Add review organization by THOClabs · Pull Request #93 · THOClabs/NIGHTWATCH

THOClabs · 2026-07-12T19:42:10Z

Summary

Installs a standing 7-level code-review organization into the repository: seven subagent definitions under .claude/agents/ and a /full-review command under .claude/commands/ that orchestrates them as a pipeline.

The seven agents:

repo-cartographer — L1 Recon. Maps the repository territory - file tree, languages, LOC, dependencies, build/test commands, entry points, config surface. Use as the first phase of any full-repo review.
git-historian — L2 Forensics. Analyzes git history for churn hotspots, bus factor, abandoned areas, commit conventions, and recent activity. Use after repo-cartographer in a full-repo review.
domain-analyst — L3 Deep dive. Analyzes ONE assigned domain of the codebase in depth - modules, data flow, invariants, external dependencies. Spawn one instance per domain, in parallel, during a full-repo review. The task prompt must name the assigned domain and its directories.
security-auditor — L4 Cross-cutting security audit. Sweeps the entire codebase for vulnerabilities after domain analysts finish, cross-checking their flagged concerns. Produces a severity-ranked findings report.
quality-auditor — L4 Cross-cutting quality audit. Assesses tests, CI, lint, error handling, and maintainability across all domains after the analysts finish. Runs the test suite when feasible.
chief-architect — L5-L6 Synthesis. Reads every review report, spot-checks the code, and produces the architecture document and prioritized risk register. Use after all analysts and auditors complete.
executive-scribe — L7 Board report. Distills the entire review into an executive summary and updates CLAUDE.md so every future session inherits the understanding. Use as the final phase of a full-repo review.

Running /full-review in Claude Code (or asking Claude to run .claude/commands/full-review.md) executes the pipeline: recon → git forensics → parallel per-domain deep dives → parallel security/quality audits → architecture synthesis and risk register → executive summary plus a generated CLAUDE.md section. Reports land under docs/review/; the organization is read-only toward source code.

Related Issues

None.

Type of Change

Bug fix (non-breaking change that fixes an issue)
New feature (non-breaking change that adds functionality)
Breaking change (fix or feature that would cause existing functionality to not work as expected)
Documentation update
Refactoring (no functional changes)
Test addition/update

(Tooling/configuration addition: Claude Code agent and command definitions only.)

Changes Made

Added .claude/agents/repo-cartographer.md, git-historian.md, domain-analyst.md, security-auditor.md, quality-auditor.md, chief-architect.md, executive-scribe.md
Added .claude/commands/full-review.md defining the phased review pipeline and its rules of engagement
No source code, tests, or other repository files were modified

Safety Checklist

Not applicable — no telescope/enclosure control or safety-system code is touched. The added review organization is explicitly read-only toward source code.

Testing

Unit tests pass (pytest tests/unit/)
Integration tests pass (pytest tests/integration/)
Manually tested with simulators
Tested with actual hardware (if applicable)

Not applicable — the change adds Markdown configuration for Claude Code agents; there is no runtime code to test.

Voice Commands

Not applicable — no voice commands added or modified.

Documentation

Code comments added/updated
README updated (if needed)
API documentation updated (if needed)
Configuration examples updated (if needed)

The added files are self-documenting agent/command definitions.

Screenshots / Logs

Not applicable.

Additional Notes

The task specified branch name chore/add-review-org; this session's push access is scoped to claude/install-review-org-37y4ck, so the work ships on that branch instead. File contents are otherwise installed verbatim as specified.

🤖 Generated with Claude Code

https://claude.ai/code/session_01FjTbUXge6kcW3TZMfAdz2J

Generated by Claude Code

Note

Low Risk
Documentation and Claude tooling only; no changes to observatory control, safety, or deploy/runtime paths.

Overview
Adds a standing Claude Code review organization: seven role definitions under .claude/agents/ (L1 recon through L7 executive scribe) plus .claude/commands/full-review.md, which runs a phased, read-only pipeline—inventory → git forensics → parallel domain deep dives → security/quality audits → architecture/risk synthesis → executive summary and a generated CLAUDE.md section. Writes are limited to docs/review/, .claude/agent-memory/, and the delimited CLAUDE.md block.

This PR also ships the first full review run on the branch: docs/review/00-inventory.md through multiple 20-domain-*.md reports, durable notes in .claude/agent-memory/ (e.g. chief-architect, voice/NLP analyst), and a generated repository review summary in CLAUDE.md (verified commands, danger zones, conventions). No application source under nightwatch/, services/, or voice/ is modified.

