Coding policy tile for Baruch's AI agents. Language-agnostic code quality rules plus Tessl-specific plugin authoring standards — covering commits, testing, error handling, skill structure, script delegation, and eval quality.
- 16 always-on steering rules: 8 covering code quality, 5 covering plugin authoring, 1 covering author-model declaration, 1 covering concurrency, 1 covering review discipline
releaseskill — structured PR + merge workflow with Copilot review and paired-reviewer cross-family enforcementeval-authoringskill — generate, review, and curate eval scenarios with score-driven iterationinstall-reviewerskill — scaffold the paired gh-aw PR review workflows (OpenAI + Anthropic) into a consumer repo- 0.3.0 added
install-reviewerupgrade mode (--override) — refreshes scaffolded reviewer files in place instead of requiring a manualgit rm-and-rerun - 0.2.0 lifted with-context attainment from 93 to 98 (3× avg, lift +17 → +22) by tuning skill prose against eval log analysis
- Language-agnostic: works with any stack, no Python/JS assumptions
See CHANGELOG.md for full version history.
tessl install jbaruch/coding-policy
| Category | Rule | Summary |
|---|---|---|
| Git | commit-conventions | Imperative mood, one change per commit, PR hygiene |
| Testing | testing-standards | Outcome-based, deterministic, no binary fixtures |
| Errors | error-handling | Specific exceptions (with outer-boundary process-contract carve-out), actionable messages, structured logging |
| Deps | dependency-management | Stdlib-first, pinned versions, lock files |
| Files | file-hygiene | Proper .gitignore, no generated files committed |
| CI | ci-safety | Never skip tests, never modify CI without asking |
| Secrets | no-secrets | No credentials in code, env vars or secrets manager |
| Style | code-formatting | Use project's formatter, don't mix style with logic |
| Authoring | context-artifacts | Plugin structure, rule format, review iteration, surface sync, consistency checks |
| Authoring | skill-authoring | SKILL.md structure, step numbering, typed calls, tile.json reference |
| Authoring | script-delegation | Deterministic → script, reasoning → LLM, the regex trap |
| Authoring | plugin-evals | No bleeding, no leaking, persistent eval coverage |
| Authoring | stateful-artifacts | Cross-invocation state: schema, owner skill, schema_version, hints-not-authority, migration |
| Review | author-model-declaration | PRs declare author model; paired reviewers pick the cross-family one |
| Concurrency | agent-worktree-isolation | Mandatory git worktrees for concurrent agent work; cleanup; read-only exception |
| Discipline | boy-scout | Leave it better than you found it; "pre-existing" is not a valid concept; in-scope cleanups bundle, out-of-scope ones get filed |
| Skill | Description |
|---|---|
| release | PR creation, Copilot review, merge + cleanup workflow |
| eval-authoring | Generate, review, iterate on eval scenarios with score-driven feedback |
| install-reviewer | Scaffold the paired gh-aw PR review workflows (OpenAI + Anthropic) into a consumer repo — reviews every PR against the latest published jbaruch/coding-policy with cross-family enforcement. Supports --override for in-place upgrades. |
- Language-agnostic code rules. The code quality rules (commits through formatting) apply to Python, TypeScript, Go, Rust, Java — any language. No framework-specific assumptions.
- Tessl-specific authoring rules. The authoring rules (context-artifacts through plugin-evals) are specific to the Tessl plugin workflow. They codify how to build, test, and ship tiles.
- One concern per rule. Each file covers one topic. Easy to read, easy to reference, easy to override if a project needs an exception.
- Opinionated but practical. These rules reflect real patterns found across 17+ repositories and the Tessl plugin authoring workflow. They solve problems that actually come up when agents write and ship code.
- Always on. Every rule is
alwaysApply: true. Agents follow these conventions without being reminded.