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 himkt/cafleet --skill cafleet-design-docgit 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/cafleet-design-doc)<a href="https://agentmods.dev/skills/himkt/cafleet/cafleet-design-doc"><img src="https://agentmods.dev/badge/skills/himkt/cafleet/cafleet-design-doc/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/cafleet-design-doc"><img src="https://agentmods.dev/badge/skills/himkt/cafleet/cafleet-design-doc.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 | $0.00132 | $0.00895 |
| Opus 5 | $0.00066 | $0.00447 |
| Sonnet 5 | $0.00026 | $0.00179 |
| Haiku 4.5 | $0.00013 | $0.00089 |
Grade A, and why
cafleet-design-doc 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 10d 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 — 54 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Design Document Skill (CAFleet Edition)
This skill is the umbrella for the full design-document lifecycle: the standardized format spec plus three CAFleet-native orchestration workflows (create, validate/interview, implement/execute). It is a dispatcher — consult a reference page for the format, or route to the matching workflow body to run a team.
Teammates in member teams must always load this skill by its name cafleet-design-doc via their backend's skill-loader — never by reading the skill files directly.
Required reading
Before routing into a workflow or consulting a reference page, Read your overlay — it is row #1 below. Identify your coding agent first: your spawn prompt's CODING AGENT: line names it; a standalone / main-session reader uses its own identity.
Load-bearing — Read before acting:
| # | Read | What you lose if you skip it |
|---|---|---|
| 1 | your overlay section ../cafleet/reference/coding-agent-overlays.md#<name> — read and resolve it (see Resolve your overlay in the cafleet SKILL.md) |
you skip resolution — the failure modes Resolve your overlay closes, e.g. a literal {bg_run} emitted unresolved |
On-demand — consult directly (no team), only when the task needs it:
| Read | When |
|---|---|
| reference/guidelines.md | you are writing or checking a doc against the standard structure (the template opens the page), or need section guidelines, quality standards, or formatting rules |
| reference/coordination.md | you need the inter-member verb + pointer + COMMENT(role) schema |
Each workflow body (create / interview / execute) carries its own Required-reading block for the team it runs — base-dir, supervision, and coordination are gated there, not on this dispatch surface.
Dispatch
When the user's request matches a scenario below, invoke this skill and run the linked workflow as a full CAFleet team — proactively, the moment the request matches, without waiting for the user to say "use cafleet".
What ships with it
14 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.
- create/create.md 20 KB
- create/roles/director.md 8.5 KB
- create/roles/drafter.md 8.1 KB
- create/roles/reviewer.md 5.1 KB
- execute/execute.md 39 KB
- execute/roles/director.md 12 KB
- execute/roles/programmer.md 8.7 KB
- execute/roles/reviewer.md 6.5 KB
- execute/roles/tester.md 8.1 KB
- execute/roles/verifier.md 6.9 KB
- interview/interview.md 17 KB
- interview/roles/analyzer.md 5.9 KB
- reference/coordination.md 11 KB
- reference/guidelines.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.
- 10d ago First seen · 54 lines · 132 tokens per session scan A 038fbfb8dec6
cafleet-design-doc is a skill published in the GitHub repository himkt/cafleet (50 stars, last pushed today), licensed MIT. It adds 132 tokens to every session and 895 once invoked, about $0.0007 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 2026-08-30.
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-ai-tool-seo
Guide for planning and auditing SEO for AI tool, SaaS, and product-led websites. Powered by AnyCap -- the capability runtime that equips AI agents with web search and web crawl through a single CLI. Use when Codex needs to define SEO ICPs, map search intent to page types, inspect live SERPs, write page briefs for…
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…