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 chankov/agent-fleet --skill drafting-workflowsgit clone --depth 1 https://github.com/chankov/agent-fleetWrote 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/chankov/agent-fleet/drafting-workflows)<a href="https://agentmods.dev/skills/chankov/agent-fleet/drafting-workflows"><img src="https://agentmods.dev/badge/skills/chankov/agent-fleet/drafting-workflows/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/chankov/agent-fleet/drafting-workflows"><img src="https://agentmods.dev/badge/skills/chankov/agent-fleet/drafting-workflows.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 2 findings, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium MCP Rug Pull · line 99 npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.Fix: Pin the version: npx @scope/[email protected]
- medium MCP Rug Pull · line 141 npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.Fix: Pin the version: npx @scope/[email protected]
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 | $0.00049 | $0.01656 |
| Opus 5.5 | $0.00020 | $0.00662 |
| Sonnet 5.5 | $0.00010 | $0.00331 |
| Haiku 4.5 | $0.00005 | $0.00166 |
Grade A, and why
drafting-workflows 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 1mo 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 — 144 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Drafting Workflows
Overview
Draft code-owned workflows by copying a proven flow shape, then edit only the decisions that actually require judgment. The operator owns intent; code owns phase order, retries, gates, permissions, and acceptance.
When to Use
- Creating a new
scripts/workflows/wf-*.tsflow. - Changing a flow's phase order, gates, retries, or acceptance rule.
- Translating an operator request into a prompt for an agent phase.
Do not use this skill to improvise an interactive hub dispatch. just fleet remains a separate orchestration surface.
Process
1. Map, list, and stop
Read the workflow map in docs/workflows.md, then list every available scripts/workflows/wf-*.ts with exactly one line containing its name and Phases: shape. Stop and wait for the operator to select or describe the desired flow.
At this point:
- Do not open flow traces.
- Do not inventory the repository.
- Do not volunteer a dashboard or a guessed “current state.”
This discipline matters for three independent reasons: volunteered state is guessed state; reconnaissance spends context the real request will need; and a status dump is stale as soon as it is printed.
2. Preserve the request exactly
Translate the request into this four-line prompt:
<the request — one imperative sentence, retaining their exact words wherever they were specific>
Where: <files/directories you actually checked>
Done means: <the observable outcome>
Out of scope: <the tempting addition you will not add>
The intent is theirs. The precision is yours. You may improve grammar, order, and verbosity. You may not silently omit a requirement, weaken a strong request (rewrite must not become lightly refactor), or invent an outcome.
Before running an agent phase, report the exact prompt you will send verbatim. Exact-prompt fidelity is evidence: a bad translation can be corrected before it reaches a commit phase.
3. Describe the phase shape
Write phases in execution order with explicit kinds, for example:
What ships with it
1 file 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.
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.
- 1mo ago First seen · 144 lines · 49 tokens per session scan A 5f02922ee376
drafting-workflows is a skill published in the GitHub repository chankov/agent-fleet (19 stars, last pushed yesterday), licensed MIT. It adds 49 tokens to every session and 1,656 once invoked, about $0.0002 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 2026-09-03.
Other skills, from other repositories
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…