docs: wire /brevity into Tide working agreements - #92
Merged
Conversation
PR #89 landed the brevity skill with user-invocation routing. Layer 2: proactive use by referencing the skill in Tide's top-level working agreements so agents apply it without explicit user invocation. - CLAUDE.md: one bullet under Working Agreements, matching section cadence (25 words, imperative). - AGENTS.md: one paragraph under Working Agreement covering all 15 agents in the roster. Surface scoped to PR descriptions + in-code comments (matches the skill's MVP); deferred surfaces (doc/design, runbooks, memory writes, mid-conversation chat) enumerated explicitly with a pointer to references/guardrails.md. Skip language inverted on coral feedback: "The skill self-determines floor; agents do not pre-skip." Removes the bypassable threshold. Coral cross-review (product-engineer + reviewer): two HOLD findings (design-notes scope expansion + bullet length) resolved; cleared. Follow-ups tracked: - #90: portable-scrub + sync to user-scope (after 2 real-use cycles) - #91: persona-line /brevity reference in each .claude/agents/ file for sub-agent dispatch coverage Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>
PR SummaryLow Risk Overview
No runtime, registry, or interface contract changes—policy text only. Reviewed by Cursor Bugbot for commit 0589794. Bugbot is set up for automated code reviews on this repo. Configure here. |
4 tasks
bdchatham
added a commit
that referenced
this pull request
Jun 1, 2026
…greement-wired Pivot per Brandon's "targeted and effective, no bloat" framing. The original v1 shipped a GitHub Actions workflow + 8 bash scripts + claude-code-action invocation + state directory + concurrency group + cost guardrail + self-consistency + anchored marker + hash dedupe + 5-finding cap. The action failed-closed on its own introduction PR because the Claude Code App wasn't installed on the repo — the inverse of the suggestive-only intent. Pivot: - Drop ALL CI infrastructure - Agent-invoked + user-invocable, no claude-code-action - Working-agreement reference in CLAUDE.md + AGENTS.md (same pattern as /brevity layer 2; PR #92) ## Final shape (8 files, 393 lines) .claude/skills/pr-quality/ ├── SKILL.md (88 lines) ├── references/ │ ├── rule-registry.md (87 — locked v1 set + 2 │ │ mechanical specs inline + │ │ deferred mechanisms with │ │ un-defer triggers) │ ├── format-spec.md (41) │ └── judges/ │ ├── narration_comments.md (33) │ ├── temporary_migration_notes.md (38) │ └── authoritative_voice.md (33) ├── scripts/ │ ├── scan-yaml-cpu.sh (39 — stateful awk, indent │ │ + parent-block tracking, │ │ multi-container aware) │ └── scan-harbor-ghcr.sh (34 — unified-diff state │ machine) └── evals/evals.json (happy + halt + pressure) ## Two invocation modes **Pre-PR (agent-fired)**: before `gh pr create`, agent runs /pr-quality against the staged diff + planned body. Findings surface inline for revision. No comment posted. **Post-PR (user-invocable)**: /pr-quality <PR> reads the existing PR via gh, dispatches the v1 judges, posts a fresh comment with findings. No comment on zero findings. ## Composition with /brevity Verbosity dimension dispatches /brevity via subagent-loads-target-skill (same pattern as /coral, /council). The verbosity judge in references/judges/ is intentionally NOT a re-implementation of brevity's rules — pr-quality detects the trigger, brevity owns the standard. PE flagged the coupling risk in scope review; the boundary is preserved. ## Deletions (was CI ceremony) - .github/workflows/pr-quality.yml - 9 scripts (check-optout, check-pr-size, fetch-context, dispatch-judges, aggregate, render-comment, post-or-update, judge-llm, judge-skill-dispatch — plus the now-split judge-mechanical) - scripts/README.md - references/guardrails.md (CI-specific content; what remained fits in SKILL.md guardrails stanza) - references/judge-prompt-template.md (without self-consistency, the structured-output contract collapses to 5 fields — inlined into rule- registry's per-judge schema) - references/judges/no_cpu_limits.md, harbor_ecr_convention.md (mechanical specs are in the script + 1 row in rule-registry) - state/.gitkeep (no state worth persisting; closer to a thin orchestrator than a stateful procedure) ## Working-agreement wiring (same-PR per layer-2 pattern) CLAUDE.md ## Working Agreements gains: - **PR-quality discipline:** Before invoking `gh pr create`, apply /pr-quality to the staged diff + planned body. Findings surface inline for revision. Post-PR: invoke /pr-quality <PR> to post a fresh comment with findings. (Brevity runs during authoring; pr-quality runs on the final diff — they don't chain.) AGENTS.md ## Working Agreement gains a parallel "Pre-PR review" paragraph after the existing "Output discipline" entry. ## Deferred mechanisms (un-defer triggers in rule-registry.md) - Self-consistency (n=3 sampling) → first real false-positive - 5-finding cap + severity rank → first PR producing >7 findings - Anchored marker + hash dedupe → first comment-spam complaint - Cost ceiling per PR → first session budget overrun Coral panel reviewed the trim plan: PE CLEAR, reviewer CLEAR (3 small adjustments incorporated), PM NEW with harder cuts (all incorporated; Brandon explicitly retained pre-PR mode as the customer override). Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>
