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/KevinZai/commanderWrote 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/kevinzai/commander/review-skills)<a href="https://agentmods.dev/commands/kevinzai/commander/review-skills"><img src="https://agentmods.dev/badge/commands/kevinzai/commander/review-skills.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 5.1 | $0.00038 | $0.04200 |
| Opus 5 | $0.00019 | $0.02100 |
| Sonnet 5 | $0.00008 | $0.00840 |
| Haiku 4.5 | $0.00004 | $0.00420 |
Grade A, and why
review-skills 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 3d 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 — 326 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Skill Coherence Review
You review changed skills with automated bash checks (Phase 2), 9 structural dimensions (D1-D9), and 5 intent checks (M1-M5). Fix issues in-place. Report with PASS/FAIL verdict.
Phase 1: Scope Detection
If $ARGUMENTS provided: treat each token as a skill directory prefix (e.g., ln-400 matches ln-400-story-executor/). Glob {prefix}*/SKILL.md per token.
If $ARGUMENTS empty: auto-detect from git:
git diff --name-only HEAD
git diff --name-only --cached
git ls-files --others --exclude-standard
Extract unique skill dirs (pattern ln-\d+-[^/]+) and shared paths (shared/). If shared files changed, Grep all ln-*/SKILL.md for references to changed filenames.
Build scope:
- Primary — skills with directly changed files
- Affected — skills referencing changed shared files
- Dependencies — for each primary skill, extract
ln-\d{3,4}references from its SKILL.md (callers, callees, worker tables)
Deduplicate. Report: Scope: N primary, M affected, K dependency skills.
Phase 2: Automated Verification
Run these bash commands for every SKILL.md in scope. Record failures — they feed D7/D8 as pre-verified violations. Every FAIL is a confirmed violation — no judgment needed, no skipping allowed.
Frontmatter check (D7):
for f in {scoped SKILL.md files}; do
head -5 "$f" | grep -q "^---" || echo "FAIL: no frontmatter: $f"
grep -q "^name:" "$f" || echo "FAIL: no name: $f"
grep -q "^description:" "$f" || echo "FAIL: no description: $f"
done
Version/date check (D7):
for f in {scoped SKILL.md files}; do
grep -q "\*\*Version:\*\*" "$f" || echo "FAIL: no version: $f"
grep -q "\*\*Last Updated:\*\*" "$f" || echo "FAIL: no date: $f"
grep -q "\*\*Changes:\*\*" "$f" && echo "FAIL: has Changes section: $f"
done
Size check (D8):
for f in {scoped SKILL.md files}; do
lines=$(wc -l < "$f")
[ "$lines" -gt 800 ] && echo "FAIL: $lines lines (>800): $f"
done
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.
- 3d ago First seen · 326 lines · 38 tokens per session scan A bc47002fd253
review-skills is a command published in the GitHub repository KevinZai/commander (6 stars, last pushed today), licensed MIT. It adds 38 tokens to every session and 4,200 once invoked, about $0.0002 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 2026-09-04.
Other commands, from other repositories
loop
Autonomous execution loop. Runs the TDD cycle repeatedly until all tasks in an epic are complete, with circuit breaker protection and PR workflow.
execute
Execute the next available tracked task with TDD, pre-commit validation, PR creation, AI code review, and issue tracker bridge sync.
codex-loop
Use Codex as a second, differently-trained reviewer of your branch, fix every real finding with regression tests, and loop until two consecutive reviews come back clean. Runs autonomously.
verify
A verification command that runs a test agent and a code-review agent in the same round, then combines their results.
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.