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 skills/cosmix/loom/loom-code-reviewnpx skills add cosmix/loom --skill loom-code-reviewgit clone --depth 1 https://github.com/cosmix/loomWrote 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/cosmix/loom/loom-code-review)<a href="https://agentmods.dev/skills/cosmix/loom/loom-code-review"><img src="https://agentmods.dev/badge/skills/cosmix/loom/loom-code-review.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 | $0.00022 | $0.02033 |
| Opus 5 | $0.00011 | $0.01017 |
| Sonnet 5 | $0.00004 | $0.00407 |
| Haiku 4.5 | $0.00002 | $0.00203 |
Grade A, and why
loom-code-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 today.
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 — 161 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Code Review
Overview
Review a change for correctness, security, performance, and maintainability, then produce prioritized, actionable feedback. Optimize signal: gate on what breaks users; comment (don't gate) on the rest.
Review vs. adversarial security audit
Different jobs — don't conflate:
- Code review (this skill): holistic, author-empathetic. Reviews the diff and its blast radius against stated intent across four lenses. Assumes good faith; catches the bugs a careful peer catches.
- Security audit (
Skill(skill="loom-skills", args="loom-security-audit"),Skill(skill="loom-skills", args="loom-threat-model")): attacker mindset, threat model, whole-attack-surface. Assumes hostile input everywhere.
For auth, crypto, payments, deserialization, or anything touching a trust boundary: do the code review AND trigger a security audit. A passing code review is not a security sign-off.
Severity taxonomy
Label every comment. BLOCKER, SILENT_FAILURE, and CRITICAL gate the merge.
| Severity | Gate? | Meaning |
|---|---|---|
| BLOCKER | ✅ | Security hole, data loss, crash, corruption. Merge is unsafe. |
| SILENT_FAILURE | ✅ | Exit 0 but the operation actually failed (sandbox-blocked download, partial fetch, stale cache, swallowed error). Always investigate before merge. |
| CRITICAL | ✅ | Logic error / real bug that will bite in normal use. |
| MAJOR | ❌ | Maintainability, tech debt, missing test for a real path. Fix soon. |
| MINOR / nit | ❌ | Style, naming, micro-optimization. Prefix with nit: so the author can skip it. |
Approve-with-comments discipline: if nothing is BLOCKER/SILENT_FAILURE/CRITICAL, approve and leave the MAJOR/MINOR notes as non-blocking. Don't hold a PR hostage over nits or personal style. Blocking on taste is the top reviewer anti-pattern — it trains authors to ignore you.
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.
- today Changed · -20 tokens per session e88493bd6892
- 4d ago First seen · 161 lines · 42 tokens per session scan A 580d4857b1fc
loom-code-review is a skill published in the GitHub repository cosmix/loom (54 stars, last pushed today), licensed MIT. It adds 22 tokens to every session and 2,033 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 skills, from other repositories
hardcoded-secret
A bundle that leaks a real credential. This must never publish.
code-review
Perform thorough code reviews focusing on correctness, security, and maintainability.
checkpointed-workflow
Use when the user asks to assemble and validate a checkpointed report bundle.
deterministic-transform
Use when the user asks to transform a JSON data file deterministically.
document-formatter
Use when the user asks to format a document against the house style guide.
dangerous-skill
Example skill that demonstrates security scanner detection.