli2; npx --help describes it as running from a “local or remote npm package”, so the hook captures npm fetch failures and reports them as markdownlint findings on every Markdown edit instead of being a no-op. Check for an actually local/resolvable package or suppress this fallback when the package cannot be executed without fetching.
Useful? React with 👍 / 👎.
This was referenced Jun 29, 2026
This was referenced Jul 12, 2026
kyle-sexton
added a commit
that referenced
this pull request
Jul 12, 2026
…r self-contained Address three more Codex P2 findings: - teach topic case (#1): topic is start-or-resume, so a fresh-workspace expectation flakes on a machine with prior data. Assert the start-or-resume contract — mission interview for a new workspace, resume for an existing one. - teach primer case (#3): the primer intakes the user's starting point with one question before building the ladder, so a single-turn run may correctly open with the intake. Make the expectation intake-first. - diagnose cleanup case (#6): a broad grep -r "[DEBUG-" already matches the diagnose docs and this fixture in the checkout. Scope the assertion to the specific [DEBUG-a4f2] tag across the changed source.
kyle-sexton
added a commit
that referenced
this pull request
Jul 13, 2026
… hardening (#138) Applies the resolved `planning/setup` hardening to `knowledge/setup`'s `library_dir` seam (same single-directory `userConfig` shape, same latent issues). ## Changes **`plugins/knowledge/skills/setup/SKILL.md`** - **Precedence** — step 1 now resolves the full documented order (Managed > `--settings` > Local > Project > User), warns when higher layers are unreadable instead of declaring a lower value authoritative, and surfaces layer shadowing before the project write. - **Portability** — step 5 guards the tracked project write: never propagate a machine-specific personal-layer value into team settings; route personal-only overrides to `.claude/settings.local.json` (portability required only for the shared project write). - **Declared-convention alignment** — inspect the repo's declared working-notes/artifacts convention even when a value is set; surface divergence and offer to reconcile. **`plugins/codebase-audit/skills/setup/SKILL.md`** (partial match — writes a tracked `.md`, not settings) - Applied only the precedence/shadowing subset: step 1 reports the *effective additively-merged* config across user-global → team → local layers (and warns on unreadable layers), instead of summarizing the team file alone. Settings-write portability specifics do not apply. ## Deviations (own-flagged) 1. **Fix #3 premise softened for knowledge.** The issue's fix #3 parenthetical assumed knowledge "honors that convention over the config at write time" (true for planning). Verified via `skills/youtube/extraction/lib/work-root.js` and the youtube pipeline that **knowledge resolves `library_dir` directly at write time — no skill overrides it with a repo convention at runtime.** Documenting that behavior would be false, so I softened the imported write-time-override claim: `library_dir` is runtime-authoritative, and setup's job is to keep it *aligned* with any declared convention. Fixes #1 and #2 are unaffected. 2. **`codebase-audit` version bump not in issue scope.** Patch-bumped `0.1.0 → 0.1.1` because its SKILL behavior changed; the issue only specified the `knowledge` minor bump. ## Verification - `knowledge` `plugin.json` minor bump `0.2.0 → 0.3.0`; `codebase-audit` `0.1.0 → 0.1.1`. - `claude plugin validate` clean on both plugins. - markdownlint clean on both edited files. Refs melodic-software/medley#1463 <!-- CURSOR_SUMMARY --> --- > [!NOTE] > **Low Risk** > Changes are limited to plugin skill documentation and version metadata; no application runtime or security-sensitive code paths are modified. > > **Overview** > **Hardens setup skills** for the `knowledge` and `codebase-audit` plugins so interactive setup reflects layered config reality instead of treating a single team file as authoritative. > > For **`knowledge/setup`**, step 1 now follows the full Claude Code precedence chain (Managed → `--settings` → Local → Project → User), warns when higher layers are unreadable, and calls out when a project write would stay shadowed. A new step reconciles `library_dir` with repo-declared working-notes conventions even when a value is already set. Persistence (step 5) blocks copying machine-specific personal paths into tracked project settings, routes personal-only overrides to `.claude/settings.local.json`, and the output section documents honest pipeline behavior (`book-distill` ignores `library_dir`; YouTube does not yet honor it). **`knowledge`** bumps **0.2.0 → 0.3.0**. > > For **`codebase-audit/setup`**, step 1 is expanded to summarize the **effective merged** config across user-global → team → local layers (including dimension opt-outs via empty source lists), explain that only the team file is written, and warn when overlays block re-enabling dimensions. **`codebase-audit`** patch-bumps **0.1.0 → 0.1.1**. > > <sup>Reviewed by [Cursor Bugbot](https://cursor.com/bugbot) for commit f13139a. Bugbot is set up for automated code reviews on this repo. Configure [here](https://www.cursor.com/dashboard/bugbot).</sup> <!-- /CURSOR_SUMMARY -->
This was referenced Jul 16, 2026
kyle-sexton
added a commit
that referenced
this pull request
Jul 16, 2026
… follow-ups) (#205) ## Summary The three follow-ups deliberately deferred out of #204 (recorded in its PR body), each decision-gated with the maintainer before editing. Net **−341 lines**; no plugin manifest, schema, or skill behavior touched. ## #1 — Retire the audit snapshots Delete `docs/evals-coverage.md` and `docs/extensibility-contract-grading.md`. They were hand-stamped, point-in-time records that drift the moment a plugin changes (the reorg already forced a two-layer temporal re-stamp). **Retire over generate.** The durable policy already lives in `docs/MIGRATION-PLAYBOOK.md` — the warrant rule + consumer-verify recipe ("Evals — warrant policy and consumer-verify recipe") and the four-seams contract ("Extensibility contract v2.1"). A generator could derive only eval *presence* (a live glob) — the minority of one doc and none of the other; class, contract grades, and medley program state stay irreducibly hand-graded or externally-owned. Generating only the presence slice yields a half-generated hybrid that still drifts on its biggest surface. Retire is the clean fit. **Gaps captured first.