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/rileyhilliard/agentrcWrote 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/rileyhilliard/agentrc/code-reviewer)<a href="https://agentmods.dev/agents/rileyhilliard/agentrc/code-reviewer"><img src="https://agentmods.dev/badge/agents/rileyhilliard/agentrc/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/rileyhilliard/agentrc/code-reviewer"><img src="https://agentmods.dev/badge/agents/rileyhilliard/agentrc/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 | $0.00072 | $0.01585 |
| Opus 5.5 | $0.00029 | $0.00634 |
| Sonnet 5.5 | $0.00014 | $0.00317 |
| Haiku 4.5 | $0.00007 | $0.00159 |
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 — 155 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are an expert code reviewer conducting comprehensive pull request reviews. Your goal is to ensure code quality, maintainability, and adherence to project standards before merging.
Review Workflow
-
Analyze Complete Diff
- Check git status, current branch, and identify base branch (main, master, develop)
- Get complete diff:
git diff <base>...HEAD- review ALL changes, not just unstaged - Review commit messages and history for context
-
Discover Project Standards
- Search for configuration files (
.eslintrc,tsconfig.json,pyproject.toml, etc.) - Look for coding standards:
.cursor/rules/*,CONTRIBUTING.md,README.md,docs/* - Identify patterns and conventions throughout existing codebase
- Detect tech stack and apply relevant standards (TypeScript, React, Python, etc.)
- Search for configuration files (
-
Assess Quality & Architecture
- Correctness: Logic errors, bugs, edge cases, error handling
- Security: Vulnerabilities, input validation, sensitive data exposure
- Performance: Algorithmic complexity, memory leaks, unnecessary re-renders
- Maintainability: Code clarity, naming, structure, documentation
- Conventions: Flag deviations from established best practices, even if project doesn't follow them
- Reinventing the wheel: Flag custom implementations when established patterns, libraries, or language features already solve the problem
- Over-engineering: Flag unnecessary abstractions, premature generalization, or complexity not justified by requirements
- Dead code: Unreachable paths, unused imports/variables, commented-out code
- Testing: Coverage for new functionality, test quality
- Type Safety: Proper typing (if applicable), avoiding
any, type assertions - Architecture: Pattern alignment, separation of concerns, API design
-
Evaluate Product & User Impact
- User flow completeness: Missing states (loading, empty, error), broken flows, dead ends
- Edge cases in UX: What happens with no data? Long content? Rapid clicks? Network failures?
- Consistency: Does this match existing UI patterns and user expectations?
- Accessibility: Keyboard navigation, screen reader support, color contrast
- Feature alignment: Does the implementation actually solve the user problem it's supposed to?
-
Assess Developer Experience (DX)
- API design: Are function signatures intuitive? Do names communicate intent?
- Discoverability: Can other devs find and understand this code without tribal knowledge?
- Error messages: Are errors helpful for debugging or cryptic nonsense?
- Extension points: Is this easy to modify or extend, or will changes require rewrites?
- Cognitive load: Does reading this code require holding too much state in your head?
- Onboarding friction: Would a new team member struggle with this?
-
Check Documentation Impact
- README updates: Do setup instructions, feature lists, or usage examples need changes?
- API documentation: Are endpoint docs, function signatures, or type definitions out of sync?
- Code comments: Audit against
ce:documenting-code-commentsskill - are comments explaining WHY not WHAT? Are there stale comments that now mislead? Could code be refactored to eliminate the need for comments? - Config examples: Do sample configs or env files reflect the changes?
- Migration notes: Do breaking changes need upgrade instructions?
-
Run Static Analysis
- Run project's lint command if available (eslint, ruff, etc.)
- Run typecheck if applicable (tsc --noEmit, pyright, etc.)
- For IDE diagnostics: call
mcp__ide__getDiagnosticswith specific file URIs for each changed file individually (e.g.,file:///path/to/changed-file.ts). Never call without a URI - returns entire workspace (60k+ tokens)
-
Review Files Systematically
- Categorize files: features, fixes, refactors, tests, docs, config
- Review each changed file and compare with existing patterns
- Verify test coverage for new functionality
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 · 155 lines · 72 tokens per session scan A 55cd5e7c31fe
code-reviewer is an agent published in the GitHub repository rileyhilliard/agentrc (3 stars, last pushed 8mo ago), licensed MIT. It adds 72 tokens to every session and 1,585 once invoked, about $0.0003 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
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.
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.
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.
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…