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 tomzx/agents --skill review-requested-prsgit clone --depth 1 https://github.com/tomzx/agentsWrote 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/tomzx/agents/review-requested-prs)<a href="https://agentmods.dev/skills/tomzx/agents/review-requested-prs"><img src="https://agentmods.dev/badge/skills/tomzx/agents/review-requested-prs/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/tomzx/agents/review-requested-prs"><img src="https://agentmods.dev/badge/skills/tomzx/agents/review-requested-prs.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Excessive Agency · line 219 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
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 | $0.00146 | $0.05167 |
| Opus 5.5 | $0.00058 | $0.02067 |
| Sonnet 5.5 | $0.00029 | $0.01033 |
| Haiku 4.5 | $0.00015 | $0.00517 |
Grade A, and why
review-requested-prs 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 today.
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 — 313 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Review Requested PRs
Finds all open PRs where you are a requested reviewer (or accepts specific PR URLs), plus PRs where a team you belong to was requested and the request was later dropped (recovered from notifications), computes for each PR which of /assess-pr-risk, /summarize-behavior-changes, /adversarial-pr-review, /analyze-test-coverage, /validate-pr, /verify-pr, and /review-pr are stale for its current HEAD, plus which of the conditional surface reviews (/review-cli-changes, /review-sdk-changes, /review-api-changes, /review-db-changes) the PR's changed files call for and whether those are stale, then hands each PR to its own review-pr-full session that runs that PR's stale steps to completion (the risk assessment, behavior change summary, adversarial review, and applicable surface reviews concurrently with the chain).
The orchestrator (this session) only discovers work and aggregates results.
It never runs a review step itself.
Before dispatching, it stops any older run of the same task in the same directory so only the newest one works there.
Each PR is owned end to end by one review-pr-full subagent, so a slow step on one PR (for example a verify-pr build) cannot delay any other PR.
The discovery, staleness check, and head-ref resolution are done by a deterministic Python script (~/.agents/scripts/review_requested_prs.py).
Its --dispatch-prs output is one self-contained /review-pr-full command per PR, carrying the precomputed stale steps and head refs:
/review-pr-full 42 acme/api --steps validate-pr,verify-pr --head-repo acme/api --head-branch feature-x
Because the command is self-contained, review-pr-full starts the checks immediately: it does not re-query GitHub for staleness or PR status.
This is what keeps the orchestrator from slowing the work down.
Marker format
Each sub-skill posts a comment (or writes locally when posting is disabled) with an HTML marker containing a JSON object with the step name, commit SHA, tree hash, and verdict:
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.
- today Changed · +5 lines · +6 tokens per session a23bb5b6869c
- 11d ago Changed · +11 lines · +31 tokens per session a770a8434271
- 18d ago Changed · +4 lines · +7 tokens per session 819348f98923
- 22d ago Changed · +37 lines ba10af9af364
- 23d ago Changed · +15 lines c4dc027201d6
- 24d ago Changed a8e846d66b97
- 28d ago Changed · +7 lines · +11 tokens per session 42d7617160d6
- 1mo ago Changed · +3 lines · +12 tokens per session 54d18b9862bd
- 1mo ago Changed · +2 lines · +15 tokens per session 541b86ef13c0
- 1mo ago First seen · 229 lines · 64 tokens per session scan A f47e11458fa0
review-requested-prs is a skill published in the GitHub repository tomzx/agents (13 stars, last pushed yesterday), licensed MIT. It adds 146 tokens to every session and 5,167 once invoked, about $0.0006 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 2026-09-03.
Other skills, from other repositories
autoreview
Structured code review through the shared OpenClaw agent-skills installation.
omh-code-review
This is an OMH code-review workflow skill, projected for Agent Skills hosts (Claude Code, Codex, Cursor, opencode, OpenClaw, pi).
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"…
explore-unknowns
Guide the user through a quadrant walk that maps the unknowns of a task — open by listing the known knowns, then work through known unknowns, unknown knowns, and unknown unknowns one stage at a time, ending with a complete four-quadrant map in the user's hands. Use when a request is ambiguous or underspecified, the…
re0-merge
Review and land an external contribution the way this suite does: gate it against the thesis, land it with the author's credit intact, complete a new skill rather than merging it raw, then approve, credit, and explain before closing. Use when reviewing a pull request, as any collaborator or maintainer, not only the…
asplos-writing-style
Use when drafting or revising ASPLOS prose — engineering the first two pages that rapid review actually reads, stating the cross-layer insight as one quotable sentence, structuring per-layer mechanism sections, writing bounded claims, and fitting everything into 11 self-contained pages that include figures and…