** Two warranted-but-unowned eval gaps were recorded *only* in the retired snapshot (verified still live against the tree): `context7/setup` and `planning/wayfind`. Filed durably before deletion: - `melodic-software/medley#1537` — evals(context7/setup) - `melodic-software/medley#1538` — evals(planning/wayfind) Inbound pointers updated: README doc-index (2 bullets removed) and the playbook's evals section (now states on-demand verification instead of pointing at a deleted snapshot). No dangling references remain (repo-wide grep clean). ## #2 — Reclassify the depth-variant convention tension The playbook stated a depth/intensity variant "takes an argument, never a sibling," yet `discovery`'s `explore-deep` / `research-deep` ship as sibling skills. Inspection shows they are **structural, not depth**: - `explore-deep` — `context: fork` + `agent: general-purpose`: a distinct execution *topology* (isolated forked subagent), declared in frontmatter, not expressible as a runtime argument. - `research-deep` — a dispatcher to the heaviest isolated tier (workflow engine, forked subagent, or inline fallback), with its own body and auto-invocation description. The convention needed no exception — it needed a sharper structural/depth test. Amended to classify **execution tier as a structural axis** (sibling) and bind the `-deep` suffix to that axis, so the naming no longer reads as a violation and a future reader does not re-flag it. A true effort knob on one execution path still takes an argument. No skills renamed. ## #3 — README revisit-condition dedup Assessed, closed **no-op**. The coupling flagged in #204 is a documented, directional SSOT+index: `docs/CATALOG-TAXONOMY.md` (L71–73) declares plugin-scoped revisit conditions are *owned by each plugin's README* and the taxonomy "Trigger register" lists them "only as pointers." The READMEs are the single owners of genuine plugin-specific rationale; the register summarizes them. Nothing to dedup. Confirmed none of the three sections cross-names the taxonomy doc. ## Verification - `scripts/validate-plugins.sh`: pass (all manifests + strict catalog sync) - `scripts/run-plugin-tests.sh`: 7 passed, 0 failed - `markdownlint-cli2`: 0 errors on both touched markdown files - Repo-wide grep for the retired doc names: no remaining references ## Note (not in this PR) `docs/hook-migration-audit.md` is the same "point-in-time audit" genus as the two retired here. Left untouched; flagged for a consistency decision in a later pass. 🤖 Generated with [Claude Code](https://claude.com/claude-code) https://claude.ai/code/session_0163dXPBdRYFpx4wTtS648tE Co-authored-by: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
kyle-sexton
added a commit
that referenced
this pull request
Jul 16, 2026
#218) ## Summary `code-tidying:tidy`'s Phase H ("Ship") told the agent to create the PR by calling `gh pr create` directly — a bare bypass of `source-control:pull-request`'s canonical create flow, which resolves issue-linkage (with an issue-existence check before shipping a `Closes #N` keyword), assembles the PR body injection-safely (quoted heredoc + parameter-expansion concat, a defense against shell injection through prompt-derived text), and gates PR creation on a valid closing keyword or explicit opt-out before calling `gh pr create` itself. Closes decisions **#3** and **#42** of the melodic-software issue/PR consistency initiative's Decisions Log (`https://claude.ai/code/artifact/232ecdce-8316-4880-8c0a-dc3c7dcf3a63`): - **#3 (formatting-tidy-canonical-pr-gate-bypass)** — "YES, fix — but not via direct skill-to-skill coupling... minimize coupling between `code-tidying:tidy` and `source-control:pull-request`... Likely shape: a shared script/check both skills call, or a convention-level requirement enforced by a common gate." This PR fixes the bypass without a hard cross-plugin dependency (below). - **#42 (crosscut-skill-content-sync-mechanism)** — "Single shared reference doc, all authoring skills import it." Applied here for its first concrete instance (see Design rationale). ## What changed Phase H now applies the same optional-plugin graceful-degrade pattern `tidy` already uses elsewhere in its own SKILL.md (Phase C for `discovery`, Phase D for `work-items`): - **If `source-control` is installed:** invoke `/pull-request create`, supplying tidy's own title/body-section content. Its stage-and-commit step (§2.3) is a no-op here since Phase E already committed the tidyings atomically — the call goes straight to rebase-check, issue-linkage resolution, and gated PR creation. - **If `source-control` isn't installed:** the same invariants apply inline — verify an issue exists before writing `Closes #N`, assemble the body via quoted heredoc + concat (never an unquoted `<<EOF`), and refuse `gh pr create` until the body carries a valid closing keyword or an explicit `Refs #N` / `No related issue:` opt-out. ## Design rationale (decision #42, recorded as an assumption — no user available to confirm interactively this session) Considered extracting the safety invariants into a new shared reference doc (mirroring the `docs/PLUGIN-ARTIFACT-PROTOCOL.md` → per-plugin `reference/artifact-protocol.md` precedent, drift-checked by `validate-plugin-contracts.mjs` and this session's new `scripts/check-cross-plugin-source-drift.sh`). Rejected for now: every invariant worth stating is already authoritative in `pull-request/reference/create.md`, so a copied doc would be pure duplication with drift risk — and with exactly one non-`source-control` consumer today, it wouldn't even register as a cluster for the new drift checker (which requires 2+ plugin copies). A prose convention pointer is lighter, carries no duplication to drift, and degrades gracefully if `source-control` is absent — which a hard-copied doc wouldn't buy any safety over. This is decision #42's design choice for its *first application*, not a retrofit of every authoring skill in the marketplace — no other skill is touched by this PR. Rolling the same pattern out to other PR-creating skills (if any surface a similar bypass) is deferred, unscoped follow-up work, tracked in the Decisions Log rather than guessed at here. ## Test plan - `bash scripts/validate-plugins.sh` — all plugin manifests + strict catalog validation pass. - `node scripts/validate-plugin-contracts.mjs` — 16 setup skills + 1342 plugin files checked, clean. - `npx markdownlint-cli2 plugins/code-tidying/skills/tidy/SKILL.md` — 0 errors. - Confirmed no other stale bare-`gh pr create` references remain under `plugins/code-tidying/`. - No existing test file exercises `tidy`'s `SKILL.md` prose directly (only `open-pr-count.test.sh`, unrelated to Phase H) — nothing to update there.
