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 aneja5/forge-skills --skill documentation-hygienegit clone --depth 1 https://github.com/aneja5/forge-skillsWrote 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/aneja5/forge-skills/documentation-hygiene)<a href="https://agentmods.dev/skills/aneja5/forge-skills/documentation-hygiene"><img src="https://agentmods.dev/badge/skills/aneja5/forge-skills/documentation-hygiene.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 | $0.00048 | $0.01616 |
| Opus 5 | $0.00024 | $0.00808 |
| Sonnet 5 | $0.00010 | $0.00323 |
| Haiku 4.5 | $0.00005 | $0.00162 |
Grade A, and why
documentation-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 5d 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 — 146 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Documentation Hygiene
Overview
Define the project's documentation contract — what gets documented, where it lives, how it stays current — before docs rot. Output is .forge/docs-policy.md: README standard per repo and subdirectory, in-code comment policy (WHY not WHAT), doc-rot prevention rules (dates, code links, generated docs), public-vs-internal doc split, and changelog discipline. Pairs with code-review-and-quality (review enforces the policy) and shipping-and-launch (CHANGELOG updated per release).
When to Use
- A repo is older than 3 months and the README hasn't been touched since the first commit
- Subdirectories have grown to 5+ files with no entry-point doc
- In-code comments are mostly restating the code instead of explaining intent
- A new contributor takes >2 hours to figure out where things live
- A release shipped without a CHANGELOG entry
- A doc references a system that no longer exists
When NOT to Use
- Greenfield project, day one — README will exist; full policy can wait until week 2
- Throwaway prototype
- A single typo fix in one doc
Common Rationalizations
| Thought | Reality |
|---|---|
| "The code is self-documenting" | Code shows what, not why. Two months later the original author cannot reconstruct why. |
| "Docs get stale anyway, why bother" | Dated docs with code links rot slower than undated docs. The half-life of a comment near its code is years; far from its code, weeks. |
| "README is enough" | README without subdirectory docs creates a treasure hunt for every new contributor. |
| "We'll document before launch" | You won't. And if you do, the doc will be wrong because you'll write it from memory. |
| "Comments are noise" | Comments that explain WHY are signal. Comments that restate the code are noise. The fix is to write the right comments, not to delete all comments. |
| "Generated docs are good enough" | Generated docs answer "what does this function take" — not "when should I call it" or "what changes if I don't." |
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.
- 5d ago First seen · 146 lines · 48 tokens per session scan A 78ce66c38f43
documentation-hygiene is a skill published in the GitHub repository aneja5/forge-skills (3 stars, last pushed 3mo ago), licensed MIT. It adds 48 tokens to every session and 1,616 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 2026-09-03.
Other skills, from other repositories
link-ticket-to-session
Link the current Claude Code session to a ticket (Linear, Jira, GitHub Issues, or GitHub Pull Requests) and cache its title/status in karma. Use when the user explicitly asks to link, attach, associate, or connect this session to a ticket, issue, or PR — e.g. "/link-ticket-to-session ABC-123", "link this session to…
lead
Use when acting as the factory tech lead: classify work, ask the minimum questions, create tickets, and dispatch without implementing.
to-tickets
Use when breaking a plan into tracer-bullet GitHub issues with blocking edges.
swarm-swarm
Self-claiming pool orchestration. Workers race to claim tasks from a shared pool, loop until the pool is empty.
build-flow
Autonomously build a complete Power Automate flow from a description. Use when you need to generate a full flow definition and create it.
add-azuredevops
Adds Azure DevOps connector to a Power Apps code app. Use when querying work items, creating bugs, managing pipelines, or making ADO API calls.