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 genai-io/san --skill code-reviewgit clone --depth 1 https://github.com/genai-io/sanWrote 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/genai-io/san/code-review)<a href="https://agentmods.dev/skills/genai-io/san/code-review"><img src="https://agentmods.dev/badge/skills/genai-io/san/code-review/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/genai-io/san/code-review"><img src="https://agentmods.dev/badge/skills/genai-io/san/code-review.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 | $0.01065 |
| Opus 5.5 | $0.00033 | $0.00426 |
| Sonnet 5.5 | $0.00017 | $0.00213 |
| Haiku 4.5 | $0.00008 | $0.00106 |
Grade A, and why
code-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 1mo 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 — 103 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Code Review: Correctness
Review the changed code for correctness bugs — cases where it does the wrong
thing, crashes, corrupts state, or breaks a contract. This skill is deliberately
scoped to bugs. Do not report reuse, quality, style, or efficiency cleanups here;
those belong to a separate cleanup pass (San's simplify skill, where present).
If the arguments include --fix, apply fixes after reporting. Otherwise report
only and offer to fix. A leading focus area (e.g. concurrency) narrows the
review to that dimension.
Phase 1: Identify Changes
Run git diff (or git diff HEAD when changes are staged) to see what changed.
If there are no git changes, review the most recently modified files the user
named or that you edited earlier in this conversation. Read enough of the
surrounding code that each changed line can be judged in context — a line is
rarely a bug on its own, only against the code that calls it and the code it
calls.
Phase 2: Launch Review Agents in Parallel
Use the Agent tool to launch the dimension agents concurrently in a single
message (foreground — do NOT set run_in_background). Pass each agent the full
diff plus the context it needs. Each agent returns a list of findings; every
finding must carry:
- a severity —
critical(crash, data loss, security),high(wrong result on a realistic input),medium(wrong only in an edge case),low(fragile, latent); - a
file:linereference; - a concrete failure scenario — specific inputs or interleaving that lead to the wrong outcome. A finding with no scenario is a guess; drop it.
Agent 1: Logic & Control Flow
- Off-by-one, wrong comparison or boolean operator, inverted condition.
- Incorrect boundary handling; loops that skip the first/last item or run one too many times.
- Branches that can't be reached, or that fall through when they shouldn't.
- Wrong operator precedence; integer division or truncation where not intended.
Agent 2: Nil, Errors & Return Values
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.
- 1mo ago First seen · 103 lines · 83 tokens per session scan A 7b7e707f26ea
code-review is a skill published in the GitHub repository genai-io/san (78 stars, last pushed today), licensed Apache-2.0. It adds 83 tokens to every session and 1,065 once invoked, about $0.0003 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 2026-08-30.
Other skills, from other repositories
code-review
Perform thorough code reviews with security, performance, and maintainability analysis. Use when user asks to review code, check for bugs, or audit a codebase.
review-this-branch
Run the nohuman review gate (fresh-session adversarial reviewer + tamper guard) over the current branch or a GitHub pull request, with no server, no database, and no onboarding, and relay the pass/fail checklist.
review-harness
Use when reviewing implementation work that ran through a /tmp Pi task harness. Checks contract drift, unsafe shortcuts, validation evidence, and status honesty.
scrutiny-validator
Adversarial scrutiny procedure for engineering validation assignments. Runs hard-gate commands, reviews the current implementation and evidence integrity against assigned contracts, can use feature-reviewer lanes, and returns per-target verdicts.
ahk-review
Preview a code review against ticket/objective alignment, with deep semantic (name-vs-behavior) analysis. No tasks created, no harness tracking.
pi-parity-review
Adversarially verify that a ported change is faithful to the original pi implementation (TS source + published npm build). Use after porting upstream pi changes, or standalone on any area of this repo ("is X faithful to pi?").