This was referenced Jul 17, 2026
kyle-sexton
added a commit
that referenced
this pull request
Jul 20, 2026
…verb (#709) ## Summary The work-item-tracker seam reserves `work-map` **containers** as a first-class use case, but its read side was repo-global only — there was no way to operate one container within scope (#498). Concretely: `list-frontier` had no container scoping, its rows drop parent linkage (GitHub's list surface omits it), an unassigned/unblocked container surfaced as **its own** frontier item, and no verb enumerated a container's children (needed for a closed-children invariant check). Surfaced by the #416 wayfind-routing planning pass. ## Fix - **`list-sub-items <parent-id> [--state open|closed|all]`** — new seam + adapter verb. Returns a container's **direct** children as full normalized item objects (same `{items:[…]}` envelope as `list-items`), each re-parented to the container. Raw enumeration — closed and nested-container children are kept (the closed-children invariant check and sub-map traversal need them). `--state` defaults to `all`. Both adapters implement it: GitHub resolves children via the native `subIssues` link and intersects with `list-items` output (its list surface omits parent linkage, so the child set can't be derived from rows); the offline `local-markdown` adapter matches on the stored `parent` frontmatter. - **`list-frontier --parent <container-id>`** — container-scoped frontier. Core reads `list-sub-items` for that container instead of the repo-global `list-items`, then applies the identical filter. The scoped verb is chosen **before** the capability gate, so an adapter with `list-items` but not `list-sub-items` degrades explicitly (exit 6) rather than passing the gate then failing mid-call. - **Container exclusion (obs #3).** `list-frontier` now excludes any item carrying the container label (`work-map`) **unconditionally** — global and `--parent`-scoped, and under `--autonomous`. Justification: the CONTRACT already states containers are never claimable by workers, so this is a correctness fix, not a policy toggle — deliberately not behind a flag. Design notes for the reviewer: - The container label is a named constant (`WIT_CONTAINER_LABEL`, default `work-map`) matching the CONTRACT term — not a new binding key. Per-repo remapping is **deferred** to the existing `config.role_labels` convention, keyed off the first consumer that needs a non-`work-map` marker. - Obs #2 (global rows drop parent linkage) is addressed by the `--parent` scoping path, **not** by enriching global `list-items` rows — GitHub's bulk list surface genuinely omits `parent`, and `get-item` remains authoritative for a single item's parentage (unchanged CONTRACT stance). - Container exclusion lives only in the core frontier filter; `list-sub-items` stays a raw enumeration (nested sub-maps and closed children must survive it). Version `0.15.0` → `0.16.0` (additive); CHANGELOG entry added. ## Verification All commands run in the worktree on the rebased branch (tip of `origin/main` + this commit). New behavioral test — `local-markdown list-sub-items` end-to-end through the core CLI (offline, CI-runnable): ``` $ bash plugins/work-items/tools/work-item-tracker/adapters/local-markdown/list-sub-items.test.sh PASS: [1] list-sub-items holds open child C1 PASS: [2] list-sub-items holds closed child C2 PASS: [3] list-sub-items excludes the container itself PASS: [4] list-sub-items excludes an unrelated leaf PASS: [5] list-sub-items excludes a grandchild (direct children only) PASS: [6] list-sub-items (default all) child count PASS: [7] children carry parent_id PASS: [8] list-sub-items --state open keeps only C1 PASS: [9] list-sub-items --state closed keeps only C2 PASS: [10] list-sub-items on a leaf is empty PASS: [11] scoped frontier holds the open child C1 PASS: [12] scoped frontier drops the closed child C2 PASS: [13] scoped frontier drops the grandchild (not a direct child) PASS: [14] scoped frontier never holds the container PASS: [15] global frontier excludes the unassigned/unblocked container PASS: [16] global frontier still holds the workable leaf ``` Core frontier filter unit test (container exclusion added): ``` $ bash plugins/work-items/tools/work-item-tracker/lib/frontier.test.sh PASS: [7] default frontier excludes the container (work-map) PASS: [8] autonomous frontier also excludes the container PASS: [9] explicit container label excludes the remap, not the stale default ... (9 cases, 0 failed) ``` Abstract conformance suite through the core CLI (exercises `list-sub-items` + `list-frontier --parent` for the adapter — CI runs this offline binding): ``` $ bash plugins/work-items/tools/work-item-tracker/conformance/run-conformance.sh --binding local-markdown PASS: [43] list-sub-items A (exit code) PASS: [46] A's children hold B PASS: [47] enumerated child B is re-parented to A PASS: [50] list-frontier --parent A (exit code) PASS: [53] scoped frontier drops blocked child B Conformance (local-markdown): 72 cases, 0 failed ``` Full `work-items` plugin test suite + shellcheck (`0.11.0`, repo `.shellcheckrc`) over all changed/new shell files — both clean: ``` $ find plugins/work-items -name '*.test.sh' | while read t; do bash "$t"; done # all pass, 0 failures $ shellcheck -x <changed .sh + .test.sh> # rc=0, no findings $ bash scripts/check-changelog-parity.sh --check-bump origin/main # Every changed plugin has its CHANGELOG entry. ``` The GitHub `subIssues`+intersect path runs only under the on-demand `e2e-probe` (needs a live sandbox repo), which was **not** executed here; its `subIssues` node shape (`id/number/title/url/state/repository.nameWithOwner` — no `assignees/labels/blockedBy`, hence the intersect-with-`list-items` design) was verified against gh's own source (`cli/cli api/queries_issue.go`, `LinkedIssue` struct). e2e-probe was extended with container-exclusion and `list-sub-items`/`--parent` assertions for when it is next run against a sandbox. Closes #498 ## Related - #498 — the seam's own read-verb coverage for containers (this PR). - #416 — routes `planning:wayfind` through the seam (the consumer that surfaced this gap); related but distinct, unblocked by this change. - #379 — Jira adapter (a different backend); related but distinct. --------- Co-authored-by: Claude <noreply@anthropic.com>
This was referenced Jul 20, 2026
kyle-sexton
added a commit
that referenced
this pull request
Jul 21, 2026
) ## Summary Closes the three deferred, independently-corroborated (Codex + claude[bot]) review findings from PR #248's review cycle against `plugins/claude-ops/skills/plugins/scripts/fleet-state.sh`. Each was verified VALID but deferred out of #248 to bound an already-long (6+ round) fix/review loop. All fixed here with TDD regression tests (red-then-green). Version bumped `0.15.4` → `0.16.0` (minor: adds a new consumable output field). ## Fix **1 — user-scope install completeness (additive, no behavior change to the existing field).** `fleet-state.sh` now emits a new field `missing_from_user_install` = catalog minus *user-scope*-installed minus opted-out, alongside the untouched all-scope `missing_from_install`. A plugin installed only at `project`/`local` scope was present all-scope (absent from `missing_from_install`) and so was never offered a `user`-scope install by `sync` Step 4 — silently breaking the "usable from any directory" guarantee for it. `sync.md` Step 4 now keys its user-scope install offer off the new field. The existing `missing_from_install` field and its all-scope semantics are unchanged. Chosen approach: the additive option from the issue (new field), not the redefinition option — no behavior change to any existing consumer. Beyond the literal instruction: `SKILL.md`'s report template ("Action needed") reference was also switched to `missing_from_user_install`, so the report and Step 4 name the same signal (safe — `missing_from_user_install` ⊇ `missing_from_install` always, since user-installed ⊆ all-installed). `scope-semantics.md`'s reference was deliberately left on `missing_from_install` — it documents the preserved all-scope field's rename-coverage semantics. **2 — per-plugin shape validation.** The shape check validated `.plugins` is an object but not that each entry is an array. A drifted non-array entry passed the check, then failed inside the installed-flatten `jq` pipeline in a command substitution; with `set -uo pipefail` but no `set -e` the failure was swallowed and the script exited **0** with `installed: []` instead of failing loud per its stated design. The check now also asserts `(.plugins | to_entries | all(.value | type == "array"))` and exits 2 on drift. **3 — `--marketplace` with no name.** `fleet-state.sh --marketplace` (no following arg) set `TARGET=""`, then `shift 2` failed silently (only one positional param left, no `set -e`), leaving `$1` unchanged so the arg loop re-read `--marketplace` forever; the post-loop `-z "$TARGET"` guard was never reached. The empty check now runs inside the `--marketplace` branch before `shift`, exiting 2. The now-dead post-loop guard was removed. ## Verification TDD: three regression cases were added and run **against the unfixed script first** to prove each bug, then the fixes were applied. Before (unfixed script — the three new cases red, proving each bug): ``` FAIL: user-scope: project-only + never-installed both surface, user-scope install excluded FAIL: user-scope: opt-out excluded from missing_from_user_install too FAIL: non-array plugin entry: exit 2 detail: expected exit 2, got 0 # #2: swallowed failure — exited 0 with installed:[] FAIL: --marketplace no arg: exit 2, not an infinite loop detail: expected exit 2, got 124 # #3: 124 = timeout killed the infinite loop FAIL: --marketplace no arg: actionable error ``` After (fixed script — full suite green): ``` PASS: --marketplace no arg: exit 2, not an infinite loop PASS: --marketplace no arg: actionable error 23 cases, 0 failed ``` `shellcheck` (both scripts) and `markdownlint-cli2` (all changed markdown) report clean: ``` SHELLCHECK CLEAN Summary: 0 error(s) ``` Closes #254 ## Related - Closes #254 — the tracking issue enumerating all three findings. - Follow-up from PR #248 (`feat/claude-ops-plugins-skill`), the origin review cycle where these three were verified VALID and deliberately deferred. - #797 — follow-up: `FLEET_STATE_HOOK_UTILS`'s test-only override isn't gated to test contexts at runtime. Pre-existing (unchanged by this PR), out of scope here — filed post-green per the lane's review-deferral rule. Co-authored-by: Claude Sonnet 5 <noreply@anthropic.com>
