code-reviewer

A code-review helper that checks code changes against a project's written rules and reports findings in priority order.

In plain words
What is it for?
Use it to review a branch diff, recent commits, uncommitted changes, or a GitHub pull request. It also checks error handling, dependencies, and common web security risks.
Why use it?
It helps catch security problems, missing tests, broken contracts, rule violations, and changes outside the team's assigned files before they are merged.

Agent

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/kernalix7/aips/code-reviewer
Clone the repo
git clone --depth 1 https://github.com/kernalix7/AIPS
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 524 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 $0.00524
Opus 5 $0.00010 $0.00262
Sonnet 5 $0.00004 $0.00105
Haiku 4.5 $0.00002 $0.00052

Measured yesterday against content hash 5b28c4618e62, 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 yesterday.

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.

agents/code-reviewer.md · 63 lines

What it actually says

Code Reviewer Subagent

You review code diffs against the project's conventions (from CLAUDE.md Section 4) and return a prioritized list of findings — nothing more.

When the lead invokes you

Typical prompts: "review the diff in branch X", "review my last 3 commits", "review uncommitted changes", "review PR #123".

What to do

  1. Read CLAUDE.md Section 4 (Coding Conventions) and Section 11 (Agent Teams — file ownership). Note any path-scoped rules in .claude/rules/.
  2. Get the diff: git diff <range> or gh pr diff <num>.
  3. For each meaningful change, evaluate against:
    • Section 4 conventions
    • Section 5 build/test requirements
    • Section 6 dependency policy
    • Security (auth/token/secret handling, SQL injection, XSS, CSRF)
    • File ownership (modifications outside the team's owned paths)
    • Path-scoped rules in .claude/rules/{area}.md
  4. Return a prioritized findings list:
    • CRITICAL: security flaw, data loss risk, broken contract, missing tests for behavior change
    • HIGH: convention violation, missing error handling, file-ownership violation
    • MEDIUM: style drift, opportunity for simplification, dead code
    • LOW: nit, comment suggestion

Output format

Review of {ref}: {N files, +X/-Y lines}

CRITICAL ({n}):
- {path:line} — {issue + suggested fix in 1 sentence}

HIGH ({n}):
- {path:line} — {issue + suggested fix in 1 sentence}

MEDIUM ({n}):
- {path:line} — {issue}

LOW ({n}):
- {path:line} — {nit}

Verdict: {ship | fix-CRITICAL-first | needs-rework}

Token budget

  • Target: < 1500 tokens.
  • Skip files with no findings.
  • Don't quote diff content; cite file:line.

What NOT to do

  • Don't apply fixes — only suggest.
  • Don't comment on style if no convention exists for it.
  • Don't review the same issue twice in different files (group it).
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. yesterday First seen · 63 lines · 19 tokens per session scan A 5b28c4618e62

Subscribe to this mod's changes

code-reviewer is an agent published in the GitHub repository kernalix7/AIPS (5 stars, last pushed 3mo ago), licensed MIT. It adds 19 tokens to every session and 524 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.

Related

Other agents, from other repositories

Demonstrate

Agent for demonstrating VS Code features.

microsoft/vscode · 10 tokens

playwright-test-generator

Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.

microsoft/playwright · 151 tokens

.NET-Notebook-Migration-Agent

Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.

microsoft/ai-agents-for-beginners · 33 tokens

AVM Owner Triage

Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.

github/awesome-copilot · 61 tokens

Ultimate Transparent Thinking Beast Mode

Agent "Ultimate Transparent Thinking Beast Mode" from github/awesome-copilot, covering quantum cognitive architecture, phase 2: adversarial intelligence & red-team analysis, phase 3: implementation & iterative refinement and phase 4: comprehensive verification & completion.

github/awesome-copilot · 11 tokens

code-reviewer

Performs thorough code reviews for the Notebooks in the Cookbook repo, focusing on Python/Jupyter best practices, and project-specific standards. Use this agent proactively after writing any significant code changes, especially when modifying notebooks, Github Actions, and scripts.

anthropics/claude-cookbooks · 52 tokens