salvage(tooling+docs): review org, frontend prompt pack, audit archive - #112
Merged
Conversation
Preserves the durable content of three open-PR branches before the v0.1.1 branch purge closes them: - .claude/agents/ (7 review subagents) + .claude/commands/full-review.md from PR #93's branch — repo-state-independent review tooling; the stale July review reports on that branch are intentionally NOT taken. - docs/design/ Claude Design frontend prompt pack (3 files) from PR #92's branch — targets the v0.2 frontend; NEO data-model sections predate #108/#109 and need a refresh before use (noted in its provenance table). - docs/audits/ archive of AUDIT_LANDSCAPE.md + REVIEW_RECONCILIATION.md from PR #90's branch, with HISTORICAL SNAPSHOT headers — findings were fixed by #94-#110; preserved as engineering history. Its STALE_BRANCH_TRIAGE.md is dropped (superseded by #110). Part 1/Step 2 of the v0.1.1 main-only consolidation. Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
There was a problem hiding this comment.
Cursor Bugbot has reviewed your changes using default effort and found 1 potential issue.
❌ Bugbot Autofix is OFF. To automatically fix reported issues with cloud agents, enable autofix in the Cursor dashboard.
Reviewed by Cursor Bugbot for commit 6ee2456. Configure here.
|
|
||
| You are a senior domain analyst (L3) in a repository review organization. Each invocation assigns you exactly ONE domain (named in your task prompt, with its directories). Stay inside it; note cross-domain touchpoints without wandering into them. You never modify source code. You may write exactly one report file: docs/review/20-domain-<slug>.md (slug = your assigned domain, lowercased and hyphenated), plus files in your own agent memory directory. | ||
|
|
||
| Read docs/review/00-inventory.md and 10-history.md first. Then produce your report covering: |
There was a problem hiding this comment.
Review input paths ambiguous
Low Severity
Mandatory pre-reads name 10-history.md and 20-domain-*.md without the docs/review/ prefix used elsewhere (full-review.md, cartographer outputs). Delegated agents may look at repo root, skip history/domain reports, and run Phase 3–4 without required context.
Additional Locations (2)
Reviewed by Cursor Bugbot for commit 6ee2456. Configure here.
This was referenced Aug 7, 2026
Closed
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
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
Docs/tooling-only salvage ahead of the v0.1.1 branch purge — preserves the durable pieces of three open-PR branches slated for deletion:
.claude/agents/(7 review subagents) +/full-reviewcommand. The 12 stale review reports on that branch are deliberately excluded.docs/design/frontend prompt pack (cherry-picked content of 56321bc).docs/audits/historical archive of the landscape audit + review reconciliation, with prominent HISTORICAL SNAPSHOT headers (findings already fixed by Stage 2: data integrity fixes (S2-1 … S2-5) #94–docs: branch-cleanup triage + deletion script (87 stale branches) #110).No code paths touched; no tests affected.
Part 1/Step 2 of the v0.1.1 main-only consolidation.
🤖 Generated with Claude Code
Note
Low Risk
Markdown and Claude agent definitions only; no product code, CI, or dependency manifests changed.
Overview
Docs/tooling salvage for v0.1.1 consolidation: preserves durable artifacts from open PRs #90, #92, and #93 without touching runtime code.
Claude review organization — seven new agents under
.claude/agents/(repo-cartographerthroughexecutive-scribe) plus.claude/commands/full-review.md, which defines a phased, read-only pipeline that writes only todocs/review/, agent memory, andCLAUDE.md. Staledocs/review/outputs from the original #93 run are intentionally not included.Historical audits —
docs/audits/AUDIT_LANDSCAPE.mdandREVIEW_RECONCILIATION.mdare added with prominent HISTORICAL SNAPSHOT banners (commit7fa94a2; findings largely superseded by #94–#110).Frontend design pack —
docs/design/gets the master Claude Design prompt, six iteration prompts, and a README mapping spec sections to repo sources.Reviewed by Cursor Bugbot for commit 6ee2456. Bugbot is set up for automated code reviews on this repo. Configure here.