^{Reviewed by Cursor Bugbot for commit cc61aa2. Bugbot is set up for automated code reviews on this repo. Configure here.}

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_01FjTbUXge6kcW3TZMfAdz2J

cursor · 2026-07-12T19:42:19Z

Bugbot couldn't run - usage limit reached

Bugbot is counted against Cursor usage for this user or team, and this run hit a usage or spend limit.

A user or team admin can review and increase usage limits in the Cursor dashboard.

(requestId: serverGenReqId_00413fe2-37dc-404f-b11f-2d7c6b24e6e8)

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_01FjTbUXge6kcW3TZMfAdz2J

cursor · 2026-07-12T22:09:31Z

Bugbot couldn't run - usage limit reached

Bugbot is counted against Cursor usage for this user or team, and this run hit a usage or spend limit.

A user or team admin can review and increase usage limits in the Cursor dashboard.

(requestId: serverGenReqId_0aeda91f-607b-46f4-96e1-9ea47a0ce5ba)

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_01FjTbUXge6kcW3TZMfAdz2J

cursor · 2026-07-12T22:13:12Z

Bugbot couldn't run - usage limit reached

Bugbot is counted against Cursor usage for this user or team, and this run hit a usage or spend limit.

A user or team admin can review and increase usage limits in the Cursor dashboard.

(requestId: serverGenReqId_2f764230-ed80-4a44-a516-e5a70680775d)

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_01FjTbUXge6kcW3TZMfAdz2J

cursor · 2026-07-12T22:21:14Z

Bugbot couldn't run - usage limit reached

Bugbot is counted against Cursor usage for this user or team, and this run hit a usage or spend limit.

A user or team admin can review and increase usage limits in the Cursor dashboard.

(requestId: serverGenReqId_06aef9ea-7a83-4506-b73c-cf13c54ea4a7)

…n domain Co-Authored-By: Claude Fable 5 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_01FjTbUXge6kcW3TZMfAdz2J

cursor · 2026-07-12T22:23:05Z

Bugbot couldn't run - usage limit reached

Bugbot is counted against Cursor usage for this user or team, and this run hit a usage or spend limit.

A user or team admin can review and increase usage limits in the Cursor dashboard.

(requestId: serverGenReqId_94276eb3-c944-4b74-8ade-58041a785a96)

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_01FjTbUXge6kcW3TZMfAdz2J

cursor · 2026-07-12T22:23:50Z

Bugbot couldn't run - usage limit reached

Bugbot is counted against Cursor usage for this user or team, and this run hit a usage or spend limit.

A user or team admin can review and increase usage limits in the Cursor dashboard.

(requestId: serverGenReqId_d305b2de-aaf0-4c07-ac12-bbbbf74c5cb5)

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_01FjTbUXge6kcW3TZMfAdz2J

cursor · 2026-07-12T22:24:13Z

Bugbot couldn't run - usage limit reached

Bugbot is counted against Cursor usage for this user or team, and this run hit a usage or spend limit.

A user or team admin can review and increase usage limits in the Cursor dashboard.

(requestId: serverGenReqId_ebfb5f03-b3f3-43c5-9a6d-c1c939818c3f)

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_01FjTbUXge6kcW3TZMfAdz2J

cursor · 2026-07-12T22:25:53Z

Bugbot couldn't run - usage limit reached

Bugbot is counted against Cursor usage for this user or team, and this run hit a usage or spend limit.

A user or team admin can review and increase usage limits in the Cursor dashboard.

(requestId: serverGenReqId_129b5718-7e4d-418e-a14f-f610651b76c6)

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_01FjTbUXge6kcW3TZMfAdz2J

cursor · 2026-07-12T22:27:29Z

Bugbot couldn't run - usage limit reached

Bugbot is counted against Cursor usage for this user or team, and this run hit a usage or spend limit.

A user or team admin can review and increase usage limits in the Cursor dashboard.

(requestId: serverGenReqId_355852eb-0cc7-47dd-b642-fc175f23444f)

…urity.md) Co-Authored-By: Claude Fable 5 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_01FjTbUXge6kcW3TZMfAdz2J

cursor · 2026-07-12T22:43:56Z

Bugbot couldn't run - usage limit reached

Bugbot is counted against Cursor usage for this user or team, and this run hit a usage or spend limit.

