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.
npx agentmods add agents/jose-ribeir/claude-code-review-gate/code-reviewergit 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.svg" alt="Measured on agentmods" 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 | $0.00041 | $0.02241 |
| Opus 5 | $0.00020 | $0.01120 |
| Sonnet 5 | $0.00008 | $0.00448 |
| Haiku 4.5 | $0.00004 | $0.00224 |
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 4d 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 — 173 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, language_rules, diff_truncated}objects covering every file in this change set.diffis the unified diff for that file (omitted in scan mode).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 was capped to stat + hunk headers only (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.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.
- 4d 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 7d ago), licensed Apache-2.0. It adds 41 tokens to every session and 2,241 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.
Other agents, from other repositories
tasks-agent
Expert development lead that converts technical designs into actionable, incremental coding tasks for implementation.
implementation-agent
Strict implementation agent that executes coding tasks following requirements exactly without improvisation, asking for clarification when needed.
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.
experience-extractor
Learning agent for the Self-Evolving Loop. Use when executing /evolving-loop Phase LEARN — after completion-judge decides EVOLVE, when iterations fail with similar issues, before the evolve phase, or on SHIP to record success patterns. Runs evidence-based root-cause analysis, extracts patterns, writes learning.json…
agents-expert
Expert on creating and configuring custom Claude Code agents (subagents). Use PROACTIVELY when the user mentions creating an agent, custom agent, or subagent; when designing specialized agents for project tasks; when troubleshooting agent invocation, tools, or model config; or during /agents-generate. Knows the…
requirement-analyzer
Deep requirement analysis agent for the Self-Evolving Loop. Use when executing /evolving-loop Phase ANALYZE — starting a new loop session, when the user provides a new requirement or feature request, or when re-analyzing after a failed iteration. Extracts acceptance criteria, a complexity score, an implementation…