writing-skills

writing-skills is a skill for Claude Code, Codex from alleneubank/claude-code. It costs 28 tokens per session (549 once invoked), scanned A, original, Apache-2.0.

A set of guidelines for creating or editing reusable agent skills so they are concise, discoverable, and suited to their target tool.

In plain words
What is it for?
Use it when designing or maintaining skills, choosing their location, defining their structure, and deciding what reusable guidance belongs in them.
Why use it?
It helps avoid turning one-off instructions into bloated skills and clarifies where shared or tool-specific versions should live.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: mentions subagents; mentions Codex.

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/alleneubank/claude-code/writing-skills
Any agent
npx skills add alleneubank/claude-code --skill writing-skills
Clone the repo
git clone --depth 1 https://github.com/alleneubank/claude-code

Made for: Claude Code, Codex.

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-skills

README.md
[![agentmods](https://agentmods.dev/badge/skills/alleneubank/claude-code/writing-skills.svg)](https://agentmods.dev/skills/alleneubank/claude-code/writing-skills)
Your own site
<a href="https://agentmods.dev/skills/alleneubank/claude-code/writing-skills"><img src="https://agentmods.dev/badge/skills/alleneubank/claude-code/writing-skills.svg" alt="Measured on agentmods" height="20"></a>
Per session 28 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 549 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 $0.00028 $0.00549
Opus 5 $0.00014 $0.00275
Sonnet 5 $0.00006 $0.00110
Haiku 4.5 $0.00003 $0.00055

Measured 6d ago against content hash 1128393f611a, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

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 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-overrides/skills/writing-skills/SKILL.md · 88 lines

How it starts

The opening of the file, as written. The whole thing — 88 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Writing Skills

Overview

A skill should capture reusable judgment, not a story about one session.

Core principle: Write the minimum instructions that reliably change future agent behavior on the right class of tasks.

Directory Choice

Choose the source of truth before editing:

  • Shared skill source: edit the repo-managed Claude skill, not the generated runtime copy
  • Codex-only adaptation: edit the repo-managed Codex override, not the generated runtime copy

In this dotfiles setup, those live under:

  • claude-code/.claude/skills/<skill-name>/
  • claude-code/codex-overrides/skills/<skill-name>/

Use a Codex override when the upstream shared skill exists but its workflow or wording does not cleanly fit Codex.

When to Create a Skill

Create or update a skill when:

  • The technique is reusable across tasks
  • The agent repeatedly misses the same judgment call
  • A short document can prevent recurring mistakes

Do not create a skill for:

  • One-off project context
  • Purely mechanical rules that should be enforced by code or linting
  • Content that belongs in repo instructions instead

Structure

Each skill directory should stay small:

skill-name/
  SKILL.md
  supporting-file.md   # only when needed

Prefer one concise SKILL.md. Add supporting files only for heavy reference material.

Metadata Rules

Frontmatter supports only:

  • name
  • description

Description rules:

  • Start with Use when...
  • Describe triggering conditions, not the workflow
  • Stay specific enough for discovery
  • Avoid harness-specific claims unless the skill is intentionally harness-specific

Authoring Rules

  • Keep the workflow native to the target harness.
  • Name real tools and files the agent actually has.
  • Prefer concrete triggers over broad abstractions.
  • Cut repeated explanations aggressively.
  • Include red flags when the failure mode is predictable.

Testing the Skill

Validate the skill against realistic tasks:

  1. Observe baseline behavior on a representative request.
  2. Write or revise the skill to address the real failure.
  3. Re-run the task and compare behavior.
  4. Tighten wording only where the skill still leaves loopholes.

Read the full file on GitHub · 88 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 · 88 lines · 28 tokens per session scan A 1128393f611a

Subscribe to this mod's changes

writing-skills is a skill published in the GitHub repository alleneubank/claude-code (52 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 28 tokens to every session and 549 once invoked, about $0.0001 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