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 crittylabs/critty --skill critty-approvalgit clone --depth 1 https://github.com/crittylabs/crittyWrote 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/crittylabs/critty/critty-approval)<a href="https://agentmods.dev/skills/crittylabs/critty/critty-approval"><img src="https://agentmods.dev/badge/skills/crittylabs/critty/critty-approval/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/crittylabs/critty/critty-approval"><img src="https://agentmods.dev/badge/skills/crittylabs/critty/critty-approval.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 | $0.00047 | $0.02065 |
| Opus 5.5 | $0.00019 | $0.00826 |
| Sonnet 5.5 | $0.00009 | $0.00413 |
| Haiku 4.5 | $0.00005 | $0.00206 |
Grade A, and why
critty-approval 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 2d 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 — 120 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Approval documents
Prepare and interpret human decisions through Critty. The caller decides when approval is required, where drafts belong, and which operations are allowed. Reuse existing authorization for unchanged operations. Critty records decisions; the agent executes authorized actions.
Delegate the review loop to /critty; this is an explicit selection of Critty. Consult /critty-cli for attachment, form, and result contracts.
1. Prepare a concrete request
Complete authorized preparation and checks first. Use task-owned draft and result paths under the caller's storage convention; filenames below are examples. Keep review-only drafts outside the index.
Describe exact operations, destinations, payloads, and material effects. Combine related actions and identify dependencies, such as a separately gated branch push needed before creating a PR.
| Action | Identify before review |
|---|---|
| Push | Repository, resolved push URLs, fully qualified source/destination refs, full commit or tag IDs, introduced changes, and CI or deployment effects. |
| PR, issue, comment, or message | Service and destination, operation (create or edit), existing item/thread when applicable, exact title/body, and applicable recipients, labels, visibility, attachments, or scheduling. |
| Release or deployment | Candidate identity, environment, exact notes or artifacts, ordering and dependencies, material impact, and rollback where applicable. |
| Local commit or application | Exact reviewed changes and message or target paths; state explicitly if approval also requests execution. |
| AI review | Tool, model, service, assignment and source snapshots sent, investigation roots, and permitted local findings destination. Distinguish local comment storage from hosted publication. |
If the review will create a commit, identify it as reviewed-commit, record its full parent SHA (null for an initial commit), and attach its exact message alongside the reviewed diff. Record the resulting SHA separately after creation. For tags to create, specify the target, annotation, and signing requirements. A changed parent, diff, message, or tag input needs renewed approval.
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.
- 2d ago Changed · +11 lines ede5b772b4bc
- 4d ago First seen · 109 lines · 47 tokens per session scan A f06dabe3f153
critty-approval is a skill published in the GitHub repository crittylabs/critty (88 stars, last pushed yesterday), licensed MIT. It adds 47 tokens to every session and 2,065 once invoked, about $0.0002 per session on Opus 5.5. 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 2026-10-12.
Other skills, from other repositories
pr-comments
Fetch and display GitHub PR review comments for the current branch.
simplify
Clean up changed code while preserving intended behavior. Use when the user asks to simplify or improve code quality through reuse, simplification, efficiency, and abstraction reviews. Correctness bug hunting is outside scope.
cmd-review
Review the current diff or selected files (usage: /review [instructions | --last-diff | --target | --file | files...] [--style ]).
assess-patch-risk
Assess an immutable patch artifact's program impact, regression risk, and auto-merge eligibility. Use for generated patch files, provider pull-request diffs, or commit ranges when reviewers need evidence about affected runtime paths, contracts, tests, and recoverability. This skill is read-only and does not generate…
code-guidelines-go
Go 1.24–1.27 coding guidelines for the dimetron/pi-go AI agent runtime. Use this skill whenever writing, reviewing, or refactoring ANY Go code in pi-go. This covers idiomatic style, error handling, concurrency, project layout, testing (table-driven, fuzz, benchmarks, synctest), new stdlib usage, golangci-lint v2…
design-review
Deep design review of Go codebase — naming, structure, consistency, interfaces, error handling. Scores each dimension and provides actionable fixes.