A review agent that checks each proposed file change before it is written to disk. It looks for whether the change meets its goal, syntax errors, broken imports, missing dependencies, and security problems.

Use it as a verification step for generated implementation changes, especially when checking Python syntax, imports, dependencies, or hardcoded secrets.

It catches flawed or unsafe changes at the point where they are proposed, before they become part of the codebase.

reviewer — Agent for Claude Code by strikersam

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.

Clone the repo

git clone --depth 1 https://github.com/strikersam/autonomous-ai-agency

Made for: Claude Code.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

README.md

[![agentmods](https://agentmods.dev/badge/agents/strikersam/autonomous-ai-agency/reviewer/github.svg)](https://agentmods.dev/agents/strikersam/autonomous-ai-agency/reviewer)

Your own site

<a href="https://agentmods.dev/agents/strikersam/autonomous-ai-agency/reviewer"><img src="https://agentmods.dev/badge/agents/strikersam/autonomous-ai-agency/reviewer/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

Your own site · 80×15

<a href="https://agentmods.dev/agents/strikersam/autonomous-ai-agency/reviewer"><img src="https://agentmods.dev/badge/agents/strikersam/autonomous-ai-agency/reviewer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 422 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

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.

Model	Per session	Once invoked
Fable 5.1	$0.00000	$0.00422
Opus 5	$0.00000	$0.00211
Sonnet 5	$0.00000	$0.00084
Haiku 4.5	$0.00000	$0.00042

Measured 8d ago against content hash 151680b5fdae, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, 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 8d 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/reviewer.md · 62 lines

What it actually says

Agent: Reviewer (Verifier)

Role

The Reviewer (Verifier) agent evaluates each file change produced by the Implementer before it is written to disk. It is the last gate before a file is modified.

Activation

Invoked via AgentRunner._execute_step() after each file is generated, before apply_diff() is called.

Preferred Model

deepseek-r1:32b (or AGENT_VERIFIER_MODEL env var) — reasoning model for evaluation.

Responsibilities

Compare original file content with proposed new content.
Check that the change accomplishes the step goal.
Identify any syntax errors, logical issues, or security problems.
Incorporate any pre-computed syntax_issues from _local_syntax_check().
Return a VerificationResult with:
- status: "pass" or "fail"
- issues: list of problems (empty on pass)
- suggestions: optional improvement notes

Output Format

{
  "status": "pass | fail",
  "issues": ["list of problems if fail"],
  "suggestions": ["optional notes"]
}

Blocking Conditions (must return `fail`)

Python syntax error in new content
Hardcoded secret (SECRET_KEY literal assignment)
Broken import or missing dependency
Step goal clearly not met by the change
Unsafe file path construction (in agent/tools.py changes)

Non-Blocking (may return `pass` with suggestions)

Style preferences
Minor naming issues
Optional optimization opportunities

Handoff

status: "pass" → Implementer proceeds with apply_diff()
status: "fail" → Implementer retries up to 3 times with the issues as feedback
After 3 retries → step recorded as failed

Key Invariant

The Reviewer must NEVER block indefinitely. After 3 fail cycles, it defers to the failure path rather than cycling forever.

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.

8d ago First seen · 62 lines · 0 tokens per session scan A 151680b5fdae

Subscribe to this mod's changes

reviewer is an agent published in the GitHub repository strikersam/autonomous-ai-agency (8 stars, last pushed today), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 422 tokens. 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 2026-09-03.

Code review Security agentic-ai ai-agents ai-automation ai-infrastructure ollama openai-compatible

code-reviewer

Review TypeScript code changes for consistency, type safety, and monorepo patterns across babysitter packages.

a5c-ai/babysitter · 24 tokens

Security Engineer

Expert application security engineer specializing in threat modeling, vulnerability assessment, secure code review, and security architecture design for modern web and cloud-native applications.

andywxy1/ceo-plugin · 31 tokens

Code Reviewer

Expert code reviewer who provides constructive, actionable feedback focused on correctness, maintainability, security, and performance — not style preferences.

andywxy1/ceo-plugin · 28 tokens

code-documentation-code-reviewer

Elite code review expert specializing in modern AI-powered code analysis, security vulnerabilities, performance optimization, and production reliability. Masters static analysis tools, security scanning, and configuration review with 2024/2025 best practices. Use PROACTIVELY for code quality assurance.

wshobson/agents · 60 tokens

sdk-api-documenter

Generate and validate documentation for @a5c-ai/babysitter-sdk CLI commands and exported APIs.

a5c-ai/babysitter · 25 tokens

shadow-auditor

Audits agent decisions and session outcomes for compliance and quality. Assign as a shadow for end-of-session review.

AgentWorkforce/relay · 27 tokens