code-review

A structured review of code changes across correctness, readability, architecture, security, and performance. It reports findings by severity with file and line references, then gives a pass-or-fail verdict for each area.

In plain words
What is it for?
Use it to review staged changes or recent commits against a specification, inspect edge cases and tests, and get concrete recommendations for fixes.
Why use it?
It helps catch bugs, unclear code, design problems, security risks, and slow operations before changes are accepted. The verdict makes the overall state easy to assess.

Command

Install

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.

agentmods
npx agentmods add commands/askwigconsulting/cohort/code-review
Clone the repo
git clone --depth 1 https://github.com/askwigconsulting/cohort
Per session 19 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 415 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00019 $0.00415
Opus 5 $0.00010 $0.00208
Sonnet 5 $0.00004 $0.00083
Haiku 4.5 $0.00002 $0.00042

Measured 2d ago against content hash 214eebaf8878, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

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 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.

canonical/commands/code-review.md · 44 lines

What it actually says

Invoke the agent-skills:code-review-and-quality skill.

Review the current changes (staged or recent commits) across all five axes:

  1. Correctness — Does it match the spec? Edge cases handled? Tests adequate?
  2. Readability — Clear names? Straightforward logic? Well-organized?
  3. Architecture — Follows existing patterns? Clean boundaries? Right abstraction level?
  4. Security — Input validated? Secrets safe? Auth checked? (Use security-and-hardening skill)
  5. Performance — No N+1 queries? No unbounded ops? (Use performance-optimization skill)

Categorize findings as Critical, Important, or Suggestion. Output a structured review with specific file:line references and fix recommendations.

Verdict block

End your output with a fenced ```verdict block — one overall line plus one line per axis, each pass|fail with a one-line evidence note:

overall: PASS|FAIL
correctness: pass|fail — one-line evidence
readability: pass|fail — one-line evidence
architecture: pass|fail — one-line evidence
security: pass|fail — one-line evidence
performance: pass|fail — one-line evidence

Rules:

  • overall is FAIL if any axis is fail; PASS only if all five axes pass.
  • Emit exactly one line per axis, in the order above, even when an axis has no findings (pass — no issues found).
  • This fence must be the last fence in your output — it is the only verdict-shaped text a caller should trust. See the office-guide skill's "Verdict blocks" section for the full trust rule.
Changes

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.

  1. 2d ago First seen · 44 lines · 19 tokens per session scan A 214eebaf8878

Subscribe to this mod's changes

code-review is a command published in the GitHub repository askwigconsulting/cohort (2 stars, last pushed 25d ago), licensed MIT. It adds 19 tokens to every session and 415 once invoked, about $0.0001 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.