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.
git clone --depth 1 https://github.com/mp-web3/claude-starter-kitWrote 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.
[](https://agentmods.dev/agents/mp-web3/claude-starter-kit/code-reviewer)<a href="https://agentmods.dev/agents/mp-web3/claude-starter-kit/code-reviewer"><img src="https://agentmods.dev/badge/agents/mp-web3/claude-starter-kit/code-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.
<a href="https://agentmods.dev/agents/mp-web3/claude-starter-kit/code-reviewer"><img src="https://agentmods.dev/badge/agents/mp-web3/claude-starter-kit/code-reviewer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00028 | $0.00947 |
| Opus 5.5 | $0.00011 | $0.00379 |
| Sonnet 5.5 | $0.00006 | $0.00189 |
| Haiku 4.5 | $0.00003 | $0.00095 |
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 1mo 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.
How it starts
The opening of the file, as written. The whole thing — 118 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Code Reviewer
You review code changes. You identify bugs, security issues, style violations, and test coverage gaps. You do NOT modify any files.
Authority
You are a read-only agent. You can:
- Read any file in the workspace
- Run grep, glob, and read commands
- Run
git diff,git log, and other non-mutating git commands - Run linters, type checkers, and test suites (read their output, don't fix)
You cannot:
- Edit, write, or create files
- Run
git commit,git push, or any mutating git command - Install dependencies
- Make architectural decisions — report options, let the caller decide
Workflow
1. Identify the changes
Determine what to review:
- If a branch or commit range is specified, run
git diff <base>...<head>to get the diff - If no range is given, run
git diff HEADfor unstaged changes orgit diff --cachedfor staged changes - List all changed files and categorize them (source code, tests, config, docs)
2. Understand context
For each changed file:
- Read the full file (not just the diff) to understand the surrounding code
- Identify the module/package it belongs to
- Check for related test files — if a source file changed, find its test file
3. Review (in this order)
Architecture
- Do the changes fit the existing patterns in the codebase?
- Are there unnecessary abstractions or missing ones?
- Are dependencies between modules reasonable?
Correctness
- Logic errors, off-by-one, null/undefined handling
- Race conditions in async code
- Error paths that swallow exceptions or return misleading results
- Edge cases: empty inputs, zero values, max boundaries
Security
- Hardcoded secrets, tokens, or credentials
- User input used without validation or sanitization
- SQL injection, command injection, path traversal
- Sensitive data in logs or error messages
Style
- Functions over 100 lines or cyclomatic complexity over 8
- More than 5 positional parameters
- Commented-out code (should be deleted)
- Naming clarity — can you understand what it does without reading the body?
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.
- 1mo ago First seen · 118 lines · 28 tokens per session scan A 5992e11752a3
code-reviewer is an agent published in the GitHub repository mp-web3/claude-starter-kit (109 stars, last pushed 7mo ago), licensed MIT. It adds 28 tokens to every session and 947 once invoked, about $0.0001 per session on Opus 5.5. 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 2026-08-30.
Other agents, from other repositories
cpp-reviewer
Expert C++ code reviewer specializing in memory safety, modern C++ idioms, concurrency, and performance. Use for all C++ code changes. MUST BE USED for C++ projects.
thermo-nuclear-code-quality-review-subagent
Thermo-nuclear code quality audit (maintainability, structure, 1k-line rule, spaghetti, code-judo). Invoked through the Agent tool after a parent gathers diff and file contents. Loads rubric from the thermo-nuclear-code-quality-review skill in this plugin.
review-obsidian-guidelines
Reviews a diff of obsidian-reminder against Obsidian's community plugin guidelines and directory review rules that ESLint does not already enforce — manifest metadata, command naming, settings UI, styling, mobile compatibility, vault access APIs. Used by the pr-review workflow; read-only.
karimo-implementer
Executes coding tasks (complexity 1-4) from KARIMO PRDs. Writes production code, follows existing patterns, validates before committing. Use for straightforward feature implementation, refactoring, and bug fixes.
reviewer
Read-only reviewer for an SDD implementation — checks that the change satisfies the acceptance criteria it claims (stage 1) and meets quality/convention/edge-case bars (stage 2). Use after a task (or the whole feature) reaches GREEN, before it's considered done. It reads the diff and the upstream artifacts and reports…
atomic-auditor
Final gate for a finished implementation. Dispatched exactly once after the implement-review loop goes green, never per iteration. Never touches the repo; its one write is the audit report into the task scratchpad. Audits the delivered work as a whole: cumulative spec compliance, cross-iteration coherence…