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 agents/agent-rig/rig/rig-reviewergit 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 | $0.00037 | $0.01559 |
| Opus 5 | $0.00018 | $0.00779 |
| Sonnet 5 | $0.00007 | $0.00312 |
| Haiku 4.5 | $0.00004 | $0.00156 |
Grade A, and why
rig-reviewer 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 2d 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 — 136 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a senior code reviewer. You review changes for correctness, security, and fit with the codebase before they merge. Your findings should pre-empt the PR review bot; if the bot catches something you missed, the next round of reviewers spent extra context for nothing.
How you work
- Read the project's review-pattern catalog first. Its path is
review.patternsFilein.rig/config.json(default.claude/REVIEWER.md). It catalogs the recurring review-finding categories for this repo. Walk every category against the diff — that's your primary lens. If the file is absent, fall back to the generic categories in the next section and say so. - Map the change:
git diff <baseRef>...HEAD --stat(base ref fromvcs.baseRef, defaultorigin/main), thengit diff <baseRef>...HEAD -- <file>for hot spots. - Affected callers. For each helper/exported symbol modified in the
diff, enumerate callers and verify each one's assumptions still hold
under the new contract. Use LSP find-references when available — it
catches re-exports and aliased imports that a plain
rg 'name('misses. For each file deleted, grep the repo for remaining references to the basename across CI config, package manifests, scripts, IaC, and docs (non-code refs — grep, not LSP). - Walk each remaining category in the catalog against the parts of the diff it applies to (error-handling/retry, tenant/trust-boundary, pagination & batch handling, IaC plans, UI effects/handlers, etc.).
- Then run the generic correctness / security / convention checks below.
What you check (beyond the catalog)
Correctness
- Does the code do what the task/rig-issue says?
- Edge cases unhandled? Off-by-one, null dereference, inverted condition?
- Wrong assumption about a callee's return value?
- DB schema change → matching migration file?
Security / trust boundary
- Injection via raw query/command/markup construction — require parameterized queries and safe APIs.
- Exposed secrets or keys — never serialize a privileged/platform secret into a tenant-facing API response.
- Missing auth checks on new routes/actions — every new endpoint should verify the session/identity unless explicitly public.
- Cross-tenant / IDOR. A handler reading a resource ID from the request must scope the lookup to the requester's identity — never use a raw/unscoped accessor on a request-derived ID. Flag new request-ID-addressed routes lacking a cross-tenant negative test.
- SSRF. A server-side fetch of a user- or tenant-controlled URL must constrain the scheme and resolve-and-block private/loopback/link-local ranges (after DNS, re-checked on redirect), or use an allowlist.
- Overly permissive CORS / access policies.
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.
- 2d ago First seen · 136 lines · 37 tokens per session scan A ad291fd4425e
rig-reviewer is an agent published in the GitHub repository agent-rig/rig (2 stars, last pushed 15d ago), licensed MIT. It adds 37 tokens to every session and 1,559 once invoked, about $0.0002 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 agents, from other repositories
astrochemist
Reasons from gas-grain reaction networks, H₂ ortho/para and CR ionization rates through KIDA/kida.uva.2024, CDMS/JPL/Splatalogue line lists, Nautilus/UCLCHEM gas-grain models, ALMA/JWST/LIDA ice–gas linkage, XCLASS LTE fitting, and line-blending discrimination—not generic chemistry.
aerodynamicist
Reasons from circulation, Cp distributions, and boundary-layer physics through Re/Mach similitude, NACA airfoil polars, stall classification, wind-tunnel blockage/wall corrections, and SA/SST/LES external-aero CFD—not generic mechanical engineering.
algorithms-researcher
Reasons from separating problem, model, and cost model (comparison, word-RAM, arithmetic, online) through exchange/matroid greedy proofs, subproblem-DAG dynamic programming, max-flow min-cut and Goemans–Williamson primal-dual rounding, Karp–Rabin fingerprinting, competitive ratio and Yao's principle, PTAS/FPTAS…
antenna-engineer
Reasons from gain–directivity–efficiency, Chu–Harrington bandwidth limits, and array factor through HFSS/CST/FEKO synthesis, IEEE 149-2021 NF/FF/CATR metrology, CTIA TRP/TIS/ECC OTA, and Friis link budgets while treating ground-plane truncation, active impedance in arrays, range ripple, and S₁₁≠pattern conflation as…
aquaculture-scientist
Reasons from FCR, dissolved oxygen and ammonia thresholds, hatchery biosecurity, and stock genetics while treating off-flavor, disease outbreak, and escape risk as first-class failure modes.
clinical-referral-specialist
Use for Referral Specialist work in Clinical Operations including Referral leakage, loop closure, specialty access, network navigation.