bdchatham
added a commit
that referenced
this pull request
Jun 1, 2026
* feat(skills/pr-quality): post-PR coordinator + GitHub Action Closes #88. Adds .claude/skills/pr-quality/ — a procedural coordinator skill that runs on pull_request: opened/synchronize/reopened, dispatches a fixed v1 judge set in parallel, and posts a single anchored PR comment with up to 5 findings ranked by severity. Suggestive only — never gates merge. Silence is the success state on clean PRs. ## v1 scope (locked by coral scope-cut) Dimensions: 2 (verbosity dispatches /brevity; convention adherence with 5 specific memory-encoded rules). Deferred dimensions (docs completeness, reference drift, commit message hygiene) carry un-defer triggers in references/rule-registry.md. Rules: - no_cpu_limits (mechanical YAML scan, awk indent + parent-block aware) - harbor_ecr_convention (mechanical diff-state-machine grep) - narration_comments (LLM-judged, function-doc style only, n=3 SC) - temporary_migration_notes (LLM-judged, durable docs only) - authoritative_voice (LLM-judged, .claude/skills/**/*.md only) - /brevity dispatch on PR body via skill-loaded subagent ## Architecture GitHub Action only (no local-invocable surface in v1). Workflow at .github/workflows/pr-quality.yml with: - Per-PR concurrency group + cancel-in-progress - Fork-PR guard (forks have read-only token; explicit skip rather than pull_request_target footgun) - ANTHROPIC_API_KEY pre-check (env-scoped, no template leak) - Artifact upload of full state for debugging Composition: subagent loads target skill (same pattern as /coral, /council). No skill-to-skill registry invented. ## Comment model Anchored marker `<!-- tide-pr-quality | sha=<SHA> | findings-hash=<H> -->`. - No prior + findings count == 0 → no comment posted (no thumbs-up) - No prior + findings > 0 → create new - Prior + hash matches → no-op (no churn on identical re-runs) - Prior + hash differs → PATCH in place - Prior + findings count == 0 → DELETE prior (clean PR after fixes) ## Cross-review product-engineer + reviewer + product-manager cleared after 2 review cycles. Round 1 HOLDs addressed: - Missing judge scripts (judge-mechanical.sh, judge-llm.sh, judge-skill-dispatch.sh) — written - JSON contamination via undisciplined stdout — every judge writes JSON to stdout only, logs to stderr via log() { ... >&2; } - Fork-PR write-permission reality — workflow guard added - SKILL.md step 6 vs format-spec rendering mismatch — SKILL.md defers to format-spec.md as single source of truth Round 2 HOLDs addressed: - no_cpu_limits awk was structurally broken on stdin/FILENAME — rewrote with proper file-arg + indent + parent-block tracking; PyYAML branch rejected per PE for multi-container miscite + early-return bugs (YAGNI) - Workflow secret-leak via template interpolation — switched to env: + ${ANTHROPIC_API_KEY:-} guard - judge-llm.sh --arg ARG_MAX risk — switched to --rawfile streaming ## Follow-ups (tracked in rule-registry.md un-defer triggers) - Documentation completeness dimension — un-defer on first missing-doc reviewer flag - Reference drift dimension — un-defer on first stale wikilink causing confusion - Commit message hygiene dimension — un-defer on first non-CC commit on main - Acceptance criterion deferred: dry-run on last 10 PRs (do post-merge) Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com> * refactor(skills/pr-quality): drop CI infra; agent-invoked + working-agreement-wired Pivot per Brandon's "targeted and effective, no bloat" framing. The original v1 shipped a GitHub Actions workflow + 8 bash scripts + claude-code-action invocation + state directory + concurrency group + cost guardrail + self-consistency + anchored marker + hash dedupe + 5-finding cap. The action failed-closed on its own introduction PR because the Claude Code App wasn't installed on the repo — the inverse of the suggestive-only intent. Pivot: - Drop ALL CI infrastructure - Agent-invoked + user-invocable, no claude-code-action - Working-agreement reference in