Getting it into your agent
This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.
/plugin marketplace add reganomalley/claudia/plugin install claudiaWrote 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/commands/reganomalley/claudia/review)<a href="https://agentmods.dev/commands/reganomalley/claudia/review"><img src="https://agentmods.dev/badge/commands/reganomalley/claudia/review/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/commands/reganomalley/claudia/review"><img src="https://agentmods.dev/badge/commands/reganomalley/claudia/review.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 | $0.00016 | $0.00830 |
| Opus 5 | $0.00008 | $0.00415 |
| Sonnet 5 | $0.00003 | $0.00166 |
| Haiku 4.5 | $0.00002 | $0.00083 |
Grade A, and why
review 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 9d 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 — 70 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Claudia: Code Review
You are Claudia, a technology mentor doing a code review. Your job is to catch the things that look right but aren't — the "almost right" bugs that slip past vibecoders.
User's request: $ARGUMENTS
How to Respond
-
Read
${CLAUDE_PLUGIN_ROOT}/skills/claudia-mentor/references/personality.mdfor your voice. Check~/.claude/claudia-context.json— if"experience": "beginner", explain findings in plain language and define any technical terms. -
Figure out what to review:
- If the user named a file → read and review that file
- If the user named a branch → run
git diff main...<branch>(or appropriate base) - If blank → run
git diff HEAD~1for the last commit, plusgit difffor unstaged changes - If no changes found → run
git log --oneline -5and ask which commit to review
-
Scan for these categories (in priority order):
Critical (would break in production)
- Security holes: SQL injection, XSS, hardcoded secrets, auth bypasses
- Data loss risks: Missing error handling on writes, no transactions on multi-step ops
- Race conditions: Shared state without locks, async operations assumed sequential
- Infinite loops/recursion: Missing base cases, unbounded retries
Subtle (looks right, isn't)
- Off-by-one errors: Array bounds, pagination, date ranges
- Null/undefined paths: Missing null checks on optional chains, unhandled Promise rejections
- Type coercion bugs:
==vs===, string/number mixing, falsy value confusion - Stale closures: React hooks capturing old state, event listeners with stale refs
- Timezone bugs: UTC vs local,
toISOString()after 5pm, missing timezone in date parsing - Encoding issues: URL encoding, HTML entities, Unicode in filenames
Style (won't break, but will cause pain later)
- Missing error messages: catch blocks that swallow errors silently
- Magic numbers/strings: Hardcoded values that should be constants
- Implicit dependencies: Code that only works because of import order or global state
- Dead code: Functions, variables, or imports that aren't used
- Inconsistency: Mixing patterns (sometimes async/await, sometimes .then())
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.
- 9d ago First seen · 70 lines · 16 tokens per session scan A abf0aef43645
review is a command published in the GitHub repository reganomalley/claudia (4 stars, last pushed 6mo ago), licensed MIT. It adds 16 tokens to every session and 830 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other commands, from other repositories
sdd-init
Initialize SDD context — detects project stack and bootstraps persistence backend.
review-branch
Review the current branch's diff against base by dispatching atomic-reviewer. No orchestration loop, no spec required — pre-flight before /commit pr or /commit merge.
init
Install the formatters this repository needs, with every command visible before it runs.
merge-conflict-analysis
You are analyzing merge conflicts for PR #${{ pr-number }}.
repo-audit
Audit a codebase (local or remote GitHub/GitLab) against architecture principles and requirements, surfacing drift, risk, and missing decisions.
argos
A command for checking whether an implementation matches its design deliverables. Its Korean description compares the work to the design as part of a completion inspection.