Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add chemrich/cabineteer --skill cabinet-reviewgit clone --depth 1 https://github.com/chemrich/cabineteerWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/chemrich/cabineteer/cabinet-review)<a href="https://agentmods.dev/skills/chemrich/cabineteer/cabinet-review"><img src="https://agentmods.dev/badge/skills/chemrich/cabineteer/cabinet-review/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/chemrich/cabineteer/cabinet-review"><img src="https://agentmods.dev/badge/skills/chemrich/cabineteer/cabinet-review.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00072 | $0.00937 |
| Opus 5 | $0.00036 | $0.00468 |
| Sonnet 5 | $0.00014 | $0.00187 |
| Haiku 4.5 | $0.00007 | $0.00094 |
Grade A, and why
cabinet-review scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 11d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 61 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Cabineteer review → fix → merge workflow
This is the established shape for a broad review of this repo (used for PR #21). It fans review out across modules in parallel, verifies findings independently, then lands fixes as a dedicated PR that Charlie merges on his explicit call.
1. Establish the baseline first
uv run pytest tests/ -q # capture the actual passed/skipped counts NOW
uv run python -m evals # evals baseline: see CLAUDE.md (305 scenarios / 1139 assertions as of 2026-07-29)
Record whatever numbers this run prints — the test count grows as tests are added, so the baseline is "what the suite reports on the pre-change tree," not a fixed figure. Every later "green" is measured against these captured numbers, not a hardcoded one.
2. Fan out review by module cluster (parallel agents)
Launch one agent per disjoint file group so their edits never collide. A workable split:
- geometry:
cabinet.py,drawer.py,door.py - joinery/hardware:
joinery.py,hardware.py - evaluation/fix:
evaluation.py,auto_fix.py,proportions.py - cutlist:
cutlist.py - server/security:
server.py - visualizer:
visualize.py - data/describe:
project.py,presets.py,pulls.py,describe.py,furniture_refs.py - evals/CI infra:
evals/,pyproject.toml,.github/,.claude/(plusconftest.pyif one exists)
Tell each agent to read CLAUDE.md first (it lists already-fixed issues — don't re-report those), substantiate every finding with a concrete trace or uv run python -c repro, and return severity-tagged findings (critical/major/minor/nit) with file:line, evidence, and a one-line fix.
3. Verify before acting
Independently reproduce the high-impact findings yourself (don't trust an agent's claim unseen). This repo's traps that make plausible findings wrong:
- Derived-property tautologies: several checks compare a property to its own defining formula — "it can never fire" is often real here, but confirm.
- CadQuery vs pure-Python paths can legitimately differ; check which path production uses.
- Coordinate conventions are documented in CLAUDE.md (workplane axes, GLTF node hierarchy) — verify axis/sign claims against them.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 11d ago First seen · 61 lines · 72 tokens per session scan A abcee28a5a02
cabinet-review is a skill published in the GitHub repository chemrich/cabineteer (3 stars, last pushed 6d ago), licensed Apache-2.0. It adds 72 tokens to every session and 937 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
autoreview
Pre-commit/ship code review: Codex default; optional Claude or Pi.
omh-code-review
This is a Hermes-native code-review workflow skill.
revdiff-plan
Review the last Codex assistant message (plan, analysis, or proposal) with inline annotations in a TUI overlay. Extracts the most recent response from Codex rollout files and opens it in revdiff for review and annotation. Activates on "revdiff-plan", "review plan with revdiff", "annotate plan", "review last response"…
code-reviewer
Code review specialist focused on patterns, bugs, security, and performance.
full-repo-review
Comprehensive four-wave review of all repo source files, producing a prioritized issue backlog.
agent-teams-simplify-and-harden
Implementation + audit loop using parallel agent teams with structured simplify, harden, and document passes. Spawns implementation agents to do the work, then audit agents to find complexity, security gaps, and spec deviations, then loops until code compiles cleanly, all tests pass, and auditors find zero issues or…