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 onatm/agent-skills --skill docs-feature-designgit clone --depth 1 https://github.com/onatm/agent-skillsWrote 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/onatm/agent-skills/docs-feature-design)<a href="https://agentmods.dev/skills/onatm/agent-skills/docs-feature-design"><img src="https://agentmods.dev/badge/skills/onatm/agent-skills/docs-feature-design/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/onatm/agent-skills/docs-feature-design"><img src="https://agentmods.dev/badge/skills/onatm/agent-skills/docs-feature-design.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00037 | $0.00604 |
| Opus 5.5 | $0.00015 | $0.00242 |
| Sonnet 5.5 | $0.00007 | $0.00121 |
| Haiku 4.5 | $0.00004 | $0.00060 |
Grade A, and why
docs-feature-design 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 2mo 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 — 66 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Docs Feature Design
Maintain docs that explain what a feature does and why it matters, not how it is implemented. A single component or service may support multiple features, so keep technical design out of feature docs and link it separately when needed.
Resource Map
- Use
assets/doc-starters/feature-doc.mdwhen creating or substantially rewriting a doc indocs/features/. - Read
references/feature-example.mdwhen you need a worked example of the expected behavior-focused depth.
When to Use
- New feature definition or major feature revision
- Changes to user-visible behavior, primary flows, goals, rules, or constraints
- Updates to product scope, supported actors, or expected outcomes
- Feature docs that should stay understandable without reading implementation details
Do Not Use
- API, schema, runtime, deployment, or internal control-flow detail that belongs in
docs-components-design - System topology or domain architecture that belongs in
docs-architecture
Workflow
- Identify the feature, audience, and existing doc path.
- Default location is
docs/features/ - Reuse an existing feature doc when one already exists
- Capture behavior-level content only.
- User problem and goals
- Primary actors and entry points
- Main flows, states, and business rules
- User-visible edge cases, constraints, and outcomes
- Non-Goals, Audience / Actors, and Open Questions are optional — omit them when they don't add value for the feature
- "User-Facing Behavior" (flat bullet list) is a valid simpler alternative to formal numbered Primary Flows for straightforward features
- Move technical detail out.
- If the draft starts describing APIs, schema, queues, retries, deployment, or internal implementation, link or create the relevant component design doc instead
- Keep cross-links aligned.
- Link to relevant architecture and component docs
- Do not duplicate their content inside the feature doc
- Verify the doc against the current product behavior.
- The described flows and rules match what the feature actually does
- The audience can understand the feature without technical context
What ships with it
3 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.
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.
- 2mo ago First seen · 66 lines · 37 tokens per session scan A 7eb8b30df53d
docs-feature-design is a skill published in the GitHub repository onatm/agent-skills (7 stars, last pushed 3mo ago), licensed MIT. It adds 37 tokens to every session and 604 once invoked, about $0.0001 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 2026-08-31.
Other skills, from other repositories
cf-cli
Cloudflare's official cf CLI (beta) for the public Cloudflare API and Workers projects. Use for finding and running Cloudflare commands from the terminal — sign-in and profiles, cf cli search, cf schema, cf deploy/dev/build, resource commands for DNS, zones, D1, KV, and R2 — and for choosing between cf and Wrangler in…
workers-best-practices
Cloudflare Workers best practices for production applications. Use when writing, reviewing, or configuring Workers.
find-journalists
Build a researched, fit-checked journalist list for a specific PR campaign. Prefer Medialyst's asynchronous media-list research workflow when available, with explicit approval before credit spend; otherwise produce a best-effort local list with only publicly listed, source-cited contacts.
story-origin-check
Recover the first public timestamp and canonical major coverage for a newsjacking signal, then decide whether newer coverage is the same story, a different story, or a materially new development.
relevance-coarse-filter
Cheap, high-recall first-pass filter that removes obvious junk from a detector candidate pool before expensive story-origin research and PR judgment. Decides keep, monitoronly, or reject — never ranks, writes angles, verifies dates, or decides whether to pitch.
ai-visibility-writing
Audit, question, suggest, or fact-preservingly revise a press release, blog post, contributed article, or expert explainer so AI answer systems can more easily retrieve, understand, quote, and cite its useful information. Use when someone asks for AI visibility, AI search, answer-engine, AEO, GEO, AI Overview, or…