feat: restore tier-2 salvage items across nine plugins#192
Merged
Conversation
Restores owner-approved pre-migration behavior and guidance dropped at the medley cutover (salvage sweep items #2-#12 and drift items D1-D4), each genericized to the marketplace's repo-agnostic seams: - claude-config-audit 0.4.0: pre-computed context blocks (3 skills) + allowed-tools scoping, all paths via ${CLAUDE_PLUGIN_ROOT} - event-storming 0.3.0: design-level missing-prerequisite guard + eval; bare memory refs now use the ${CLAUDE_PLUGIN_DATA}/history.jsonl seam - planning 0.9.0: agent-team composition guidance in /architect Step 4.5; baseline capture routes to verify-improvement SSOT; devils-advocate regains the verify-changes pointer - session-flow 0.4.0: retro ecosystem-improvement catalog (hook-event table reconciled against current docs); handoff failure-pattern gotchas - review-toolkit 0.5.0: normalization-pipeline model assignment - implementation 0.5.0: optional tool-pin drift warning in /lint (+ ecosystem-commands contract 1.1.0 schema key); /implement over-correction trap logs to the session retro when installed - codebase-audit 0.2.0: background/unattended Phase 1 fan-out variant - code-tidying 0.4.0: stdlib-only frontmatter-fence integrity check - prototype 0.2.1: composition table + named handoff seam Per-plugin version bumps and CHANGELOG entries throughout; all nine plugins pass claude plugin validate, catalog passes --strict. Co-Authored-By: Claude Fable 5 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_011xHkkNc7CR98L8Xz9Mu7ZA
|
Claude finished @kyle-sexton's task in 1s —— View job I'll analyze this and get back to you. |
There was a problem hiding this comment.
💡 Codex Review
Here are some automated review suggestions for this pull request.
Reviewed commit: c3e192c7df
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".
… availability gating - event-storming: --design-level BC-name prerequisite check (run-state store lookup, no Miro needed) now explicitly precedes the Miro availability gate, making the missing-prerequisite branch reachable - planning: /architect agent-team routing gated on availability (experimental, default-off surface) with sub-agent/sequential fallback Co-Authored-By: Claude Fable 5 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_011xHkkNc7CR98L8Xz9Mu7ZA
|
Claude finished @kyle-sexton's task in 1s —— View job I'll analyze this and get back to you. |
There was a problem hiding this comment.
💡 Codex Review
Here are some automated review suggestions for this pull request.
Reviewed commit: 411c7aa923
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".
…ep-dive Bash(bash <path>*) is the P1 shape this plugin's own permission-hygiene criteria flag (auto mode drops it), and !-execution does not route through allowed-tools, so the grant only served body re-runs. Removed; CHANGELOG records the rationale. Co-Authored-By: Claude Fable 5 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_011xHkkNc7CR98L8Xz9Mu7ZA
|
Claude finished @kyle-sexton's task in 1s —— View job I'll analyze this and get back to you. |
kyle-sexton
added a commit
that referenced
this pull request
Jul 15, 2026
## Summary Restores the eval/test-coverage attrition identified by the salvage sweep (tier-3: items #13, #15–#23 plus the two flagged cosmetic-severity items), recreated genericized and validated against `plugins/skill-quality/reference/evals.schema.json`. Per-plugin version bumps + CHANGELOG entries. | Plugin | Version | Restored coverage | |---|---|---| | songwriting | 0.4.0 | All 13 medley behavioral evals mapped onto the multi-skill split (workflow 3, diagnosis 3, rhyme 2, song-form 2, co-write 2, object-writing 1); zero drops | | ai-briefing | 0.4.0 | 6 engine evals + 3 synthetic fixtures via the audience-defaults seam; the legacy Grok-preload case re-derived as an unreachable-RSS visible-degrade scenario (the flag never shipped; CI contract bans the token) | | event-storming | 0.4.0 | Offline board-export eval (id 8) + 74-line fixture for `--discover-bcs` — disjoint