A user or team admin can review and increase usage limits in the Cursor dashboard.

(requestId: serverGenReqId_c9536553-b8e7-4dce-8ca0-f25da4b145a0)

…ity.md) Co-Authored-By: Claude Fable 5 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_01FjTbUXge6kcW3TZMfAdz2J

cursor · 2026-07-12T22:59:21Z

Bugbot couldn't run - usage limit reached

Bugbot is counted against Cursor usage for this user or team, and this run hit a usage or spend limit.

A user or team admin can review and increase usage limits in the Cursor dashboard.

(requestId: serverGenReqId_717717c7-4024-448f-b9f6-fdaf569ebb35)

…chitect memory Co-Authored-By: Claude Fable 5 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_01FjTbUXge6kcW3TZMfAdz2J

…AUDE.md Co-Authored-By: Claude Fable 5 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_01FjTbUXge6kcW3TZMfAdz2J

cursor · 2026-07-12T23:12:18Z

Bugbot couldn't run - usage limit reached

Bugbot is counted against Cursor usage for this user or team, and this run hit a usage or spend limit.

A user or team admin can review and increase usage limits in the Cursor dashboard.

(requestId: serverGenReqId_a7f319b5-7e0d-4176-86a1-75bae93d4610)

Reconciles the two independent full-repo reviews (AUDIT_LANDSCAPE.md at eebdbac and the docs/review corpus at cc61aa2) into a single prioritized Stage 0-5 resumption backlog, plus a two-month activity inventory and a stale-branch triage table. - Cross-confirmed findings (both reviews) treated as ground truth: broken emergency roof-close, startup crash, CI-can't-fail, assembly gap, dormant watchdog, phantom tool import, unauth network surface, PDU creds. - Harvests #90's ~10 unique data-integrity / driver / deploy bugs. - Adopts #93's aiohttp CVEs, test-pollution root cause, weather fail-open, and its re-runnable review organization. - Spot-re-verified the startup crash (main.py:308/325 vs logging_config.py:185) and the roof _gpio init-absence against live source before publishing. Orientation doc only; no product code changed. Leaves the merge/close decisions on PRs #90 and #93 to the active session. Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_01SKZMQ755R7q38SKqJsCQsg

…ranches (S5) Completes the S5 line item from REVIEW_RECONCILIATION.md. Buckets all 82 non-main remote branches: 11 merged-this-session fix/* (content in main, safe delete), 59 orphan March-2026 NEO/meteor scanner re-rolls (never PR'd, 39 behind — reference-spec only, not mergeable), 6 superseded cursor/* review orphans, and 2 legacy/misc (master, review-codebase). Names 7 reference branches worth skimming before pruning the March cluster; keeps the 4 branches backing open PRs (#89/#90/#92/#93). Ships ready-to-run per-bucket delete commands. No branches deleted, merged, or force-pushed — all removals left to the maintainer. Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_01SKZMQ755R7q38SKqJsCQsg

#112) 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>

THOClabs · 2026-08-07T04:17:17Z

Closing as part of the v0.1.1 single-branch consolidation. The durable tooling on this branch WAS salvaged to main in #112 (commit 5d84e66): all 7 .claude/agents/ review subagents + the /full-review command. The 12 July review reports were intentionally not taken — they describe a repo state 20+ commits old, superseded by the merged #94–#110 fixes. Branch will be deleted with the stale-branch purge.

Add 7-level Claude review organization (agents + /full-review command)

1634457

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_01FjTbUXge6kcW3TZMfAdz2J

docs(review): Phase 1 recon — repository inventory (00-inventory.md)

66f2f94

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_01FjTbUXge6kcW3TZMfAdz2J

docs(review): Phase 2 forensics — git history analysis (10-history.md)

92e7c4d

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_01FjTbUXge6kcW3TZMfAdz2J

docs(review): Phase 3 deep dive — LLM client & tool binding domain

318cffb

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_01FjTbUXge6kcW3TZMfAdz2J

docs(review): Phase 3 deep dive — command execution & tool integratio…

6d2db6f

…n domain Co-Authored-By: Claude Fable 5 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_01FjTbUXge6kcW3TZMfAdz2J

