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/getkyo/kyo/readme-draftnpx skills add getkyo/kyo --skill readme-draftgit clone --depth 1 https://github.com/getkyo/kyoWrote 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/getkyo/kyo/readme-draft)<a href="https://agentmods.dev/skills/getkyo/kyo/readme-draft"><img src="https://agentmods.dev/badge/skills/getkyo/kyo/readme-draft.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 | $0.00048 | $0.04451 |
| Opus 5 | $0.00024 | $0.02226 |
| Sonnet 5 | $0.00010 | $0.00890 |
| Haiku 4.5 | $0.00005 | $0.00445 |
Grade A, and why
readme-draft 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 4d 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 — 242 lines — stays where its author put it; the contents beside it link to each section on GitHub.
readme-draft
Input: the structured output of readme-analyze-source (five sections: spine candidate, callout candidates, API surface inventory, section clusters, running-domain seeds). Output: a draft README.
This skill writes from a curriculum: every API listed in the inventory must be introduced, in order, with one or more worked examples. The spine candidate becomes the opening paragraphs. Callout candidates become inline Note:, Caution:, or Unlike X paragraphs at the points where the surface they describe is introduced. The section clusters become the ## section list — one section per cluster, NOT one per API. The running-domain seeds determine the case classes used in worked examples — pick one early and reuse throughout.
This skill does NOT:
- Read or compare against an existing README at the output path. If a README exists there, the user wants a full rewrite; you write fresh.
- Add content beyond what the inventory and callouts specify.
- Invent capabilities or surfaces.
- Add hedging, defensive disclaimers, audience disclaimers, or competitor-suggestion paragraphs.
- Produce one
##section per inventory API (catalog shape). Sections come from the cluster list, not the inventory list.
What you produce
A single Markdown file at <output-readme-path>, structured as follows:
- Title (
# kyo-<name>) — exactly the module name, no marketing. - Spine paragraphs — verbatim from the spine candidate, or lightly edited for prose flow. NEVER trade specificity for fluency.
- Composition opening: ONE code block exercising 3-5 capabilities on the chosen running-domain value, with
// commentheaders. See "Structural discipline" below. ##sections IN CLUSTER ORDER (one per cluster from the source-analysis output), each with its APIs as###sub-sections. APIs from the same cluster MUST appear together under their cluster heading.- Optional sections that the inventory specifically supports (cross-platform behavior, integration points, configuration, exceptions).
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.
- 4d ago First seen · 242 lines · 48 tokens per session scan A 7b66a13bf329
readme-draft is a skill published in the GitHub repository getkyo/kyo (811 stars, last pushed today), licensed Apache-2.0. It adds 48 tokens to every session and 4,451 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 2026-08-30.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
brainstorming
You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.
auto-perf-optimize
Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.
chat-perf
Run chat perf benchmarks and memory leak checks against the local dev build or any published VS Code version. Use when investigating chat rendering regressions, validating perf-sensitive changes to chat UI, or checking for memory leaks in the chat response pipeline.
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…