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 samkawsarani/sams-product-plugins --skill write-dev-docsgit clone --depth 1 https://github.com/samkawsarani/sams-product-pluginsWrote 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/samkawsarani/sams-product-plugins/write-dev-docs)<a href="https://agentmods.dev/skills/samkawsarani/sams-product-plugins/write-dev-docs"><img src="https://agentmods.dev/badge/skills/samkawsarani/sams-product-plugins/write-dev-docs/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/samkawsarani/sams-product-plugins/write-dev-docs"><img src="https://agentmods.dev/badge/skills/samkawsarani/sams-product-plugins/write-dev-docs.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 | $0.00116 | $0.02333 |
| Opus 5.5 | $0.00046 | $0.00933 |
| Sonnet 5.5 | $0.00023 | $0.00467 |
| Haiku 4.5 | $0.00012 | $0.00233 |
Grade A, and why
write-dev-docs 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 — 193 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Dependency Check
Before starting, check optional dependencies:
- qmd (optional): Run
command -v qmd.- If available: Use
qmd queryfor semantic search across knowledge bases — this gives the best results. - If missing: Fall back to
GrepandGlobfor keyword search. Note to the user thatqmdwould improve search quality, but proceed without it.
- If available: Use
Developer Documentation Generator
Generate Stripe-quality developer documentation — API references, integration guides, code recipes, and Postman collections — from any input source.
Quick Start
Arguments: $ARGUMENTS
Parse $ARGUMENTS to determine:
- Doc type: api-reference, guide, recipe, postman
- Subject name: The resource, feature, or API being documented
- Additional context: Language preferences, audience level, specific endpoints
If doc type is not specified, ask the user which type they need.
Triggers:
/write-dev-docs api-reference payments— API reference for payments resource/write-dev-docs guide getting-started— Integration quickstart guide/write-dev-docs recipe create-payment— Multi-language code recipe/write-dev-docs postman payments-api— Exportable Postman collection- "Write API docs for..." / "Create a developer guide for..." / "Generate code samples for..."
Scope — this skill is for:
- API endpoint documentation (REST)
- Developer integration guides and tutorials
- Multi-language code samples and recipes
- Postman/API client collections
NOT for:
- PM documents (PRDs, specs, briefs) → use
write-doc - UX copy or UI text → use
write-ux-copy - SDK source code or library implementation
- Internal architecture docs
Doc Types
| Type | Command | Output | Audience | Reference |
|---|---|---|---|---|
| API Reference | api-reference [resource] |
Endpoint-by-endpoint reference with params, responses, errors | Developers integrating the API | references/api-reference-format.md |
| Integration Guide | guide [name] |
Step-by-step tutorial from zero to working code | Developers new to the platform | references/guide-format.md |
| Code Recipe | recipe [use-case] |
Multi-language copy-paste snippets (cURL, Node.js, Python) | Developers building specific features | references/code-recipe-format.md |
| Postman Collection | postman [api-name] |
Exportable Postman v2.1 JSON with test scripts | Developers testing and exploring the API | references/postman-format.md |
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.
- assets/api-reference-template.md 13 KB
- assets/code-recipe-template.md 4.4 KB
- assets/guide-template.md 5.3 KB
- assets/postman-collection-template.json 11 KB
- references/api-reference-format.md 6.9 KB
- references/code-recipe-format.md 5.8 KB
- references/guide-format.md 5.3 KB
- references/postman-format.md 6.5 KB
- references/quality-checklist.md 3.9 KB
- references/writing-standards.md 10 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.
- 1mo ago Changed · +30 lines · +25 tokens per session 1f8f8c187d5c
- 2mo ago First seen · 163 lines · 91 tokens per session scan A eda4f376e125
write-dev-docs is a skill published in the GitHub repository samkawsarani/sams-product-plugins (2 stars, last pushed 1mo ago), licensed MIT. It adds 116 tokens to every session and 2,333 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 2026-08-31.
write-dev-docs compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| write-dev-docssamkawsarani/sams-product-plugins | Skill | 2 | 1mo ago | MIT | A | 116 | Claude Code |
| mem0-oss-to-platformmem0ai/mem0 | Skill | 69k | yesterday | Apache-2.0 | A | 217 | Claude Code, Codex |
| azure-mgmt-botservice-dotnetmicrosoft/skills | Skill | 3.2k | yesterday | MIT | A | 78 | Claude Code |
| fastapi-router-pymicrosoft/skills | Skill | 3.2k | yesterday | MIT | A | 46 | Claude Code |
| dev-runtimelangwatch/langwatch | Skill | 5.0k | today | Apache-2.0 | A | 172 | Claude Code |
| api-designericrisco/rsc-harness | Skill | 529 | 3d ago | MIT | A | 105 | Claude Code, Codex |
| migrate-segw-to-raparc-mcp/arc-1 | Skill | 253 | today | MIT | A | 106 | Claude Code |