Borrowing it
Nothing to install: this file belongs to himkt/cafleet. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/himkt/cafleet/main/.claude/skills/clean-docs/SKILL.mdgit clone --depth 1 https://github.com/himkt/cafleetWrote 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/himkt/cafleet/clean-docs)<a href="https://agentmods.dev/skills/himkt/cafleet/clean-docs"><img src="https://agentmods.dev/badge/skills/himkt/cafleet/clean-docs/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/himkt/cafleet/clean-docs"><img src="https://agentmods.dev/badge/skills/himkt/cafleet/clean-docs.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 | $0.00199 | $0.04089 |
| Opus 5.5 | $0.00080 | $0.01636 |
| Sonnet 5.5 | $0.00040 | $0.00818 |
| Haiku 4.5 | $0.00020 | $0.00409 |
Grade A, and why
clean-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 3d 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 — 272 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Clean-Docs Skill (CAFleet-orchestrated)
One skill, three workflows — residue, affirmative, simplification —
run as the same CAFleet team shape over the same per-run process. This page is
the dispatcher and the single home of the shared orchestration spine; each
workflow body (<workflow>/<workflow>.md) carries only its own trigger
scenario, scan mechanics, artifact spec, and guarantees, citing the spine here
rather than restating it.
Resolve runtime tools from the executing agent's backend. For spawns, read the selected member backend's Model catalog and Role defaults under the CAFleet Director's model-selection policy; validate its effort and launch capabilities there.
Required reading
Identify the executing backend (members use CODING AGENT), resolve its runtime bindings, and load cafleet for BASE, member startup or Director orchestration. Read coordination for verbs, pointers and marker pairing, then this shared spine once. A workflow's Required reading adds only its phase-specific prerequisites. Resolve model tokens from the selected spawn backend's Role defaults and runtime tokens from the executing backend; use documented defaults only in their allowed cases.
Dispatch
Route the user's request into exactly one workflow body by phrasing, then
run that body's orchestration in full over the spine below. One workflow per
run — never a combined pass. When a request names families from more than one
workflow, the Director asks the user which single workflow to run via
{decision_surface}.
| When the user wants to… | Run |
|---|---|
| Clean up historical narration / historical residue; remove deprecation notes, "this replaces X" / "renamed from Y" / "previously … now …" prose; drop design-number provenance citations; remove historical sentinel framing while preserving current absence tests | the residue workflow (residue/residue.md) |
| Run an affirmative-writing sweep; fix prohibition-only rule sections; pair prohibitions with affirmatives; remove meaningless fallbacks; make code fail fast | the affirmative workflow (affirmative/affirmative.md) |
| Simplify the docs / comments; tighten verbose prose; de-duplicate documentation; remove redundant comments | the simplification workflow (simplification/simplification.md) |
What ships with it
11 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- affirmative/affirmative.md 5.2 KB
- affirmative/roles/reviewer.md 4.5 KB
- affirmative/roles/scanner.md 4.8 KB
- reference/review-format.md 3.8 KB
- residue/reference/patterns.md 3.9 KB
- residue/residue.md 7.6 KB
- residue/roles/reviewer.md 4.8 KB
- residue/roles/scanner.md 5.2 KB
- simplification/roles/reviewer.md 4.3 KB
- simplification/roles/scanner.md 4.9 KB
- simplification/simplification.md 3.6 KB
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.
- 3d ago Changed · -1 lines 410636794dfd
- 4d ago Changed · -5 lines 721ea517b487
- 18d ago Changed 68aadda71e9c
- 27d ago Changed 1595f25409ba
- 1mo ago Changed · -12 lines · +4 tokens per session bf4660a7d771
- 1mo ago First seen · 290 lines · 195 tokens per session scan A 650ab7c0e4ea
clean-docs is a skill published in the GitHub repository himkt/cafleet (53 stars, last pushed today), licensed MIT. It adds 199 tokens to every session and 4,089 once invoked, about $0.0008 per session on Opus 5.5. 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
anycap-human-interaction
Collect structured visual feedback from humans using AnyCap's annotation tool, or create and iterate on diagrams using the interactive whiteboard (Excalidraw). Covers image annotation, URL/web page review with screen recording, video review, audio feedback, and collaborative diagramming with Mermaid input. Use when…
anycap-media-production
Produce media assets using AnyCap: generate images, videos, music, speech, dialogue, and complete audio scenes from text or reference inputs, refine images through interactive visual annotation, and deliver finished assets. Covers the full production workflow from concept to delivery across all media types (image…
anycap-blog-production
Turn user-provided data, notes, research, product facts, or structured inputs into AnyCap-style blog posts and then enrich those posts with first-party evidence blocks when needed. Use when a user wants a blog, article, tutorial, learn page, or SEO content draft written in the tone of the AnyCap website. Best fit when…
anycap-worldcup-predict
World Cup match prediction and pre-match intel for football (soccer) fans: predict who will win and a likely scoreline, backed by structured, verifiable evidence -- player profiles, squad dossiers, current form, head-to-head records, and past-tournament history -- using AnyCap web search and crawl. Weighs FIFA…
anycap-deepresearch
Guide for conducting thorough, multi-source research and producing comprehensive, well-sourced reports. Powered by AnyCap -- the capability runtime that equips AI agents with web search (including AI Grounded citations), web crawl, image generation, cloud storage, and one-click web publishing through a single CLI. Use…
anycap-gemini-omni-video-edit
Use Gemini Omni Flash Preview through AnyCap for practical short-video editing workflows. Trigger when a user wants to edit or refine an existing video with natural-language instructions, especially product replacement, object removal or replacement, relighting, restyling, preserving a person/scene while changing one…