loom-doc-hygiene

loom-doc-hygiene is a skill for Claude Code, Codex from DanielC000/loom. It costs 64 tokens per session (809 once invoked), scanned A, original, MIT.

A documentation-editing guide for living project documents such as READMEs, notes, architecture documents, and changelogs. It says to keep current information in place, remove contradictions, and avoid uncontrolled growth.

In plain words
What is it for?
Revising documentation, resolving conflicting statements, removing stale updates and loose ends, fixing dangling references, and keeping documents concise.
Why use it?
It prevents documents from becoming confusing collections of outdated text and correction notes. Readers can rely on the document itself as the current source of truth.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: mentions CLAUDE.md.

Good fit Revising documentation, resolving conflicting statements, removing stale updates and loose ends, fixing dangling references, and keeping documents concise.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/danielc000/loom/loom-doc-hygiene
Install

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.

Any agent
npx skills add DanielC000/loom --skill loom-doc-hygiene
Clone the repo
git clone --depth 1 https://github.com/DanielC000/loom

Made for: Claude Code, Codex.

Wrote 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.

agentmods badge for loom-doc-hygiene

README.md
[![agentmods](https://agentmods.dev/badge/skills/danielc000/loom/loom-doc-hygiene.svg)](https://agentmods.dev/skills/danielc000/loom/loom-doc-hygiene)
Your own site
<a href="https://agentmods.dev/skills/danielc000/loom/loom-doc-hygiene"><img src="https://agentmods.dev/badge/skills/danielc000/loom/loom-doc-hygiene.svg" alt="Measured on agentmods" height="20"></a>
Per session 64 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 809 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00064 $0.00809
Opus 5 $0.00032 $0.00404
Sonnet 5 $0.00013 $0.00162
Haiku 4.5 $0.00006 $0.00081

Measured 8d ago against content hash ba3a0f0effab, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

loom-doc-hygiene 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 8d 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.

packages/daemon/assets/skills/loom-doc-hygiene/SKILL.md · 30 lines

How it starts

The opening of the file, as written. The whole thing — 30 lines — stays where its author put it; the contents beside it link to each section on GitHub.

doc-hygiene

Rules to apply on every documentation edit. Docs are a living source of truth, not an append-only log. A reader should be able to trust that what a doc says now is what is true now.

Rules

  1. No contradictions. A document must not assert two things that cannot both be true. Before adding a statement, scan the surrounding doc for anything it conflicts with and reconcile them in the same edit.

  2. Rewrite in place — never append "UPDATE:" notes. When information becomes outdated, debunked, or false, edit the original sentence/section to be correct. Do not leave the stale text and bolt on "UPDATE:", "EDIT:", "Note (2026):", "struck-through now actually…", or a trailing correction. Replace the wrong content with the right content as if it had always been right. (Git history preserves what changed — the doc itself should read clean.)

  3. Tidy loose ends. Resolve dangling references, half-finished sentences, TODOs that are now done, and links to things that moved or were deleted. If a section is now empty or redundant, remove it.

  4. Keep docs bounded. Don't let a doc grow without limit. Prefer revising existing sections to adding new ones. Consolidate duplicated explanations into one canonical place and link to it. Length should track the size of the subject, not the number of times it was touched.

  5. Shallow, stable structure for a notes collection. In a multi-note vault/docs tree, keep a one-level folder taxonomy — don't pile notes flat, and don't nest deeply. Fixed-path / canonical docs (ones referenced by exact path — a resume log, a note a CLAUDE.md pins by path) stay at the collection root; every other note lives in a taxonomy folder. Maintain an _Index.md map-of-content at the root: read it to locate a note instead of Globbing, and update it when you add or move one.

  6. One line per paragraph — never hard-wrap prose. Write each paragraph, list item, or table row as a single physical line and let the editor soft-wrap it. Do not insert manual line-breaks to hold prose to a column width (~80/100 chars). Hard-wrapping fights the one-line-per-block model editors like Obsidian assume, produces noisy reflow diffs when a sentence is later edited, and re-wraps unpredictably across viewers. Deliberate markdown breaks are still fine — a blank line between blocks, or a trailing \ / two trailing spaces for an intentional hard break — but column-width wrapping is not.

Read the full file on GitHub · 30 lines

Changes

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.

  1. 8d ago First seen · 30 lines · 64 tokens per session scan A ba3a0f0effab

Subscribe to this mod's changes

loom-doc-hygiene is a skill published in the GitHub repository DanielC000/loom (7 stars, last pushed yesterday), licensed MIT. It adds 64 tokens to every session and 809 once invoked, about $0.0003 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 2026-08-31.