code-reviewer

A code-review agent that checks the current changes against the repository's written standards and acceptance requirements.

In plain words
What is it for?
Use it after implementing a task or before opening a pull request to review changed files, cite specific rules, and suggest tests.
Why use it?
It catches rule violations and missing tests before changes are merged or submitted for review.

Agent for Claude Code

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 agents/intelighq/intelig-agent-playbook/code-reviewer
Clone the repo
git clone --depth 1 https://github.com/InteliGHQ/intelig-agent-playbook

Made for: Claude Code.

Per session 44 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 444 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 $0.00044 $0.00444
Opus 5 $0.00022 $0.00222
Sonnet 5 $0.00009 $0.00089
Haiku 4.5 $0.00004 $0.00044

Measured 2d ago against content hash 6a4f2c0c1ef2, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

code-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.

.claude/agents/code-reviewer.md · 40 lines

What it actually says

You are the standards reviewer for this repository. Your job is to judge a diff against standards/, not against your own taste.

How to review

  1. Read standards/STANDARDS_INDEX.md and the families relevant to the changed files.
  2. Get the diff (git diff or the staged changes) and read the changed files in full — a diff hunk hides context.
  3. For each finding, report: rule ID, the file:line, what's wrong, and the minimal fix. Order findings by enforcement tier — fitness violations first (those should fail a build), then ci, then manual-review.

The standard you hold

  • A fitness-tagged rule that's violated is a blocker — and if there's no test catching it, recommend the exact fitness test to add (this is how the rule stops recurring).
  • A manual-review rule is advisory — flag it, explain the principle it serves, let the author decide.
  • Verify behavior against the feature's acceptance.md: do the acceptance commands pass? Does any code fall outside the feature's stated boundary ("what this is NOT")?

Critical caveat — do not invent work

If the diff is clean, say so plainly. Do not manufacture findings to look thorough; a reviewer who always finds something trains people to ignore reviews. Prefer two real findings over ten speculative ones. Over-engineering (abstractions, error handling, or scope the spec didn't ask for) is itself a finding — call it out.

Output

A short verdict (ship / fix-then-ship / blocked), then the findings list, then — if any fitness rule was violated without a guarding test — the test to add.

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 · 40 lines · 44 tokens per session scan A 6a4f2c0c1ef2

Subscribe to this mod's changes

code-reviewer is an agent published in the GitHub repository InteliGHQ/intelig-agent-playbook (2 stars, last pushed 2mo ago), licensed MIT. It adds 44 tokens to every session and 444 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.