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 gabonio/agent-operator-toolkit --skill pr-review-loopgit clone --depth 1 https://github.com/gabonio/agent-operator-toolkitWrote 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/gabonio/agent-operator-toolkit/pr-review-loop)<a href="https://agentmods.dev/skills/gabonio/agent-operator-toolkit/pr-review-loop"><img src="https://agentmods.dev/badge/skills/gabonio/agent-operator-toolkit/pr-review-loop/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/gabonio/agent-operator-toolkit/pr-review-loop"><img src="https://agentmods.dev/badge/skills/gabonio/agent-operator-toolkit/pr-review-loop.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 | $0.00062 | $0.00745 |
| Opus 5.5 | $0.00025 | $0.00298 |
| Sonnet 5.5 | $0.00012 | $0.00149 |
| Haiku 4.5 | $0.00006 | $0.00075 |
Grade A, and why
pr-review-loop 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 6d 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 — 36 lines — stays where its author put it; the contents beside it link to each section on GitHub.
PR Review Loop
Use the adversarial reviewer, repository instructions, and available Git/GitHub tools. Read Git Safety. Stop after ten iterations without a new user decision.
Scope and authorization
Choose the review scope:
- Incremental checkpoint: one coherent, verified slice; record the last clean head as baseline.
- Final integrated review: the complete, cross-slice result. Earlier clean checkpoints do not replace this pass.
Record authorization separately:
- Inspect: read-only local diff, PR, branch, checks, and thread inspection.
- Fix/sync: explicit permission for the named merge, edit, commit, push, reply, or resolve scope.
Do not infer writes from skill invocation, a PR URL, or earlier permission. Preserve unrelated changes. Before published-PR fix/sync actions, confirm the checkout is the fetched PR head (or only authorized descendants), the upstream is expected, and the outgoing diff contains only authorized work. If ownership is uncertain, stop or use a clean isolated worktree. Recheck outgoing commits and diff before each push.
Loop
- Identify the complete working-tree/index diff or PR diff, real base branch, starting head, checks, scope, baseline, and authorizations. When a PR exists, inspect checks, mergeability, base freshness, and unresolved threads.
- For a published PR, fetch the base when authorized. If behind, report it in inspect mode; when sync is authorized, merge without rewriting published history, resolve evidence-backed conflicts, verify, and push. Ask before conflicts that alter behavior, contracts, security, migrations, or scope.
- Review the complete current diff locally across behavior, security, data integrity, compatibility, operations, tests, and the approved objective. Report only the three or four highest-value findings, fewer when fewer are real, with severity, evidence, impact, fix/validation, and a useful
path:lineanchor. - Verify findings against code, tests, design, and local rules. Classify as fix, false positive, duplicate, accepted risk, or user decision. Present local review comments; use inline annotations when available. Publish comments only when authorized.
- In inspect mode, report and stop. When fixes are authorized, make scoped changes, add focused tests for behavior changes, and verify. Commit and push only when separately authorized.
- Mark local findings addressed after verification. For authorized remote replies/resolution, include evidence and a fixing commit when pushed; resolve only fully addressed findings. Leave partial, unverified, unpushed, and security/product decisions open.
- Recompute and review the complete diff after fixes or synchronization, not just the last batch's files. Recheck published-PR base freshness and unresolved threads before declaring readiness.
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 6d ago Changed · +12 lines · -7 tokens per session 4c885aed24b7
- 1mo ago First seen · 24 lines · 69 tokens per session scan A df8f5c487c12
pr-review-loop is a skill published in the GitHub repository gabonio/agent-operator-toolkit (1 stars, last pushed 7d ago), licensed MIT. It adds 62 tokens to every session and 745 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 2026-08-31.
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"…
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…
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…
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…