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 OutlineDriven/odin-claude-plugin --skill writing-skillsgit clone --depth 1 https://github.com/OutlineDriven/odin-claude-pluginWrote 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/outlinedriven/odin-claude-plugin/writing-skills)<a href="https://agentmods.dev/skills/outlinedriven/odin-claude-plugin/writing-skills"><img src="https://agentmods.dev/badge/skills/outlinedriven/odin-claude-plugin/writing-skills/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/outlinedriven/odin-claude-plugin/writing-skills"><img src="https://agentmods.dev/badge/skills/outlinedriven/odin-claude-plugin/writing-skills.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 | $0.00065 | $0.01130 |
| Opus 5 | $0.00032 | $0.00565 |
| Sonnet 5 | $0.00013 | $0.00226 |
| Haiku 4.5 | $0.00006 | $0.00113 |
Grade A, and why
writing-skills 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 8d 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 — 79 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Writing skills
One property decides whether a document works: the agent takes the same process every run. The levers below produce it. The packaging differs across a skill, an AGENTS.md, and a pointer-reached doc; the writing does not.
Contract
| Field | Bound contract |
|---|---|
| Trigger | A SKILL.md or AGENTS.md/CLAUDE.md is being authored, refactored, ported, or upgraded, or the user asks to write a skill, improve one, or fix unreliable skill firing |
| Authority | Reversible local writes to the target document and the skill directory it belongs to, plus the repository-owned registration or attribution surfaces those artifacts require. Never publishes, installs, commits, or mutates remote state |
| Side effect | The target document changes on disk when the request is to author or refactor one. Guidance alone when the request is a review |
| Done | The document is predictable, and the repository's own gate passes on every changed file |
Inputs
The document being authored or refactored: a skill, an AGENTS.md/CLAUDE.md, or a pointer-reached doc. Optionally the surrounding skill tree, which co-location and routing decisions need.
Procedure
Each step names its lever and its completion criterion. The levers themselves live in
references/authoring-levers.md; load it when a step's name is not enough to act on.
- Identify the document type: a skill, an AGENTS.md/CLAUDE.md, or a pointer-reached doc. Done when: the type is named, because step 8 fires only for a skill.
- Shape every context pointer against the pointer rules in
references/authoring-levers.md: state what the material is and the branches that trigger reaching it, front-load the leading word, give one trigger per branch and collapse synonyms that rename a single branch, and cut identity the body already carries. Done when: every pointer meets all of those rules. - Assign every document and pointer to a load budget. Done when: each assignment is explicit and its trade-off is stated.
- Place each piece on the information hierarchy. Done when: every piece sits at one level, and neither the top bloats nor needed material hides.
- Apply progressive disclosure and co-location. Done when: branch-specific material is behind pointers and the top stays legible.
- Set a completion criterion for every step, clear and high-demand. Done when: every step has one.
- Justify every split by sequence-rush or invocation-reach. Done when: each split carries its justification and the rest are rejected.
- For a skill document, apply
references/skill-mechanics.md. Done when: those mechanics are applied, or the document is not a skill and this step is skipped. - Hunt for leading words and collapse restatements into them. Done when: restatements are collapsed.
- Prune to one source of truth per meaning. Done when: no duplication and no no-op remain.
- When the request writes a skill directory, follow
references/authoring-procedure.md. Done when: the write path reached its validation step, or the request was a review.
What ships with it
4 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.
- 8d ago First seen · 79 lines · 65 tokens per session scan A de259eb7362b
writing-skills is a skill published in the GitHub repository OutlineDriven/odin-claude-plugin (36 stars, last pushed 3d ago), licensed Apache-2.0. It adds 65 tokens to every session and 1,130 once invoked, about $0.0003 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 2026-09-04.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
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…
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…