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 skills add nguyenthienthanh/aura-frog --skill code-reviewergit clone --depth 1 https://github.com/nguyenthienthanh/aura-frogWrote 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/skills/nguyenthienthanh/aura-frog/code-reviewer)<a href="https://agentmods.dev/skills/nguyenthienthanh/aura-frog/code-reviewer"><img src="https://agentmods.dev/badge/skills/nguyenthienthanh/aura-frog/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/skills/nguyenthienthanh/aura-frog/code-reviewer"><img src="https://agentmods.dev/badge/skills/nguyenthienthanh/aura-frog/code-reviewer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Agent Snooping · line 67 Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.Fix: Remove all code or instructions that list or read other skills' files or directories. Skills should operate independently; cross-skill access is a privilege escalation.
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 | $0.00105 | $0.01602 |
| Opus 5.5 | $0.00042 | $0.00641 |
| Sonnet 5.5 | $0.00021 | $0.00320 |
| Haiku 4.5 | $0.00011 | $0.00160 |
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 — 116 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AI-consumed reference. Optimized for Claude to read during execution. Sources and quotes for every standard below:
references/standards.md.
Code Reviewer
Runs in: TDD Phase 4 (reviewer ≠ Phase 3 builder), /check review [path|PR], /run review <target>, or on request.
Bar
Approve when the change definitely improves code health, even if not perfect. Technical facts beat opinions; the project's style guide and linters settle style — don't repeat them.
Process
- Scope:
git diff --name-only <base>...HEAD(or the given path/PR). Read diff hunks + immediate callers/callees, not whole files. - Size check: >400 changed lines → review in file groups and state which groups were covered. Never claim full coverage you didn't do.
- Read every changed line. Run the 8 aspects, CRITICAL-priority ones first.
- Verify each candidate finding (below), drop the unproven, report.
8 Aspects
aspects[8]{aspect,priority,checks}:
Security,CRITICAL,"OWASP Top 10:2025 (list below) · CWE Top 25 · secrets · untrusted input reaching queries/shell/HTML/paths · authz on every protected action"
Correctness,CRITICAL,"Does it do what the task intends? Off-by-one, null/empty/boundary input, wrong operator/condition, races and shared state, time zones, partial failure leaving bad state"
Compatibility,CRITICAL,"No breaking change: public API/CLI/config/schema/file format/defaults/output shape unchanged unless versioned; observable behavior others rely on (Hyrum's law); migration or deprecation path"
Architecture,HIGH,"Right layer, SRP, coupling, fits existing patterns; reuse over new helper"
Error Handling,HIGH,"Swallowed errors, empty catch, fail-open on exceptions (OWASP A10), missing cleanup, errors that leak secrets/internals"
Test Gaps,HIGH,"Changed behavior without a test; missing edge/failure-path test; tests that can't fail"
Type Safety,MEDIUM,"any/unchecked casts, unhandled null, unvalidated external data"
Simplicity,MEDIUM,"Over-engineering, speculative code, dead code, unnecessary comments (rules below)"
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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 Changed · +31 lines · +41 tokens per session 4fda6447e178
- 1mo ago First seen · 85 lines · 64 tokens per session scan A be179bc53309
code-reviewer is a skill published in the GitHub repository nguyenthienthanh/aura-frog (25 stars, last pushed 3d ago), licensed MIT. It adds 105 tokens to every session and 1,602 once invoked, about $0.0004 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 2026-08-30.
Other skills, from other repositories
review-pr
Multi-agent PR review with four modes (review, re-review, self-review, address-feedback) - spawns parallel subagents, saves diff to /tmp for context efficiency, supports file exclusion patterns.
codex-code-review
Automate code review remediation loops with the codex CLI. Requests reviews from codex, classifies findings by severity (P0-P4), fixes critical issues (P0/P1) through iterative cycles, defers quality improvements to backlog, and escalates after 3 review cycles. Use when working with code that needs structured…
github-commander
Structured workflows for GitHub issues, PRs, milestones, and code audits with validation gates and HITL checkpoints. Use when assigned a GitHub issue, reviewing a PR, sprinting through a milestone, updating dependencies, or running code audits. Also use when asked to "triage an issue", "review a PR", or "update deps".…
adversarial-workflow-audit
Multi-pass adversarial quality audit for flat markdown workflow files. Combines structured evaluation (Agent A) with adversarial stress-testing (Agent B) to assess sequential clarity, prerequisite validation, HITL (Human-in-the-loop) safety gates, loop prevention, and formatting. Use when auditing workflow scripts…
code-quality-guardian
Use before merging or committing code. Performs six-axis code quality gating — security, complexity, style, test coverage, documentation, and dependency health. Blocks low-quality code from entering the main branch.
gsd-ns-review
Invoke this Pi skill with /skill:gsd-ns-review.