docs(review): Phase 3 deep dive — voice & NLP domain

7ba250a

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_01FjTbUXge6kcW3TZMfAdz2J

docs(review): domain-analyst agent memory — voice & NLP learnings

49b7170

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_01FjTbUXge6kcW3TZMfAdz2J

docs(review): Phase 3 deep dive — core orchestration & safety domain

9779a9f

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_01FjTbUXge6kcW3TZMfAdz2J

docs(review): Phase 3 deep dive — astronomy & hardware services domain

6328485

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_01FjTbUXge6kcW3TZMfAdz2J

docs(review): Phase 4 audit — cross-cutting security findings (30-sec…

7c3e607

…urity.md) Co-Authored-By: Claude Fable 5 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_01FjTbUXge6kcW3TZMfAdz2J

docs(review): Phase 4 audit — cross-cutting quality findings (31-qual…

8c1588d

…ity.md) Co-Authored-By: Claude Fable 5 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_01FjTbUXge6kcW3TZMfAdz2J

claude added 2 commits July 12, 2026 23:08

docs(review): Phase 5 synthesis — architecture doc, risk register, ar…

0f683f5

…chitect memory Co-Authored-By: Claude Fable 5 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_01FjTbUXge6kcW3TZMfAdz2J

docs(review): Phase 6 board report — executive summary + generated CL…

cc61aa2

…AUDE.md Co-Authored-By: Claude Fable 5 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_01FjTbUXge6kcW3TZMfAdz2J

THOClabs mentioned this pull request Aug 7, 2026

salvage(tooling+docs): review org, frontend prompt pack, audit archive #112

Merged

THOClabs closed this Aug 7, 2026

THOClabs deleted the claude/install-review-org-37y4ck branch August 7, 2026 04:23

Navigation Menu

Add review organization - #93

Add review organization#93
THOClabs wants to merge 13 commits into
mainfrom
claude/install-review-org-37y4ck

THOClabs commented Jul 12, 2026 •

edited by cursor Bot

Loading

Uh oh!

cursor Bot commented Jul 12, 2026

Uh oh!

cursor Bot commented Jul 12, 2026

Uh oh!

cursor Bot commented Jul 12, 2026

Uh oh!

cursor Bot commented Jul 12, 2026

Uh oh!

cursor Bot commented Jul 12, 2026

Uh oh!

cursor Bot commented Jul 12, 2026

Uh oh!

cursor Bot commented Jul 12, 2026

Uh oh!

cursor Bot commented Jul 12, 2026

Uh oh!

cursor Bot commented Jul 12, 2026

Uh oh!

cursor Bot commented Jul 12, 2026

Uh oh!

cursor Bot commented Jul 12, 2026

Uh oh!

cursor Bot commented Jul 12, 2026

Uh oh!

THOClabs commented Aug 7, 2026

Uh oh!

Reviewers

Assignees

Labels

Projects

Milestone

Development

Uh oh!

2 participants

Conversation

THOClabs commented Jul 12, 2026 • edited by cursor Bot Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

Summary

Related Issues

Type of Change

Changes Made

Safety Checklist

Testing

Voice Commands

Documentation

Screenshots / Logs

Additional Notes

Uh oh!

cursor Bot commented Jul 12, 2026

Bugbot couldn't run - usage limit reached

Uh oh!

cursor Bot commented Jul 12, 2026

Bugbot couldn't run - usage limit reached

Uh oh!

cursor Bot commented Jul 12, 2026

Bugbot couldn't run - usage limit reached

Uh oh!

cursor Bot commented Jul 12, 2026

Bugbot couldn't run - usage limit reached

Uh oh!

cursor Bot commented Jul 12, 2026

Bugbot couldn't run - usage limit reached

Uh oh!

cursor Bot commented Jul 12, 2026

Bugbot couldn't run - usage limit reached

Uh oh!

cursor Bot commented Jul 12, 2026

Bugbot couldn't run - usage limit reached

Uh oh!

cursor Bot commented Jul 12, 2026

Bugbot couldn't run - usage limit reached

Uh oh!

cursor Bot commented Jul 12, 2026

Bugbot couldn't run - usage limit reached

Uh oh!

cursor Bot commented Jul 12, 2026

Bugbot couldn't run - usage limit reached

Uh oh!

cursor Bot commented Jul 12, 2026

Bugbot couldn't run - usage limit reached

Uh oh!

cursor Bot commented Jul 12, 2026

Bugbot couldn't run - usage limit reached

Uh oh!

THOClabs commented Aug 7, 2026

Uh oh!

Reviewers

Assignees

Labels

Projects

Milestone

Development

Uh oh!

2 participants

THOClabs commented Jul 12, 2026 •

edited by cursor Bot

Loading