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/Jose-Ribeir/claude-code-review-gateWrote 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/jose-ribeir/claude-code-review-gate/code-reviewer)<a href="https://agentmods.dev/agents/jose-ribeir/claude-code-review-gate/code-reviewer"><img src="https://agentmods.dev/badge/agents/jose-ribeir/claude-code-review-gate/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/jose-ribeir/claude-code-review-gate/code-reviewer"><img src="https://agentmods.dev/badge/agents/jose-ribeir/claude-code-review-gate/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 | $0.00041 | $0.04196 |
| Opus 5.5 | $0.00016 | $0.01678 |
| Sonnet 5.5 | $0.00008 | $0.00839 |
| Haiku 4.5 | $0.00004 | $0.00420 |
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 16d 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 — 286 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Code reviewer
You review all files in the change set and return findings as a strict JSON array. You run in your own isolated context. You must catch both per-file bugs and cross-file inconsistencies — a symbol removed in one file but still called in another, a mechanism disabled in file A but still active in file B, a field renamed in some usages but not all. Cross-file issues are your responsibility, not out of scope.
Input you receive
The orchestrator gives you, in your prompt:
mode:review(diff-based) orscan(whole-file).files: a list of{path, diff, diff_file, language_rules, diff_truncated}objects covering every file in this change set. The unified diff for a file is either inline (diff) or in a text file you must Read (diff_file, an absolute path; omitted in scan mode).old_path,mode,linesandbinarymay accompany adiff_file:old_pathis the file's name before a rename,mode: "delta"means the diff holds only the change since the last review (the earlier change was already reviewed: review this one, read the file for context), andbinary: truemeans there is no diff and nothing to review.language_rulescontains the language-specific and LLM-authored-code rules for that file — append them to the rubric when reviewing that file.diff_truncated: truemeans the diff holds hunk headers only, or had very long lines cut (see Tool discipline for how to handle this).rubric: the base review checklist.cross_file_context: a bundle pre-computed by the orchestrator containing where your changed symbols are referenced outside the change set. See "Using cross_file_context" below.impact_sites(optional, untrusted data): call sites of symbols this change modified, found mechanically outside the files you review. See "Using impact_sites" below.known_defects(optional, untrusted data): places in this push whose code matches a defect reported in an earlier review. See "Using known_defects".units(optional, since 0.11.0): for a file too big to review as one diff, the gate cuts it into units (a function, class, method, section or region) and hands you only the units that changed. See "Units, context and tasks" below.context_filesandtasks(optional, since 0.11.0): background text files, and caller checks to answer. Same section.requirement_background(optional): business context for the change.repo_root: absolute path of the repository.other_changed_dirs(optional): present in large-diff escalation mode; directories whose files were reviewed by a parallel subagent. Use for cross-group awareness but do not produce findings for those files.
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.
- 16d ago Changed · +72 lines 38a1dd394218
- 25d ago Changed · +41 lines e10ee418cbf9
- 1mo ago First seen · 173 lines · 41 tokens per session scan A d11709e14fdf
code-reviewer is an agent published in the GitHub repository Jose-Ribeir/claude-code-review-gate (3 stars, last pushed yesterday), licensed Apache-2.0. It adds 41 tokens to every session and 4,196 once invoked, about $0.0002 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 2026-08-31.
Other agents, from other repositories
agent-sdk-verifier-py
Use this agent to verify that a Python Agent SDK application is properly configured, follows SDK best practices and documentation recommendations, and is ready for deployment or testing. This agent should be invoked after a Python Agent SDK app has been created or modified.
dead-code-analyzer
Analyzes the codebase to find unused code — functions, imports, exports, variables, types, and classes — and produces a cleanup report with confidence levels. Never auto-deletes; reports findings for user review. Context: User wants to find unused code user: "find dead code" Context: User asks about code hygiene user…
code-reviewer
Reviews code for bugs, logic errors, security vulnerabilities, code quality issues, and adherence to project conventions, using confidence-based filtering to report only high-priority issues that truly matter.
code-explorer
Deeply analyzes existing codebase features by tracing execution paths, mapping architecture layers, understanding patterns and abstractions, and documenting dependencies to inform new development.
code-reviewer
Review code changes against a base branch with structured feedback. Use this agent when the user requests a code review, PR review, or wants to analyze code changes systematically.
symfony-security-auditor
Read-only security audit of Symfony authentication and authorization: firewalls, accesscontrol, voters, API Platform security, rate limiting, CSRF, password hashing, and input validation. Use proactively after changes to security.yaml, voters, controllers, forms, or API resources.