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 anthony-spruyt/claude-plugins --skill writing-agentsgit clone --depth 1 https://github.com/anthony-spruyt/claude-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/anthony-spruyt/claude-plugins/writing-agents)<a href="https://agentmods.dev/skills/anthony-spruyt/claude-plugins/writing-agents"><img src="https://agentmods.dev/badge/skills/anthony-spruyt/claude-plugins/writing-agents/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/anthony-spruyt/claude-plugins/writing-agents"><img src="https://agentmods.dev/badge/skills/anthony-spruyt/claude-plugins/writing-agents.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 | $0.00067 | $0.02462 |
| Opus 5.5 | $0.00027 | $0.00985 |
| Sonnet 5.5 | $0.00013 | $0.00492 |
| Haiku 4.5 | $0.00007 | $0.00246 |
Grade A, and why
writing-agents 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 6d 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 — 140 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Writing Agents
Overview
Patterns and workflows for writing effective, token-efficient agent system prompts.
Quick Reference
| Task | Reference |
|---|---|
| Frontmatter fields | references/agent-frontmatter.md |
| Override built-in | references/agent-frontmatter.md, Overriding built-in agents |
| Plugin agents | references/agent-frontmatter.md, Plugin agents |
| Description template | references/project-patterns.md Section 6 |
| Model selection | references/project-patterns.md Section 2 |
| Size targets | references/project-patterns.md Section 3 |
| Output format patterns | references/project-patterns.md Section 4 |
| Handoff patterns | references/project-patterns.md Section 5 |
| Emphasis calibration | references/anthropic-best-practices.md Section 3 |
| Parallel execution | references/anthropic-best-practices.md Section 6 |
| Common mistakes | references/common-mistakes.md |
Description Field
Syntax: Single line with \n for newlines. Wrap in '...' if contains # after whitespace.
Write in third person — the description is injected into the system prompt by the routing system.
Content pattern: Brief capability statement (1 clause), then triggering conditions. Don't expand the capability statement into a workflow summary: the description rides in every parent request and is all the parent sees when deciding to delegate, while the body loads only when the agent runs. Keep "what" to a single clause, put process details in the body.
Include:
- "When to use" conditions, written as categories of intent rather than sample phrasings
- "When NOT to use" boundaries, naming the agent or command to use instead
Leave <example> dialogue out of the description. The parent reads it on every request as routing signal, and sample exchanges anchor delegation to the phrasings they show; the intent categories carry the same signal. Worked examples the agent itself needs go in the body.
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.
- 6d ago First seen · 140 lines · 67 tokens per session scan A 7271cb5a61a8
writing-agents is a skill published in the GitHub repository anthony-spruyt/claude-plugins (2 stars, last pushed yesterday), licensed MIT. It adds 67 tokens to every session and 2,462 once invoked, about $0.0003 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 2026-10-13.
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…
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…
next-cache-components-optimizer
Optimize the meaningful UI available immediately from a Next.js route on an initial load (hard navigation) or named client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route and entry point at a time; the shipped test then guards…