kyle-sexton
added a commit
that referenced
this pull request
Jul 21, 2026
Work item #3 body and the stress-test reversal summary still named --max-turns for the per-run mechanical bound, contradicting this note's own recorded deviation (--max-turns absent from the installed CLI; --max-budget-usd is the actual flag). Update both to --max-budget-usd so the active Phase 1 build path can't wire the nonexistent flag. Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_01Fgx6EDAL4cGAFwTNgLpsus
This was referenced Jul 21, 2026
kyle-sexton
added a commit
that referenced
this pull request
Jul 21, 2026
… recording tier, routines provenance (#845) ## Summary Absorbs the vetted ideas from the "4 Levels of Agentic Coding" video digest (Boris Cherny "Steps of AI Adoption" walkthrough) into the plugin estate, per the approved plan at `docs/topics/boris-video-absorption/PLAN.md`. - **testing 0.3.0 (minor):** `/testing:run-e2e` gains the consumer config surface `.claude/testing/e2e.md` (`recording: video|gif|off` default `off`; `browser_mode: headed|headless` default `headless`) with explicit read path, per-key merge + provenance reporting, and plumbing to the playwright executor; keys owned by new `context/e2e-config.md` (policy-vs-mechanics boundary; prompt > config precedence). Prerequisite hard-fail keeps STOP and adds a structured verification-environment gap report. Drive loop subagent-isolated; presence-gated `/verify`-first delegation (CC >=2.1.145). Evidence contract adds optional recording tier + session artifacts. Eval #1 updated. - **verification 0.3.2 (patch):** `/verification:confirm` delegation wording acknowledges the enriched run-e2e; stages/verdict machinery untouched. - **autonomy 0.8.0 (minor):** `reference/routines.md` gains the instruction-provenance clause — routine instruction content lives in a version-controlled artifact, stored prompt is a thin pointer; surface mappings are illustrative deployment-owned bindings. - Implementers-table row added in `docs/conventions/consumer-config-layering/README.md`. Coordination: zero file overlap with the ignition/enforcement lanes (#778 comment posted; ignition Phases 2–3 merged via #810). Defaults preserve current consumer behavior. ## Related No linked issue: this PR closes no GitHub issue. Related, not closed: - #778 — ignition lane coordination (comment posted; zero file overlap) - #810 — ignition Phases 2-3 (merged; separate lane) ## Verification - markdownlint: 0 errors on all touched files; typos gate exit 0 - `check-skill.sh`: run-e2e PASS, confirm PASS (pre-existing advisory warnings only) - run-e2e `evals/evals.json`: valid against bundled schema (ajv, draft2020) - Sanity greps per PLAN phase checks: all pass - Stage-structure invariant on confirm SKILL.md: 16 before/after <details> <summary>PLAN.md</summary> # PLAN — boris-video-absorption ## Brief Absorb the vetted ideas from the Ray Amjad "4 Levels of Agentic Coding" video digest (research base: `~/.work/youtube-watch/the-4-levels-of-agentic-coding-how-to-sh-XLA-sTSJ-Wc/`) into the plugin estate. Interview-locked contracts (this session): - Extend existing seams, no new skill: `testing:run-e2e` (driver) + `verification:confirm` (judge) keep their division of labor. - run-e2e gains: subagent-isolated surface runs; native-/verify-first delegation (presence-gated, CC ≥2.1.145); structured missing-environment gap report on prerequisite failure (hard-fail stays, plus actionable report); video/session-artifact evidence tier. - Recording format (video | gif | off) and browser mode (headed | headless) are layered config knobs per `docs/conventions/consumer-config-layering/` — NOT hardcodes. - `plugins/autonomy/reference/routines.md` gains a thin-pointer clause: routine/scheduled-task prompts on any surface point to version-controlled files; pasted prose non-compliant. - `~/.claude/scheduled-tasks/` (exists, live task) proposed for dotfiles tracking via the dotfiles repo's add-dotfile flow. - Deferred-with-trigger (recorded in digest slice, NO tracker issues): verification self-improvement loop (trigger: accumulated recorded runs); bounded build→review→fix loop (trigger: post-Phase-II enforcement rail); Claude Tag enablement (trigger: post-8/3 cutover + Enterprise admin check). - Out of scope: presenter-custom harness (Percy), chat-surface wiring, Chronicle adoption, lifecycle reordering. - Boris doc capture re-verified NO-DRIFT 2026-07-21; all adopted items trace to the doc's step 1→2/2→3 recipes or native CC features. Success: PRs merged with skill-quality + markdownlint green; every adopted behavior traceable to research findings; zero collision with the primary session's lanes (ignition Phases 2–3 merged via #810; no pending branch touches target files — verified). ## Standards grounding - `docs/conventions/consumer-config-layering/README.md` — three layers (user-global / team / local overlay), additive-preferred merge; new config surface must declare keys in the owning plugin's docs and point at the convention for layering. - `docs/CATALOG-TAXONOMY.md` + `docs/PLUGIN-PHILOSOPHY.md` — extend-over- add, seam cooperation presence-gated, fresh-eyes delegation. - Repo commit/PR conventions (conventional commits, codex thread