writing-agents

writing-agents is a skill for Claude Code, Codex from xiaolai/nlpm. It costs 35 tokens per session (2,674 once invoked), scanned A, original, ISC.

Guidance for writing Claude Code agent definition files in Markdown, including their triggers and output instructions. It also notes how agent definitions differ in Codex CLI and Antigravity.

In plain words
What is it for?
Use it when creating, improving, or reviewing Claude Code agents and their definition files.
Why use it?
It helps agents start for the right requests and produce consistent results instead of being chosen unpredictably or behaving differently each time.

Skill for Claude CodeCodex

Written for Claude Code and Codex: shipped in a Claude Code plugin, but also reads ~/.codex or $CODEX_HOME. Also seen: reads .claude/ paths; mentions subagents; mentions Claude Code.

Part of the nlpm plugin — 17 skills, 12 commands, 8 agents, 1 hook shipped together

Install

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.

agentmods
npx agentmods add skills/xiaolai/nlpm/writing-agents
Any agent
npx skills add xiaolai/nlpm --skill writing-agents
Clone the repo
git clone --depth 1 https://github.com/xiaolai/nlpm

Made for: Claude Code, Codex.

Or install nlpm, the plugin that ships this one along with the rest of its 17 skills, 12 commands, 8 agents, 1 hook.

Wrote 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.

agentmods badge for writing-agents

README.md
[![agentmods](https://agentmods.dev/badge/skills/xiaolai/nlpm/writing-agents.svg)](https://agentmods.dev/skills/xiaolai/nlpm/writing-agents)
Your own site
<a href="https://agentmods.dev/skills/xiaolai/nlpm/writing-agents"><img src="https://agentmods.dev/badge/skills/xiaolai/nlpm/writing-agents.svg" alt="Measured on agentmods" height="20"></a>
Per session 35 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,674 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00035 $0.02674
Opus 5 $0.00017 $0.01337
Sonnet 5 $0.00007 $0.00535
Haiku 4.5 $0.00003 $0.00267

Measured 6d ago against content hash e78b21d49da2, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

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.

codex/skills/writing-agents/SKILL.md · 339 lines

How it starts

The opening of the file, as written. The whole thing — 339 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Writing Agents

Scope: covers Claude Code agent .md file authoring (Markdown + frontmatter at .claude/agents/). Codex CLI defines agents differently — as [agents.<name>] TOML tables in .codex/config.toml; see [[nlpm:conventions-codex]]. Antigravity subagents are under-documented at this writing; see [[nlpm:conventions-antigravity]]. For multi-agent orchestration, see [[orchestration]]. For plugin architecture, see [[writing-plugins]].

1. Example Blocks Make or Break Triggering

Without <example> blocks, Claude guesses when to dispatch your agent. With them, it pattern-matches against real scenarios.

Minimum: 2 examples. Ideal: 3 -- one obvious trigger, one edge case, one non-obvious.

Example Block Anatomy

<example>
Context: [what the user is doing -- not just "user needs help"]
user: "[realistic user message that should trigger this agent]"
assistant: "[what Claude says when dispatching -- shows the decision logic]"
</example>

Bad Example (too vague -- 40% trigger accuracy)

<example>
Context: User needs code review
user: "review my code"
assistant: "I'll use the reviewer agent."
</example>

Problems: generic context, generic query, no decision logic shown.

Good Example (specific scenario -- 92% trigger accuracy)

<example>
Context: User just pushed changes to the authentication module and wants feedback before merging
user: "Can you check if the auth changes look good before I create the PR?"
assistant: "I'll dispatch the security-reviewer agent to check the auth changes for vulnerabilities, token handling, and session management best practices."
</example>

Why it works: specific context (auth module, pre-PR), realistic query (how users actually talk), decision logic visible (what the agent will check).

The Three-Example Pattern

Example Purpose What it demonstrates
1. Obvious trigger Baseline dispatch User explicitly asks for what the agent does
2. Edge case Boundary behavior User asks something adjacent -- agent should still trigger
3. Non-obvious Discovery User doesn't know the agent exists but their need matches

Read the full file on GitHub · 339 lines

Changes

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.

  1. 6d ago First seen · 339 lines · 35 tokens per session scan A e78b21d49da2

Subscribe to this mod's changes

writing-agents is a skill published in the GitHub repository xiaolai/nlpm (135 stars, last pushed yesterday), licensed ISC. It adds 35 tokens to every session and 2,674 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.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

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…

microsoft/ai-agents-for-beginners · 200 tokens

chronicle

Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…

microsoft/vscode · 72 tokens

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.

microsoft/vscode · 53 tokens

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…

microsoft/vscode · 71 tokens

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…

vercel/next.js · 95 tokens