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-documentationnpx skills add cosmix/loom --skill loom-documentationgit 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-documentation)<a href="https://agentmods.dev/skills/cosmix/loom/loom-documentation"><img src="https://agentmods.dev/badge/skills/cosmix/loom/loom-documentation.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 | $0.00032 | $0.01995 |
| Opus 5 | $0.00016 | $0.00997 |
| Sonnet 5 | $0.00006 | $0.00399 |
| Haiku 4.5 | $0.00003 | $0.00199 |
Grade A, and why
loom-documentation 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 — 241 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Documentation
Overview
Create and maintain documentation artifacts and their required structure: docstrings, inline comments, API references, READMEs, ADRs, changelogs, and architecture docs. This skill owns WHAT each artifact must contain. For prose mechanics (voice, clarity, sentence craft) and the Diátaxis mode framework, see loom-technical-writing. For visuals, see loom-diagramming; for API-spec files (OpenAPI), see loom-api-documentation.
Artifact → structure map
Pick the artifact by audience and Diátaxis mode, then fill its required structure. Never mix modes in one document (a reference is not a tutorial).
| Artifact | Diátaxis mode | Must contain |
|---|---|---|
| README | how-to + reference | one-line pitch, install, quick-start, links out |
| Tutorial / getting-started | tutorial | ordered steps, a path guaranteed to work, expected output |
| How-to guide | how-to | goal-titled, prerequisites, numbered steps, verification |
| API reference | reference | every public symbol: params, returns, errors, ≥1 example |
| ADR | explanation | context, decision, consequences, alternatives, status |
| Changelog | reference | changes grouped per version, dates, breaking changes flagged |
| Docstring | reference | purpose, params, returns, raises/panics, example |
| Inline comment | explanation | WHY only — never restate the code |
First step on any task: identify the audience (developer / end-user / operator / contributor), then read the code so docs match real behavior — never document from assumption.
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 · -15 tokens per session cb13e748654d
- 4d ago First seen · 241 lines · 47 tokens per session scan A 04032d6f8d66
loom-documentation is a skill published in the GitHub repository cosmix/loom (54 stars, last pushed today), licensed MIT. It adds 32 tokens to every session and 1,995 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 2026-08-30.
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.