CLAUDE.md + AGENTS.md (same pattern as /brevity layer 2; PR #92) ## Final shape (8 files, 393 lines) .claude/skills/pr-quality/ ├── SKILL.md (88 lines) ├── references/ │ ├── rule-registry.md (87 — locked v1 set + 2 │ │ mechanical specs inline + │ │ deferred mechanisms with │ │ un-defer triggers) │ ├── format-spec.md (41) │ └── judges/ │ ├── narration_comments.md (33) │ ├── temporary_migration_notes.md (38) │ └── authoritative_voice.md (33) ├── scripts/ │ ├── scan-yaml-cpu.sh (39 — stateful awk, indent │ │ + parent-block tracking, │ │ multi-container aware) │ └── scan-harbor-ghcr.sh (34 — unified-diff state │ machine) └── evals/evals.json (happy + halt + pressure) ## Two invocation modes **Pre-PR (agent-fired)**: before `gh pr create`, agent runs /pr-quality against the staged diff + planned body. Findings surface inline for revision. No comment posted. **Post-PR (user-invocable)**: /pr-quality <PR> reads the existing PR via gh, dispatches the v1 judges, posts a fresh comment with findings. No comment on zero findings. ## Composition with /brevity Verbosity dimension dispatches /brevity via subagent-loads-target-skill (same pattern as /coral, /council). The verbosity judge in references/judges/ is intentionally NOT a re-implementation of brevity's rules — pr-quality detects the trigger, brevity owns the standard. PE flagged the coupling risk in scope review; the boundary is preserved. ## Deletions (was CI ceremony) - .github/workflows/pr-quality.yml - 9 scripts (check-optout, check-pr-size, fetch-context, dispatch-judges, aggregate, render-comment, post-or-update, judge-llm, judge-skill-dispatch — plus the now-split judge-mechanical) - scripts/README.md - references/guardrails.md (CI-specific content; what remained fits in SKILL.md guardrails stanza) - references/judge-prompt-template.md (without self-consistency, the structured-output contract collapses to 5 fields — inlined into rule- registry's per-judge schema) - references/judges/no_cpu_limits.md, harbor_ecr_convention.md (mechanical specs are in the script + 1 row in rule-registry) - state/.gitkeep (no state worth persisting; closer to a thin orchestrator than a stateful procedure) ## Working-agreement wiring (same-PR per layer-2 pattern) CLAUDE.md ## Working Agreements gains: - **PR-quality discipline:** Before invoking `gh pr create`, apply /pr-quality to the staged diff + planned body. Findings surface inline for revision. Post-PR: invoke /pr-quality <PR> to post a fresh comment with findings. (Brevity runs during authoring; pr-quality runs on the final diff — they don't chain.) AGENTS.md ## Working Agreement gains a parallel "Pre-PR review" paragraph after the existing "Output discipline" entry. ## Deferred mechanisms (un-defer triggers in rule-registry.md) - Self-consistency (n=3 sampling) → first real false-positive - 5-finding cap + severity rank → first PR producing >7 findings - Anchored marker + hash dedupe → first comment-spam complaint - Cost ceiling per PR → first session budget overrun Coral panel reviewed the trim plan: PE CLEAR, reviewer CLEAR (3 small adjustments incorporated), PM NEW with harder cuts (all incorporated; Brandon explicitly retained pre-PR mode as the customer override). Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com> --------- Co-authored-by: Claude Opus 4.7 <noreply@anthropic.com>
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.
Layer 2 of the staged brevity roll-out (#86 → #89 → this).
Diff (3 lines)
CLAUDE.md## Working Agreementsgains:AGENTS.md## Working Agreementgains:Why
/brevity(PR #89) handles user-invocation routing via SKILL.md description. But proactive use — agents pre-applying brevity before drafting a PR body, without being asked — requires explicit wiring. Caveman'sSessionStart+UserPromptSubmithook approach was rejected on trust-boundary grounds (#86 coral synthesis). This PR is the cheapest version of proactive wiring: working-agreement references in the two top-level project conventions docs.Coral cross-review
product-engineer + reviewer reviewed once with two HOLDs:
design noteswidens surface beyond skill's MVPAll addressed. Re-review: both CLEAR.
Follow-ups (tracked durably)
PORTABLEinscripts/sync-skills.sh. Un-defer trigger: 2 real-use cycles complete, no rule additions needed./brevityreference to each.claude/agents/*.mdpersona so sub-agent dispatch viaAgenttool reliably picks up the discipline (PE flagged the gap in this layer's review).Test plan
product-engineerorkubernetes-specialist) to draft a PR body for a fake-but-realistic 5-file refactor. Verify the sub-agent references / applies brevity even though no user phrase like "tighten this" appears.🤖 Generated with Claude Code