fix: structural mismatches in workspace directories#1
Merged
Auto-Skiller merged 1 commit intoApr 23, 2026
Merged
Conversation
- Created missing root directories: `scripts/` and `_archive/` - Created missing management/archive directories in `_projects/` and `_pipelines/` - Created missing `INDEX.md` files for `agents/`, `knowledge/`, `skills/`, `commands/`, `rules/`, and `templates/` to match `INDEX.md` spec - Added `.gitkeep` to track empty newly created directories - Updated `BOARD.md` to track outstanding tasks to restructure domain/nested directories Co-authored-by: Auto-Skiller <253765279+Auto-Skiller@users.noreply.github.com>
Contributor
|
👋 Jules, reporting for duty! I'm here to lend a hand with this pull request. When you start a review, I'll add a 👀 emoji to each comment to let you know I've read it. I'll focus on feedback directed at me and will do my best to stay out of conversations between you and other bots or reviewers to keep the noise down. I'll push a commit with your requested changes shortly after. Please note there might be a delay between these steps, but rest assured I'm on the job! For more direct control, you can switch me to Reactive Mode. When this mode is on, I will only act on comments where you specifically mention me with New to Jules? Learn more at jules.google/docs. For security, I will only act on instructions from the user who triggered this task. |
Auto-Skiller
pushed a commit
that referenced
this pull request
May 18, 2026
Three deliverables in one commit, all triggered by the simulation findings:
────────────────────────────────────────────────────────────────────
1) H-LAW-015 revised — Source Quality Bar is now agent-judged
────────────────────────────────────────────────────────────────────
Sim 1 surfaced regex misses on real Darija transcripts: 2 of 23 sources
got REJECTED purely because the keyword list didn't match Arabic content
that was unambiguously Algerian Facebook Ads material. Revised the rule:
- Scoring authority is now SEMANTIC, not regex/keyword.
- The agent reads each source end-to-end and assigns booleans against
a per-criterion rubric (Recency, Authority, Specificity, Relevance,
Completeness). Each boolean carries a 1-sentence rationale citing
concrete evidence from the source.
- Crucial detail in the Specificity rubric: 'the constraint may be
implicit and non-English' — closes the false-negative gap exactly.
- New ledger schema for quality_scoring includes scored_by:
agent_semantic. Any cascade reading scored_by != agent_semantic
must re-score before counting.
- Old regex-based scaffold in sim_runner.py marked DEPRECATED but
kept verbatim so the original Sim 1 report stays reproducible.
────────────────────────────────────────────────────────────────────
2) Audit Pass loop closed — DRIFT 5 → 0
────────────────────────────────────────────────────────────────────
Sim 2 (Audit Pass dry-run) found 5 DRIFT entries against historical
archived cards. Triage revealed:
- 3 false-positives in the simulator's MOVE handling (it checked
MOVE source paths as if they were destinations). Fixed in
sim_runner.py.
- 8 real path supersessions across 4 historical cards. The CREATE/EDIT
targets were correct at integration time, but later cards refactored
the locations without leaving forward-pointers.
Drafted MEGA-INT-AUDIT-REMEDIATION-2026-05-18 (the exact card the rule
predicted would be auto-drafted on DRIFT). Direct-archived per Fresh
Start Law since it ran in EXECUTION mode. Annotates each historical
card in-place with a superseded_by_path_changes[] block:
HUSTLER-V53-TEMPLATE-MIGRATION → 3 supersessions (state, ledgers, naming)
LEDGERS → 1 supersession (master ledger split)
SCALER-RUNBOOKS-V52-ALIGNMENT → 3 supersessions (_scaler_runbooks rename)
SCALER-STRUCTURE-V53-RELINK → 5 supersessions (same rename, intra-card)
Updated sim_runner.py Check #1 to consult the supersession block and
skip drift-flagging on annotated original_paths. Re-ran the simulator
end-to-end:
Sim 2 verdict: DRIFT (5) → WARN (15)
The 15 WARN findings are pre-P-LAW-020 provenance gaps. By design,
WARN-only — they cannot be retroactively required.
This is the eat-our-own-dogfood validation of the Audit Pass workflow.
The rule found real archive inconsistency, predicted the remediation
shape, and the remediation closed the loop deterministically.
────────────────────────────────────────────────────────────────────
3) Three polished READMEs
────────────────────────────────────────────────────────────────────
Rewrote root README.md and _pipelines/_scaler/README.md, created
_pipelines/hustler/README.md from scratch. Voice shift from inward
('substrate', 'metabolic engine') to outward — concrete, opinionated,
oriented around what a human deciding whether to use this needs to
see in the first 30 seconds:
- Root: 'a substrate, not an agent'. Pain/gain table, two-pipeline
diagram, file-tree maps, agent-vs-human boot sequences.
- Scaler: pain points → P-LAW responses, granular gateway profiles
table, 7 integration types, 20 P-LAWs in plain English, real
cycle-trigger commands.
- Hustler: cascading decision tree drawn out, C1-C5 boundary
signals, 5-phase summary, 15 H-LAWs, lineage_graph schema, audit
pass scope, isolation contract reaffirmed.
All three READMEs cross-link consistently and lead the reader by hand
from 'what is this?' to 'how do I trigger a cycle?'.
────────────────────────────────────────────────────────────────────
Side-effects
────────────────────────────────────────────────────────────────────
~85 routine sync reformats across toolbox/router YAMLs (line wrap and
timestamp updates only). proposals_ledger summary updated to 15 resolved.
Final meta_sync.py: 0 warnings, 0 errors. Sim 2 final verdict: WARN.
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.
This PR aligns the actual file structure with the specifications laid out in the root
INDEX.md.It adds the missing index files, scaffolds out missing core directories (tracked via
.gitkeep), and records the remaining larger refactor tasks (moving nested directories to flat, and flat to domain partitions) to theBOARD.mdactive goals list.PR created automatically by Jules for task 16426321294777757845 started by @Auto-Skiller