resolution before merge, `--body-file -` for PR bodies). ## Plan ### Phase 1: Lane setup [DONE] - Create worktree off `origin/main`, branch `feat/boris-video-absorption` (sibling-worktree convention). - Materialize `docs/topics/boris-video-absorption/PLAN.md` (this file) + `design/design-resolution.md` (Tier B early-exit: no new types; one new config surface whose shape is resolved here — see Decisions). - Post coordination comment on #778: secondary session lane, files touched, no overlap with ignition/enforcement lanes. - **Sanity Check:** `git worktree list` shows the new worktree on the new branch; `gh issue view 778` shows the comment; PLAN.md exists in the worktree at `docs/topics/boris-video-absorption/PLAN.md`. ### Phase 2: run-e2e enrichment [DONE] Files: `plugins/testing/skills/run-e2e/SKILL.md`, `plugins/testing/skills/run-e2e/context/e2e.md`, `plugins/testing/README.md`, new `plugins/testing/skills/run-e2e/context/e2e-config.md` (key owner doc), `plugins/testing/skills/run-e2e/evals/evals.json` (eval #1 asserts the prerequisite-failure behavior this phase changes — update unconditionally), `plugins/testing/CHANGELOG.md` (Keep a Changelog entry; **minor** bump — new behaviors), `docs/conventions/consumer-config-layering/README.md` (Implementers-table row for the new surface — the convention tracks conformance, not assumes it). - Declare config surface `.claude/testing/e2e.md` (folder-form name per convention: surface identity = whole path relative to `.claude/`). Keys: `recording: video | gif | off` (default `off` — evidence contract screenshots stay the floor), `browser_mode: headed | headless` (default headless, operator overrides for visibility). Per-key override semantics. Layering resolution cites the convention doc — no restatement. - **Read path (reviewer gap #3 — mandatory):** SKILL.md gains explicit resolution instructions — anchor at repo root, read all three layers (user-global → team → local overlay), merge per-key, report which layer supplied each effective value. **Plumbing:** resolved `browser_mode` and `recording` are passed to the executor (`/playwright:playwright` invocation args / gif_creator choice) — keys without plumbing are the documented ai-briefing deviation; not repeating it. - **Key-ownership framing (reviewer risk #6):** e2e-config.md states the boundary — run-e2e owns capture POLICY (what evidence, which format, visibility preference); playwright owns MECHANICS (how the browser runs). Keys are policy inputs run-e2e resolves and passes through. - **Precedence (operator-locked):** config keys are DEFAULTS only; an explicit session prompt always wins ("run this headed" overrides `browser_mode: headless`). e2e-config.md states this: prompt > local overlay > team > user-global > bundled default. - SKILL.md: subagent-isolated run guidance (delegate the drive loop to a subagent; orchestrator consumes evidence paths only); /verify-first delegation note (presence-gated on bundled /verify, CC ≥2.1.145, with existing orchestrator fallback unchanged). - Prerequisite failure path: keep hard-fail STOP; add a structured verification-environment gap report (what's missing, what the operator must provide — keys/CLIs/environments; the "what do you need to verify this e2e" elicitation) written to the run's evidence output. - context/e2e.md evidence contract: add optional recording tier (video via playwright CLI preferred for long flows; GIF via gif_creator for short demos — driven by the `recording` key) + session artifacts row (recording path, session ID, transcript pointer) in the evidence table. - **Sanity Check:** `rg -c "e2e-config|\.claude/testing/e2e\.md" plugins/testing/skills/run-e2e/SKILL.md` ≥ 1; `rg -c "gap report" plugins/testing/skills/run-e2e/SKILL.md` ≥ 1; `rg -c "recording" plugins/testing/skills/run-e2e/context/e2e.md` ≥ 2; **read-path present:** `rg -c "layer" plugins/testing/skills/run-e2e/SKILL.md` ≥ 2 AND `rg -c "browser_mode" plugins/testing/skills/run-e2e/SKILL.md` ≥ 2 (resolution + plumbing sites); Implementers-table row: `rg -c "testing/e2e" docs/conventions/consumer-config-layering/README.md` ≥ 1; CHANGELOG entry present; eval #1 updated (`rg -c "gap" plugins/testing/skills/run-e2e/evals/evals.json` ≥ 1); markdownlint exit 0 on changed files; `/skill-quality:check run-e2e` PASS. ### Phase 3: confirm delegation touch-up [DONE] Files: `plugins/verification/skills/confirm/SKILL.md`, `plugins/verification/README.md` (only if wording drifts), `plugins/verification/CHANGELOG.md` (**patch** bump — wording touch-up). - Delegation section: acknowledge enriched run-e2e (subagent isolation + recording/session evidence tier + gap report); /verify stays named as the supplementary live-run path with unchanged presence gate. No structural change to stages or verdict machinery. - **Sanity Check:** `rg -c "gap report|recording" plugins/verification/skills/confirm/SKILL.md` ≥ 1; stage structure unchanged (`rg -c "Stage" plugins/verification/skills/confirm/SKILL.md` equal before/after); markdownlint exit 0. ### Phase 4: routines.md thin-pointer clause [DONE] Files: `plugins/autonomy/reference/routines.md`, `plugins/autonomy/CHANGELOG.md` (**minor** bump — new normative clause). - New subsection, phrased to honor the doc's hosting-agnosticism (reviewer