code-review

A command that runs the three-part adversarial code review covering code quality, requested behavior, and security or failure risks.

In plain words
What is it for?
Use it on a pull request, commit, code reference, pending changes, or a whole codebase.
Why use it?
It helps review different kinds of correctness separately instead of treating one overall impression as proof that a change is safe and complete.

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/ainative-build/skills/code-review
Clone the repo
git clone --depth 1 https://github.com/ainative-build/skills
Per session 33 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 255 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 $0.00033 $0.00255
Opus 5 $0.00016 $0.00128
Sonnet 5 $0.00007 $0.00051
Haiku 4.5 $0.00003 $0.00026

Measured 2d ago against content hash 3efb4ad6bb64, 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.

commands/code-review.md · 22 lines

What it actually says

/aif:code-review

Run the aif-code-review skill on the target described by $ARGUMENTS.

Read and follow ${CLAUDE_PLUGIN_ROOT}/skills/engineering/aif-code-review/SKILL.md in full, then execute its workflow against $ARGUMENTS:

  1. Resolve the input mode and pin the fixed-point SHAs.
  2. Discover the spec source and build the shared context pack.
  3. Dispatch the three axes — in parallel isolated subagents here (Task tool available), one axis each — using ${CLAUDE_PLUGIN_ROOT}/skills/engineering/aif-code-review/references/.
  4. Aggregate into three separate sections (never merged or re-ranked) per output-format.md.
  5. Apply the verification gate before any pass/fixed claim.

For the parallel axes, spawn the aif:code-reviewer agent per axis with the axis brief + shared context pack.

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 · 22 lines · 33 tokens per session scan A 3efb4ad6bb64

Subscribe to this mod's changes

code-review is a command published in the GitHub repository ainative-build/skills (7 stars, last pushed 1mo ago), licensed MIT. It adds 33 tokens to every session and 255 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.