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 theam/facility --skill reviewing-to-standardgit clone --depth 1 https://github.com/theam/facilityWrote 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/theam/facility/reviewing-to-standard)<a href="https://agentmods.dev/skills/theam/facility/reviewing-to-standard"><img src="https://agentmods.dev/badge/skills/theam/facility/reviewing-to-standard/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/theam/facility/reviewing-to-standard"><img src="https://agentmods.dev/badge/skills/theam/facility/reviewing-to-standard.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00045 | $0.00498 |
| Opus 5 | $0.00023 | $0.00249 |
| Sonnet 5 | $0.00009 | $0.00100 |
| Haiku 4.5 | $0.00005 | $0.00050 |
Grade A, and why
reviewing-to-standard 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 10d 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.
What it actually says
Reviewing to standard
A review exists to change the implementer's next action. Everything else is noise.
Review order (stop-the-line first)
- Correctness and fit — the change does what was asked, no more. Scope creep is a finding, not a bonus.
- Security and privacy — auth regressions, data exposure, secret handling, injection paths, new attack surface. Verify the negative case; never accept a prose claim that a boundary holds.
- Maintainability — same concept reused not duplicated, clear ownership boundaries, domain names, side effects visible, easy for the next caller and the next test.
- Standard compliance —
STANDARD.mdand its module sections were followed. A missed module requirement (seeds, analytics, evidence, exposure) is a product-quality gap, not optional polish. - Verification evidence — the right checks ran for the risk taken, and
skipped checks are named.
node guards/run.mjsshould be green.
The comment contract
Every finding carries four things: file:line, the exact risk, the smallest
practical fix, and the standard it missed. Severity is explicit — Blocker /
High / Medium — and separated from optional suggestions. Never post:
- Style-only nits, unless they hide a real bug or future maintenance cost.
- Vague asks ("clean this up", "add tests") — name the missing case, command, or assertion instead.
- Requests for broad rewrites when a narrow change closes the risk.
Leverage
For domains with real risk, dispatch the matching reviewer subagent from
.claude/agents/ and consolidate its findings rather than re-deriving them.
If the same problem has now appeared twice in reviews, the review is the
wrong tool: propose the guard (guards/) that makes the third occurrence
impossible, and say so in the review.
Verdict
End with Ready / Ready with follow-ups / Not ready, the checks you ran, and nothing else. You never approve or merge — that signature is human.
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.
- 10d ago First seen · 50 lines · 45 tokens per session scan A a3916e379781
reviewing-to-standard is a skill published in the GitHub repository theam/facility (61 stars, last pushed today), licensed Apache-2.0. It adds 45 tokens to every session and 498 once invoked, about $0.0002 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 2026-08-30.
Other skills, from other repositories
autoreview
Pre-commit/ship code review: Codex default; optional Claude or Pi.
rework-rate
Measure and interpret PR rework rate — the emerging 5th DORA metric.
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.
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…