from the live-Miro-required eval, reconciliation noted inline | | codebase-audit | 0.3.0 | Scope-boundary eval: decline settings/MCP/hooks claim-extraction, route to `/claude-config-audit:settings-audit` | | discovery | 0.5.0 | Research floor-scaling ("floors are not targets") + broad-topic doubled-minimums evals, vendor-neutral | | source-control | 0.2.0 | Readiness security-gate eval + genericized fixture, mixed-actor (bot-fix-now vs human-pause) eval, three worktree evals (dry-run report-only, invalid-name rejection, batched-gh status + graceful degrade) | | docs-hygiene | 0.4.0 | Two self-contained fixture-backed cases (compress classification-table, declutter opt-out/section-exemption) — fixtures empirically verified against `detect.sh`; rename-references "add an eval case" clauses | | review-toolkit | 0.6.0 | code-review-fanout evals 6 → 20: dedup/severity-derivation, fix-pass safety fence (correctness never routed to /simplify), run-everything null-reconciliation + priority-ordering; 2 medley cases skipped (fixed-roster counts deliberately generalized away), their surviving assertions folded in | ## Verification - All 8 plugins pass `claude plugin validate`; `scripts/validate-plugin-contracts.mjs` passes (1311 files) - Every evals.json jq-parses and validates against the schema (ajv/check-jsonschema) - markdownlint-cli2 0 errors on new fixtures + CHANGELOGs; coupling grep (medley/consumer refs) clean - Rebased onto main post-#192; per-plugin validate re-run green after rebase 🤖 Generated with [Claude Code](https://claude.com/claude-code) https://claude.ai/code/session_011xHkkNc7CR98L8Xz9Mu7ZA --------- Co-authored-by: Claude Fable 5 <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.
Summary
Executes the owner-approved tier-2 restores from the salvage sweep (items #2–#12 plus semantic-drift items D1–D4): pre-migration behavior and guidance dropped at the cutover, restored and genericized to the marketplace's repo-agnostic seams. Every touched plugin gets a version bump and CHANGELOG entry.
allowed-toolsscoping; all script paths${CLAUDE_PLUGIN_ROOT}-rooted; every!command empirically tested with fallbacks--design-levelmissing-prerequisite guard (never fabricate a process model) + eval id 7; bare "memory" refs swept to the${CLAUDE_PLUGIN_DATA}/history.jsonlseam/implementation:verify-improvementSSOT when installed; devils-advocate regains the/implementation:verify-changespointerreference/, 221 lines) — hook-event table reconciled against the current hooks doc (8 events added, 2 medley errors fixed); handoff failure-patterncontext/gotchas.mdtool-pinversion-drift warning in /lint + ecosystem-commands contract 1.1.0 (additive schema key, per the contract's own versioning rule); /implement over-correction trap logs to the session retro when installedwhen installedgating); namedsession-flow:handoffseam in the auto-invoke gatePlaybook compliance
disable-model-invocation/frontmatter,${CLAUDE_PLUGIN_ROOT}substitution scope ("Skill and agent content — anywhere the placeholder appears"), and the hook-event table were verified against code.claude.com docs this session.docs/conventions/ecosystem-commands/confirmed repo-owned (not a standards-managed materialization) before the schema edit.claude plugin validate; catalog passesclaude plugin validate --strict; new/changed markdown passes markdownlint-cli2 (0 errors); the new eval validates againstevals.schema.json.Security review note (claude-config-audit 0.4.0)
The pre-computed context blocks add a code-execution-at-skill-load surface:
!commands run when the skill is invoked. Scope check per the plugin-acceptance review: all commands invoke scripts bundled inside the plugin via${CLAUDE_PLUGIN_ROOT}(no../reach-outs, no absolute paths), are read-only inventory/count operations, carry|| echo-style fallbacks so load never hard-fails, and make no network calls. Theallowed-toolsentry pre-approves exactly the one bundled read-only script, nothing broader.🤖 Generated with Claude Code
https://claude.ai/code/session_011xHkkNc7CR98L8Xz9Mu7ZA