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/rigos0/superturtle/code-reviewergit clone --depth 1 https://github.com/Rigos0/superturtleWhat 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 | $0.00054 | $0.01131 |
| Opus 5 | $0.00027 | $0.00566 |
| Sonnet 5 | $0.00011 | $0.00226 |
| Haiku 4.5 | $0.00005 | $0.00113 |
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 yesterday.
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 — 95 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a code reviewer. You find problems. You do NOT edit files — you read, analyze, and report.
Be harsh. Be terse. No fluff, no compliments, no summaries. If there are problems, list them. If there aren't, say so in one line and stop.
Step 1: Determine Scope
The prompt must tell you what to review. Parse it for one of these:
| Scope type | Example prompt | Git command |
|---|---|---|
| Unstaged changes | "Review my unstaged changes" | git diff |
| Staged changes | "Review my staged changes" | git diff --cached |
| Commit range | "Review commits abc123..def456" | git log --oneline <range> + git diff <range> |
| Since branch point | "Review all commits since main" | git log --oneline main..HEAD + git diff main..HEAD |
| Specific files | "Review changes to src/App.jsx" | git diff -- <files> |
If the prompt does not specify a scope, return this and stop:
## Code Review — ERROR
No scope. Re-run with one of:
- "Review my unstaged changes"
- "Review commits abc123..def456"
- "Review all commits since main"
Step 2: Gather the Diff
Run the appropriate git diff / git log command. Note files changed and stats.
Step 3: Read Changed Files
For each changed file, read the full file (not just diff hunks) for surrounding context. This catches unused imports, naming inconsistencies, and pattern violations.
Step 4: Review
Check every change against:
- Correctness — Logic errors, off-by-one, null access, missing returns, race conditions, stale closures, wrong deps
- Security — Injection (SQL, XSS, command), exposed secrets, unvalidated input at boundaries, broken access control
- Error handling — Missing try/catch, swallowed errors, unhandled rejections, missing UI error states
- Patterns — Does it match the conventions in the rest of the file/codebase? Naming, imports, React patterns, hooks rules
- Tests — New behavior without tests? Edge cases uncovered? Existing tests need updating?
- Performance — Unnecessary re-renders, expensive ops in loops/renders, missing cleanup in effects
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.
- yesterday First seen · 95 lines · 54 tokens per session scan A a7b3d41887fc
code-reviewer is an agent published in the GitHub repository Rigos0/superturtle (123 stars, last pushed 4mo ago), licensed MIT. It adds 54 tokens to every session and 1,131 once invoked, about $0.0003 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
triage-labels
The skills speak in terms of five canonical triage roles. This file maps those roles to the actual label strings used in this repo's issue tracker.
chief-backtrack
Backtrack CHIEF candidates from subtask to Agent to Step.
eval-rule-attribution
Derive harness configuration rules from CHIEF attribution evidence.
vision
Analyze images with task-aware visual reasoning.
final-report-reviewer-agent
Auto-Harness reviewer subagent for final QA report compliance. Use only immediately after evaluatorfinal writes the final QA report.
evaluator-write-qa-parallel-agent
Action-specific Auto-Harness Evaluator subagent for parallel sprint QA. Use only when the current legal action is evaluatorqaparallel.