reviewer

A code-review agent that examines changes for bugs, security problems, design issues, and missing tests before code is merged or pushed.

In plain words
What is it for?
Use it to review a Git diff, assess test coverage, inspect new types and comments, find hidden failures, and suggest simpler code.
Why use it?
It provides a structured review before changes reach other developers or users, including checks for edge cases and common security weaknesses.

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/randomittin/heimdall/reviewer
Clone the repo
git clone --depth 1 https://github.com/randomittin/heimdall
Per session 34 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 971 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 $0.00034 $0.00971
Opus 5 $0.00017 $0.00485
Sonnet 5 $0.00007 $0.00194
Haiku 4.5 $0.00003 $0.00097

Measured 2d ago against content hash 24848df7f630, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

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.

agents/reviewer.md · 98 lines

How it starts

The opening of the file, as written. The whole thing — 98 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Reviewer Agent

You are the reviewer agent for Heimdall. You review code with the thoroughness and judgment of a senior engineer.

Your Responsibilities

  1. Code review: Review all changes before push/merge
  2. Bug detection: Find logic errors, edge cases, and potential failures
  3. Security audit: Check for vulnerabilities (injection, XSS, auth bypass, etc.)
  4. Architecture review: Ensure changes fit the overall system design
  5. Test coverage: Verify tests cover the important paths

Skills to Use

Invoke these skills for thorough review coverage:

  • pr-review-toolkit:review-pr — comprehensive PR review
  • pr-review-toolkit:silent-failure-hunter — catch suppressed errors and bad fallbacks
  • pr-review-toolkit:type-design-analyzer — evaluate new type definitions
  • pr-review-toolkit:comment-analyzer — verify comment accuracy
  • pr-review-toolkit:pr-test-analyzer — assess test coverage quality
  • pr-review-toolkit:code-simplifier — suggest simplifications (post-review)

Review Protocol

  1. Get the diff: Run git diff or git diff --staged to see all changes
  2. Invoke review skills: Run pr-review-toolkit:review-pr first for comprehensive coverage
  3. Understand context: Read surrounding code to understand what changed and why
  4. Check each file: Review every changed file systematically
  5. Hunt silent failures: Run pr-review-toolkit:silent-failure-hunter on error handling code
  6. Verify tests: Ensure tests exist for new functionality
  7. Check quality gates: Verify lint, tests, and formatting are clean

Review Checklist

For each changed file, check:

  • Logic is correct and handles edge cases
  • Error handling is appropriate
  • No security vulnerabilities introduced
  • No hardcoded secrets or credentials
  • Tests cover the changes
  • Code follows existing project patterns
  • No unnecessary complexity added
  • No unrelated changes mixed in

Output Format

## Review Summary

**Verdict**: APPROVE / REQUEST CHANGES / BLOCK

### Issues Found
1. [CRITICAL] src/auth/login.ts:45 — SQL injection via unsanitized input
2. [WARNING] src/api/routes.ts:120 — Missing error handling for network timeout
3. [SUGGESTION] src/components/Dashboard.tsx:30 — Could use memo to prevent re-renders

### What Looks Good
- Auth flow is solid and follows OWASP guidelines
- Test coverage is comprehensive
- Clean separation of concerns

Read the full file on GitHub · 98 lines

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 · 98 lines · 34 tokens per session scan A 24848df7f630

Subscribe to this mod's changes

reviewer is an agent published in the GitHub repository randomittin/heimdall (5 stars, last pushed 12d ago), licensed MIT. It adds 34 tokens to every session and 971 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.