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 cosmix/loom --skill loom-technical-writinggit 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-technical-writing)<a href="https://agentmods.dev/skills/cosmix/loom/loom-technical-writing"><img src="https://agentmods.dev/badge/skills/cosmix/loom/loom-technical-writing/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/cosmix/loom/loom-technical-writing"><img src="https://agentmods.dev/badge/skills/cosmix/loom/loom-technical-writing.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00013 | $0.01492 |
| Opus 5 | $0.00006 | $0.00746 |
| Sonnet 5 | $0.00003 | $0.00298 |
| Haiku 4.5 | $0.00001 | $0.00149 |
Grade A, and why
loom-technical-writing 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 6d 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 — 141 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Technical Writing
Overview
Style, voice, clarity, and structure for software documentation. This skill owns HOW to write well; for the required structure of each artifact (README, ADR, changelog, API reference, docstrings) see loom-documentation. Always read the code before writing — never document from assumption.
Diátaxis: pick one mode per document
The load-bearing framework. Docs fail mostly by mixing modes — a tutorial that digresses into API tables, a reference padded with narrative. Each document serves ONE of four user needs:
| Mode | User is… | Serves | Voice | Anti-pattern if mixed |
|---|---|---|---|---|
| Tutorial | learning | acquisition | "we will…", hand-held, safe | reference detail derails it |
| How-to | working toward goal | application | "to do X, do Y", imperative | teaching concepts slows it |
| Reference | looking something up | information | neutral, exhaustive, dry | opinions/steps bloat it |
| Explanation | trying to understand | understanding | discursive, "why", trade-offs | step lists flatten the "why" |
Rules: title how-tos by the goal ("Deploy to staging", not "Deployment"). Tutorials must succeed on a clean machine end-to-end. Reference mirrors code structure and stays complete. Explanation (ADRs, design docs) argues the "why". When a page wants to do two jobs, split it and cross-link.
Know your audience
- Developers — API details, code examples, technical depth.
- End users — tasks and outcomes; minimal jargon.
- Operators/DevOps — deploy, config, monitoring, troubleshooting.
- New contributors — onboarding, architecture overview, contribution workflow.
Prose style
- Active voice. "The function returns X" not "X is returned".
- Imperative for instructions. "Run the command" not "You should run".
- Present tense for current behavior.
- One idea per sentence. Split any sentence with two clauses joined by "and/but/which"; aim 15-25 words. Delete throat-clearing ("It should be noted that…").
- Front-load. Lead each paragraph, section, and sentence with its most important point; put the conclusion first, support after. Readers scan — reward the scan.
- Specific, not hedged. "Returns an empty list" not "returns the result"; "does X" not "might do X". Every "usually/typically/generally" hides an unstated condition — state it.
- Minimalism. Cut words that don't change meaning: "in order to"→"to", "is able to"→"can", "at this point in time"→"now". If a sentence survives deletion, delete it.
- Parallel structure in lists; consistent terminology (one term per concept — never alternate "user/account/profile" for the same thing).
- Define terms on first use; expand acronyms once.
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.
- 6d ago First seen · 141 lines · 13 tokens per session scan A e9ce2173efb9
loom-technical-writing is a skill published in the GitHub repository cosmix/loom (54 stars, last pushed today), licensed MIT. It adds 13 tokens to every session and 1,492 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 2026-09-03.
Other skills, from other repositories
API Discoverability for Agents
Making self-hosted services agent-discoverable — bake in a machine-readable API description (OpenAPI spec or a minimal API.md) when building, and discover-first (spec paths, repo search) before probing when integrating.
Agent Design Principles
A checklist for designing agent personas, skills, and multi-agent pipelines that stay reliable as they grow — grounded in the 12-factor-agents principles.
workers-best-practices
Cloudflare Workers best practices for production applications. Use when writing, reviewing, or configuring Workers.
find-journalists
Build, refine, dedupe, and enrich small fit-checked journalist lists for newsjack campaigns. Uses the newsjack CLI (preferred) or the medialyst MCP for news search and journalist enrichment, and falls back to a best-effort local mode with no verified contacts; the agent owns how returned data is organized.
story-origin-check
Recover the first public timestamp and canonical major coverage for a newsjacking signal, then decide whether newer coverage is the same story, a different story, or a materially new development.
relevance-coarse-filter
Cheap, high-recall first-pass filter that removes obvious junk from a detector candidate pool before expensive story-origin research and PR judgment. Decides keep, monitoronly, or reject — never ranks, writes angles, verifies dates, or decides whether to pitch.