risk #7): the NORMATIVE clause is surface-agnostic — "a routine's instruction content lives in a version-controlled, reviewable artifact; the stored prompt is a thin pointer to it; pasted-prose prompts are non-compliant (no history, invisible drift)". The surface-specific mappings (cloud routines → committed `.claude/skills/`, documented transfer path; Desktop scheduled tasks → `~/.claude/scheduled-tasks/<task>/SKILL.md` under dotfiles) appear only as ILLUSTRATIVE binding examples, marked as deployment-owned bindings per the doc's own Hosting stance. Cite research (`routines-versioning-deep-dive.md`: native prompt versioning documented-absent). If the clause reads better in `wiring-vs-advisor.md` at build time, the builder flags it back to the main thread rather than deciding — placement objection is the known review risk. - **Sanity Check:** `rg -c "thin pointer|version-controlled" plugins/autonomy/reference/routines.md` ≥ 2; agnosticism preserved: `rg -c "deployment-owned" plugins/autonomy/reference/routines.md` count increases by ≥1; markdownlint exit 0; CHANGELOG entry present. ### Phase 5: digest-slice deferred items + through-line [DONE] Files (home slice, not repo): `~/.work/youtube-watch/the-4-levels-of-agentic-coding-how-to-sh-XLA-sTSJ-Wc/recommendations/menu.md`, `README.md` (same slice). - Update menu items to final dispositions (adopted → PR refs; deferred → named triggers; no-go unchanged). Add through-line note: Boris doc → interview locks → PLAN → PRs. - **Sanity Check:** `rg -c "deferred" menu.md` ≥ 3; each adopted item carries a PR/branch reference. ### Phase 6: dotfiles tracking proposal [TODO — user gate] - Run the dotfiles repo's `add-dotfile` flow for `~/.claude/scheduled-tasks/` (dir exists with live `autonomy-demo-hourly-drain/`). Flow owns chezmoi mechanics; never `chezmoi apply` from agent context. - **Sanity Check:** dotfiles repo PR/branch exists containing the scheduled-tasks source state, or an explicit operator decline recorded in PLAN. - **User gate:** surfaces before executing (cross-repo write). ### Phase 7: verify + ship [TODO] - Empirical verification in worktree: markdownlint sweep, typos gate, `/skill-quality:check` per touched skill, eval validation. - Version bumps via Edit on the version line (biome retab gotcha). - Conventional commits; PR(s) with PLAN.md in `<details>`; codex threads resolved before merge; close-out per `/planning:plan close-out` (slice prune + pointer). - **Sanity Check:** CI green on PR; `gh pr view` shows mergeable; all phase tags [DONE]. ### Phase 8: trial run (post-merge validation) [TODO] - After plugins update, run the enriched flow end-to-end on a real UI change in a consumer repo: config surface resolved + reported, recording produced per key, gap report exercised (remove a prereq deliberately), evidence table carries session artifacts. - **Sanity Check:** recording artifact exists on disk; gap report emitted on induced prereq failure; operator reviews the recording. ## Blast radius LOW-MEDIUM. Markdown skill/contract text + one new additive config surface; zero runtime code; three plugins touched; consumers unaffected by default (recording defaults off, browser_mode default preserves current behavior). Cross-repo edge: dotfiles proposal (user-gated). ## Stress-test summary Fresh-context plan-reviewer ran against live repo. 3 CONFIRMED-GAPs folded: (1) phantom config surface — read-path resolution + executor plumbing now mandated in P2 with sanity greps; (2) Implementers-table row added to P2 files; (3) CHANGELOG entries added to P2/P3/P4 with SemVer magnitudes (testing minor, verification patch, autonomy minor). Risks addressed: key-ownership boundary framed policy-vs-mechanics in e2e-config.md; routines.md clause re-phrased surface-agnostic with bindings as illustrative examples; eval #1 update made unconditional. Collision re-verified clean (no open PR overlap). Formal /devils-advocate skipped: blast radius LOW-MEDIUM, no infra/CI/dependency triggers. ## Execution shape Wave A (parallel, file-disjoint, one worktree, agents never touch git): | Phase | Surface | Basis | |---|---|---| | 2 run-e2e | Opus builder subagent | mechanical doc edits, largest item | | 3 confirm | Opus builder subagent | small disjoint edit | | 4 routines | Opus builder subagent | small disjoint edit | Wave B (sequential, main thread): 5 (home slice), 6 (user-gated cross-repo), 7 (verify + ship — main thread only, empirical checks + git). Phase 1 precedes all. Scope fences: each builder gets an ALLOWED list = its phase's files; FORBIDDEN = PLAN.md, other phases' files, any git command. Cost: 3 builders vs sequential saves modest wall-clock; fallback = run 2→3→4 sequentially in main thread on any fence violation. ## Open questions None blocking — all interview-locked. ## Handoff to implementation ### User-approval gates - Phase 6 dotfiles add-dotfile run (cross-repo write). - Any mid-flight scope change to config-surface shape. ### Execution shape ([EXEC-SHAPE] tagged) - [EXEC-SHAPE] PLAN drafted in `.work/` first; materialized to `docs/topics/` inside the worktree at Phase 1 (avoids writing to the canonical checkout the primary session owns). - [EXEC-SHAPE] Wave A 3-builder parallel shape with scope fences as above; sequential fallback documented. - [EXEC-SHAPE] Single PR for phases 2–4 (one review surface, shared rationale) unless review load argues for a split at ship time. ### Mechanical work - Commit boundaries: Phase 1 (PLAN + design-resolution), one commit per phase 2–4, Phase 5 lives outside the repo (no commit), Phase 7 ship. - Verification checkpoints: markdownlint + typos + skill-quality per phase before its commit; empirical greps per Sanity Checks. - Sequential fallback: any fence violation → abandon parallel, re-run remaining phases in main thread. </details> 🤖 Generated with [Claude Code](https://claude.com/claude-code) https://claude.ai/code/session_01QdCmaHa15bwUTh9sy7Rfdz --------- Co-authored-by: Claude Fable 5 <noreply@anthropic.com>
