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 agentmods add skills/agent-rig/rig/rig-reviewnpx skills add agent-rig/rig --skill rig-reviewgit clone --depth 1 https://github.com/agent-rig/rigWhat 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 | $0.00142 | $0.04336 |
| Opus 5 | $0.00071 | $0.02168 |
| Sonnet 5 | $0.00028 | $0.00867 |
| Haiku 4.5 | $0.00014 | $0.00434 |
Grade A, and why
rig-review 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 3d 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 — 281 lines — stays where its author put it; the contents beside it link to each section on GitHub.
rig-review — find and fix, in one skill
Local code review with two verbs:
find(default) — walk the project'sREVIEWER.mdcatalog and the applicable per-scope invariants against a diff with a fresh-contextrevieweragent (two passes), and return a triaged P0–P3 finding list. Read-only — it reports, it doesn't edit.fix— take review feedback and loop acoderagent over it until the review comes back clean (or a round budget is hit). Two feedback sources: a PR review bot on an open PR, or localfindresults.
The point is to pre-empt the PR review bot: every finding caught and fixed
locally is one you don't pay PR round-trip latency on. Implement/epic-style
flows call rig-review find then rig-review fix --source local so the loop
lives in one place.
Configuration
Reads .rig/config.json:
review.patternsFile— the P0–P3 catalog the reviewer walks (default.claude/REVIEWER.md). If absent, fall back to the kit's generic categories (correctness, security/trust-boundary, error-handling, concurrency, API/contract, tests, style) and say so.review.bot— PR review bot to poll/re-trigger:codex,claude, ornone(defaultnone).noneforces the local-only loop forfix.review.botRetrigger— comment that re-triggers the bot (e.g.@codex review). Required whenbotis notnone.review.maxRounds— max fix↔recheck rounds before handing to a human (default5);--rounds Noverrides.vcs.baseRef— diff base when no<base>is given (defaultorigin/main).project.repo—owner/namefor everygh apicall (bot source). Never hardcode; derive from the git remote if unset.agents.reviewer/agents.coder— the project's names for those roles (defaultrig-<role>).style.guideFile— the writing style for findings (default.claude/STYLE.md).
Scope invariants (per-subsystem REVIEWER.md). Beyond the root catalog, a
subsystem may carry its own REVIEWER.md colocated with its code — concrete
correctness invariants it "learned the hard way," each ideally citing the PR
where it was found. scripts/scope-reviewer.ts resolves which apply to a diff
(ancestor-walk + any governs: globs a scope declares). find collects them
and has the reviewer assert each as a P1. No-op if the project ships none.
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.
- 3d ago First seen · 281 lines · 142 tokens per session scan A 93343ac19fde
rig-review is a skill published in the GitHub repository agent-rig/rig (2 stars, last pushed 16d ago), licensed MIT. It adds 142 tokens to every session and 4,336 once invoked, about $0.0007 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 2026-08-31.
Other skills, from other repositories
audit-onboarding-proposal
Independently audit a brownfield onboarding transcript, operational map, or exact proposed documentation patch before application. Use when a fresh reviewer must verify an $onboard-repository first pass, distinguish environment-caused Unknowns from reasoning defects, score its safety and evidence gates, or run a…
improve-harness
Run one explicitly authorized, evidence-backed improvement to a repository's agent guidance, tools, runbooks, or validation. Use only when the user invokes $improve-harness or explicitly asks to improve the Harness after observed reusable agent friction. Do not use for ordinary product changes, speculative cleanup…
ai-elements
Build AI chat interfaces using ai-elements components — conversations, messages, tool displays, prompt inputs, and more. Use when the user wants to build a chatbot, AI assistant UI, or any AI-powered chat interface.
red-team-adversarial
Adversarial security and resilience analysis — auto-triggered during /review and /test based on task classification. Provides attack surface analysis, boundary testing, auth bypass attempts, dependency chain attacks, and Beast Mode stress testing.
product-decision-agent
中文产品决策 Agent。用于中国大陆互联网产品、运营、增长、商业化、数据、项目推进和组织协作场景：产品规划、需求分析、PRD、需求优先级、排期、版本规划、Roadmap、MVP、灰度、上线、迭代、增长停滞、拉新、投放、渠道、裂变、CAC、LTV、ROI、留存、转化、DAU/MAU、GMV、漏斗、社区运营、内容供给、创作者、用户运营、活动运营、私域、会员、定价、指标异常、数据口径、埋点、A/B…
architecture-review
Use for clean architecture, modular monoliths, hexagonal boundaries, service boundaries, data flow, dependency direction, ADRs, or large feature planning.