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/fmind/dot/improve-docsnpx skills add fmind/dot --skill improve-docsgit clone --depth 1 https://github.com/fmind/dotWrote 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/fmind/dot/improve-docs)<a href="https://agentmods.dev/skills/fmind/dot/improve-docs"><img src="https://agentmods.dev/badge/skills/fmind/dot/improve-docs.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 | $0.00044 | $0.00630 |
| Opus 5 | $0.00022 | $0.00315 |
| Sonnet 5 | $0.00009 | $0.00126 |
| Haiku 4.5 | $0.00004 | $0.00063 |
Grade A, and why
improve-docs 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 yesterday.
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 — 35 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Improve Documentation
Documentation is read far more than it is written; every stale page costs every reader. This pass keeps what answers a real question and removes the rest. README.md and AGENTS.md alone are covered by readme-agents; this skill handles the wider set.
Workflow
- Inventory: list every doc source (
README.md,AGENTS.md,docs/, wiki,CHANGELOG.md, inline--help) and its audience: users, contributors, or agents. - Find drift: compare each page against the code it describes: commands (
mise tasks,--helpoutput), paths, versions, screenshots. A claim the repo cannot back is removed or fixed, never left. - Cut noise: delete duplicated sections, marketing filler, and step-by-step narratives that the code already shows; merge pages that answer the same question.
- Move workflows out of prose: repeated agent instructions in
AGENTS.mdbecome skills per skillify;AGENTS.mdkeeps rules and layout only. - Verify:
lychee <files>for links,dprint checkfor formatting, and the site build (mise run build) for a hugo site. Read the rendered page, not only the Markdown. - Report: pages removed, merged, or rewritten, with the reason, plus links or facts that could not be verified.
Gotchas
- Do not rewrite voice: keep the author's tone; change facts and structure, not style.
- Changelogs are generated:
CHANGELOG.mdcomes from git-cliff per the release skill; fix commits, not the file. - External links drift: prefer primary documentation URLs and record the date for facts that age.
Documentation
- lychee · dprint
- Companion skills: readme-agents (the two root files), skillify (extract workflows), hugo (docs sites), reduce-complexity (the same pass for code).
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.
- yesterday First seen · 35 lines · 44 tokens per session scan A d7fc3c30f24c
improve-docs is a skill published in the GitHub repository fmind/dot (4 stars, last pushed today), licensed MIT. It adds 44 tokens to every session and 630 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
go-stack
Build Go projects, libraries, CLIs, TUIs, web apps, or ADK agents with the standard package layout and pinned tooling.
python-stack
Build typed Python projects with uv, Ruff, ty, pytest, Litestar, and Typer. Use for packages, CLIs, web apps, tests, typing, or API verification.
chezmoi
Manage chezmoi dotfiles: source naming, Go templates, age-encrypted secrets, and the edit-source then apply/diff workflow.
hugo
Canonical Hugo static-site stack with the Hextra docs theme — Hugo Modules, mise tasks, dprint, lefthook, and GitHub Pages deploy. Use for documentation sites, project docs, and static websites.
k8s-local
Create and manage local Kubernetes clusters (k3d or kind) and deploy to them with kubectl, helm, helmfile, and skaffold. Use for local k8s cluster setup, dev loops, and debugging.
release
Cut or verify a versioned release — bump semver, generate the changelog with git-cliff, tag and publish on GitHub, or reconcile an already-published tag and assets.