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 in-the-loop-labs/pair-review --skill ai-criticgit clone --depth 1 https://github.com/in-the-loop-labs/pair-reviewWrote 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/in-the-loop-labs/pair-review/ai-critic)<a href="https://agentmods.dev/skills/in-the-loop-labs/pair-review/ai-critic"><img src="https://agentmods.dev/badge/skills/in-the-loop-labs/pair-review/ai-critic/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/in-the-loop-labs/pair-review/ai-critic"><img src="https://agentmods.dev/badge/skills/in-the-loop-labs/pair-review/ai-critic.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 | $0.00056 | $0.00455 |
| Opus 5 | $0.00028 | $0.00228 |
| Sonnet 5 | $0.00011 | $0.00091 |
| Haiku 4.5 | $0.00006 | $0.00046 |
Grade A, and why
ai-critic 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 12d 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
AI Critic
Fetch AI-generated suggestions from pair-review and make code changes to address the valid ones.
Determine review context
Determine whether this is a local review or a PR review:
- If the user explicitly says "local", use local mode.
- Otherwise, determine the GitHub owner, repo, and PR number for the current branch. If a PR exists, use PR mode with
repoandprNumberparams. - If no PR exists, use local mode with
path(absolute cwd) andheadSha(git rev-parse HEAD) params.
Fetch AI suggestions
Call mcp__pair-review__get_ai_suggestions with the review context params. This returns suggestions from the latest analysis run by default.
If the user wants suggestions from a specific analysis run, call mcp__pair-review__get_ai_analysis_runs first to list available runs, then pass the appropriate runId to get_ai_suggestions.
Only active and adopted suggestions are included (dismissed ones are excluded).
If no suggestions are returned, tell the user there are no AI suggestions to address.
Triage and address suggestions
AI suggestions are not human-curated — apply judgment. For each suggestion:
- Read the file at the referenced path and lines.
- Evaluate the suggestion: is it a real issue, a false positive, or a stylistic preference?
- If the suggestion is valid and actionable, make the code change.
- If the suggestion is a false positive or not worth addressing, skip it and note why.
Use the ai_confidence field as a signal but not a hard threshold — low-confidence suggestions can still be valid.
Report
After processing all suggestions, provide a summary:
- How many suggestions were reviewed
- Which ones were addressed (and what changed)
- Which ones were skipped (and why)
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.
- 12d ago First seen · 48 lines · 56 tokens per session scan A 8e6130d7d267
ai-critic is a skill published in the GitHub repository in-the-loop-labs/pair-review (59 stars, last pushed today), licensed Apache-2.0. It adds 56 tokens to every session and 455 once invoked, about $0.0003 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.
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…