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 review-requestsgit 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/review-requests)<a href="https://agentmods.dev/skills/in-the-loop-labs/pair-review/review-requests"><img src="https://agentmods.dev/badge/skills/in-the-loop-labs/pair-review/review-requests/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/review-requests"><img src="https://agentmods.dev/badge/skills/in-the-loop-labs/pair-review/review-requests.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 | $0.00083 | $0.00567 |
| Opus 5 | $0.00042 | $0.00283 |
| Sonnet 5 | $0.00017 | $0.00113 |
| Haiku 4.5 | $0.00008 | $0.00057 |
Grade A, and why
review-requests scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 12d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
What it actually says
Review Requests
Batch-open outstanding GitHub review requests in pair-review with AI analysis.
Workflow
Phase 1: Discover pair-review server
Call mcp__pair-review__get_server_info to get the pair-review web UI URL. If the server
is not running, inform the user and stop.
Phase 2: Find pending review requests
Use user-review-requested:@me (not review-requested) to find only PRs where the user
was directly requested as a reviewer, excluding team-based review requests. The gh search prs
CLI does not support this qualifier, so use the search API directly:
SINCE=$(date -v-7d +%Y-%m-%d 2>/dev/null || date -d '7 days ago' +%Y-%m-%d)
gh api "search/issues?q=is:pr+is:open+user-review-requested:@me+updated:>=${SINCE}&per_page=30" \
--jq '.items[] | {number, title, html_url, repo: (.repository_url | split("/")[-2:] | join("/"))}'
Each result provides number, title, html_url, and repo (as owner/repo).
Phase 3: Open each PR in pair-review with auto-analysis
Limit: Open at most 10 PRs. If more than 10 are found, open only the first 10 (most recently updated) and report how many were skipped.
For each PR found (up to the limit), open it in the browser with the ?analyze=true query parameter, which
automatically starts AI analysis when the page loads:
open "{server_url}/pr/{owner}/{repo}/{number}?analyze=true"
where {owner}/{repo} comes from the repo field split on /.
No MCP calls per PR are needed — the ?analyze=true parameter handles triggering analysis.
Phase 4: Report
Summarize what was done:
- How many PRs were found with pending review
- List each PR opened in pair-review with title and URL
- If no pending review requests exist, say so
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 · 58 lines · 83 tokens per session scan A 550c4a65e568
review-requests is a skill published in the GitHub repository in-the-loop-labs/pair-review (59 stars, last pushed yesterday), licensed Apache-2.0. It adds 83 tokens to every session and 567 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 2026-08-30.
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…