kyle-sexton
added a commit
that referenced
this pull request
Jul 21, 2026
) ## What Sharpens the `orchestrate` skill's per-worker tiering (imperative 7) into an explicit **volume-based default**, and broadens "tier" from model-only to model **and** reasoning effort. ## Why Carried from the re-anchor round-2 ledger (task #3), observed in production: an `/orchestrate` run fanned out ~100–200 agents, all on the top-tier model. PR #340 (0.9.1) fixed the root spawn-inherit bug — SPEC EVERY SPAWN + CALIBRATE now carry a per-worker tier — but the residual enhancement (making the tier *default* flip on volume) was never built. The prior text stated the direction as a gradient ("the wider the fan-out, the cheaper the default per-worker tier") without wiring the verify/judge carve-out as the standing exception, and never named reasoning effort as a tiering lever. ## Change `plugins/session-flow/skills/orchestrate/SKILL.md` — imperative 7: - Past a wide fan-out, the cheaper tier is now the **DEFAULT the whole fleet inherits** (volume multiplies every notch of over-provisioning). - The **standing exception** is an explicitly hard stage — verify, judge/adjudicate, judgment-heavy synthesis — which keeps the parent tier. A premium fan-out outside those stages is a per-stage decision to justify, never a default to inherit. - **Tier is model AND effort**: match reasoning depth (effort), not just the model, to the subtask. `context/sources.md` — three new verbatim citations grounding the change in current official docs: the per-worker `effort` frontmatter lever, the workflow fleet-model inherit mechanism, and the platform's own wide-run threshold (its `Large workflow` warning + `/config` size guideline). Per the skill's model-/tool-agnostic construction, these version-pinned specifics stay in `sources.md`, never the imperatives or export brief. ## Grounding (fresh docs, this session) - Subagent `model` precedence + `inherit` default, `effort` field, cost-routing guidance — <https://code.claude.com/docs/en/sub-agents> - Workflow fleet-model inheritance, per-stage routing, `Large workflow` threshold + size guideline — <https://code.claude.com/docs/en/workflows> ## Gates - `check-skill.sh orchestrate`: PASS (7/7 trigger phrases preserved, 125/500 lines, markdownlint clean) - `check-changelog-parity.sh --check` and `--check-bump origin/main`: PASS - `validate-plugin-contracts.mjs`, `generate-catalog.mjs --check`, `claude plugin validate .`: PASS - Version bumped 0.12.2 → 0.12.3 with CHANGELOG entry in the same diff. ## Related - PR #340 — the session-flow 0.9.1 spawn-inherit fix this builds on (SPEC EVERY SPAWN + CALIBRATE carrying a per-worker tier); not closed by this PR. - The re-anchor round-2 ledger task #3 production observation that motivated the residual enhancement. Closes #863. Co-authored-by: Claude Fable 5 <noreply@anthropic.com>
This was referenced Jul 22, 2026
This was referenced Jul 22, 2026
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
First plugin migrated from medley into this marketplace — the pilot proving the end-to-end lift-and-shift pipeline.
What's in this PR
plugins/markdown-formatter/**— ported PostToolUse hook (markdownlint-cli2 on Write/Edit), bundledhook-utils.shsubset, black-box contract test (12/12), README (16faf60)..editorconfig+.shellcheckrc— platform drop-in configs (5bb2e77)..claude-plugin/marketplace.json— catalog entry making the plugin installable (was empty).README.md— catalog section listing the plugin.docs/MIGRATION-PLAYBOOK.md— step 10 records the./-prefixed source requirement + catalog-manifest validation.Verified
claude plugin validate --strict✔ on both the plugin and the marketplace manifest.--plugin-dirload smoke + source-repo parity (fresh-context) PASS.--plugin-dirand strict-validate do not exercise what a real marketplace install does: relative-source resolution (./plugins/markdown-formatter) and hook firing from the cache copy (~/.claude/plugins/cache). Prove both from this branch ref before merging:/plugin marketplace add https://github.com/melodic-software/claude-code-plugins.git#feat/markdown-formatter-plugin /plugin install markdown-formatter@melodic-software /reload-plugins # edit a .md with a fixable issue → confirm markdownlint-cli2 auto-fixesThis closes the recorded open gap (live in-session PostToolUse fire via an installed plugin). Merge → final user/global install from
main.Note: dropped
metadata.pluginRoot—claude plugin validate --strictrejects the bare source it is meant to enable, despite the marketplaces-doc example.