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 | $0.00115 | $0.00996 |
| Opus 5.5 | $0.00046 | $0.00398 |
| Sonnet 5.5 | $0.00023 | $0.00199 |
| Haiku 4.5 | $0.00012 | $0.00100 |
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 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 — 56 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 design-document lifecycle: the standardized format spec plus the CAFleet-native orchestration workflows in Dispatch. Consult a reference page for the format, or route a main-session user request through Dispatch to run a team. Assigned teammates continue their existing workflow (Member startup); loading this umbrella as a member creates no second team.
Required reading
Identify your coding agent — your spawn prompt's CODING AGENT: line, or your own identity as a standalone / main-session reader. Then, before routing into a workflow or consulting a reference page, read and resolve your overlay section ../cafleet/reference/coding-agents.md#<name> (see Resolve your overlay in the cafleet SKILL.md), so no runtime token such as {decision_surface} is emitted unresolved.
Consult these directly (no team) only when the task needs them:
| Read | When |
|---|---|
| reference/guidelines.md | Writing or checking a doc against the standard structure (the template opens the page), or needing section guidelines, quality standards or formatting rules |
| reference/coordination.md | Needing the inter-member verb + pointer + COMMENT(role) schema |
Each workflow body in Dispatch gates BASE resolution, supervision and coordination in its own Required-reading block.
Dispatch
For a main-session user request matching 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".
Routing into a workflow means executing its entire orchestration. The Director registers its current session with cafleet fleet create, spawns the role team, receives each ready and drives the workflow’s review/revision rounds through approval, keeping reception under Director wake until fleet deletion; the linked workflow body owns its phase gates.
What ships with it
10 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 6.0 KB
- create/roles/drafter.md 6.5 KB
- create/roles/reviewer.md 3.1 KB
- execute/execute.md 8.8 KB
- execute/roles/programmer.md 6.6 KB
- execute/roles/reviewer.md 4.4 KB
- execute/roles/tester.md 5.8 KB
- execute/roles/verifier.md 4.9 KB
- reference/coordination.md 9.7 KB
- reference/guidelines.md 6.1 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.
- yesterday Changed · -8 lines ed55ef3fc940
- 3d ago Changed 5213c1b166fa
- 5d ago Changed · +3 tokens per session 4bf784d2aee4
- 6d ago Changed cda6546c1cb9
- 7d ago Changed · -2 lines · -21 tokens per session 54b4fe30b7bf
- 9d ago Changed · +12 lines 33fad3bfbd3d
- 14d ago Changed 86541900c15b
- 15d ago Changed 4283bdf0a146
- 29d ago Changed 8c4e6f58ad4d
- 1mo ago First seen · 54 lines · 133 tokens per session scan A 081037a7e2f2
cafleet-design-doc is a skill published in the GitHub repository himkt/cafleet (56 stars, last pushed yesterday), licensed MIT. It adds 115 tokens to every session and 996 once invoked, about $0.0005 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.
cafleet-design-doc compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| cafleet-design-dochimkt/cafleet | Skill | 56 | yesterday | MIT | A | 115 | Claude Code |
| anycap-human-interactionanycap-ai/anycap | Skill | 51 | 19d ago | MIT | A | 190 | Claude Code |
| anycap-media-productionanycap-ai/anycap | Skill | 51 | 19d ago | MIT | A | 167 | Claude Code |
| anycap-blog-productionanycap-ai/anycap | Skill | 51 | 19d ago | MIT | A | 143 | Claude Code, Codex |
| anycap-worldcup-predictanycap-ai/anycap | Skill | 51 | 19d ago | MIT | A | 275 | Claude Code, Codex |
| anycap-deepresearchanycap-ai/anycap | Skill | 51 | 19d ago | MIT | A | 178 | Claude Code |
| anycap-social-meme-workflowsanycap-ai/anycap | Skill | 51 | 19d ago | MIT | A | 94 | Claude Code, Codex |