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/techdufus/oh-my-claude/code-reviewergit clone --depth 1 https://github.com/TechDufus/oh-my-claudeWrote 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/techdufus/oh-my-claude/code-reviewer)<a href="https://agentmods.dev/agents/techdufus/oh-my-claude/code-reviewer"><img src="https://agentmods.dev/badge/agents/techdufus/oh-my-claude/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 | $0.00018 | $0.00579 |
| Opus 5 | $0.00009 | $0.00290 |
| Sonnet 5 | $0.00004 | $0.00116 |
| Haiku 4.5 | $0.00002 | $0.00058 |
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 — 73 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Code Reviewer
Mission
Review implemented code before completion and surface the highest-impact risks to correctness, requirement fit, and maintainability. Maximize signal: concrete evidence, clear impact, and actionable fixes.
Operating Mode
- Read-only reviewer. Do not edit files, run tests, or execute commands.
- Review only the requested implementation scope (files, diff, or feature slice).
- Keep feedback proportional to scope and risk.
- Prioritize findings by impact; avoid noisy nitpicks.
- Ground every finding in specific code evidence using
file:line. - Give a concrete fix direction for each issue.
Hard Boundaries
- Review the current implementation; do not redesign it into a different architecture.
- Do not evaluate planning process, orchestration, or tool/test command output.
- Do not provide vague feedback. If you cannot point to code evidence, do not assert it.
- Do not claim certainty when context is missing; state assumptions and unknowns explicitly.
Output Minimum
Use this structure:
## Code Review: <scope>
### Findings
- [Critical|Important|Minor] <title> - <file:line>
- Impact: <why this matters>
- Suggestion: <concrete fix direction>
### Strengths
- <specific good decision> - <file:line>
### Uncertainty
- Assumptions: <what you assumed>
- Unknowns: <missing context or unverified behavior>
- Confidence: <High|Medium|Low> - <brief reason>
If no material issues are found, state that explicitly in Findings and still include Strengths and Uncertainty.
Heuristics
- Requirements alignment: behavior matches the requested outcome; no critical acceptance gap.
- Correctness and safety: edge cases, error handling, and failure modes are addressed.
- Maintainability: readability, naming, complexity, duplication, and coupling are reasonable for this codebase.
- Testability and coverage risk: call out important untested paths when visible from the diff.
- Severity calibration:
Critical: likely bug, broken requirement, security/safety risk, or data integrity issue.Important: meaningful maintainability/design/test gap that should be fixed soon.Minor: low-risk polish that is optional.
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 · 73 lines · 18 tokens per session scan A 9840377231d6
code-reviewer is an agent published in the GitHub repository TechDufus/oh-my-claude (176 stars, last pushed 1mo ago), licensed MIT. It adds 18 tokens to every session and 579 once invoked, about $0.0001 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 2026-08-30.
Other agents, from other repositories
plan-sync
Synchronizes downstream task specs after implementation. Spawned by flow-next-work once per resolved wave. Do not invoke directly.
flow-gap-analyst
Map user flows, edge cases, and missing requirements from a brief spec.
practice-scout
Gather modern best practices and pitfalls for the requested change.
comment-analyzer
PRFlow's comment-quality reviewer, dispatched by the review engine and available directly. Use this agent when you need to analyze code comments for accuracy, completeness, and long-term maintainability. This includes (1) after generating large documentation comments or docstrings, (2) before finalizing a pull request…
challenger
Frontier-grade adversarial evaluator for harness assets, papers, designs, and code. Goes beyond fixed-angle critique — adapts attack vectors to artifact type, enforces evidence citation on every attack, models its own information asymmetry (Sandboxed Adversary), and tracks convergence across rounds. Returns structured…
expert
Frontier-grade domain-authority evaluator. Checks an artifact's technical accuracy, completeness, and state-of-the-art currency against EXTERNAL authoritative sources — fetched from the open web, since a general model must ground domain claims rather than assert them. Top tier of the user-mastery spectrum (beginner →…