writing-skills

writing-skills is a skill for Claude Code from aneja5/forge-skills. It costs 53 tokens per session (2,779 once invoked), scanned A, original, MIT.

A method for creating and editing reusable coding-agent skills. It treats skill instructions like software: first test whether an agent fails without them, then check that the new instructions prevent that failure.

In plain words
What is it for?
Use it when creating, editing, promoting, or verifying a forge-skill, including its tests and supporting files.
Why use it?
It helps avoid writing instructions that sound useful but do not change agent behavior. The process exposes gaps and closes loopholes before deployment.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: mentions CLAUDE.md; mentions subagents; mentions AGENTS.md.

Part of the forge-skills plugin — 42 skills, 36 commands, 1 hook shipped together

Good fit Use it when creating, editing, promoting, or verifying a forge-skill, including its tests and supporting files.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/aneja5/forge-skills/writing-skills
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.

Any agent
npx skills add aneja5/forge-skills --skill writing-skills
Clone the repo
git clone --depth 1 https://github.com/aneja5/forge-skills

Made for: Claude Code.

Or install forge-skills, the plugin that ships this one along with the rest of its 42 skills, 36 commands, 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-skills

README.md
[![agentmods](https://agentmods.dev/badge/skills/aneja5/forge-skills/writing-skills/github.svg)](https://agentmods.dev/skills/aneja5/forge-skills/writing-skills)
Your own site
<a href="https://agentmods.dev/skills/aneja5/forge-skills/writing-skills"><img src="https://agentmods.dev/badge/skills/aneja5/forge-skills/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.

agentmods 80×15 button for writing-skills

Your own site · 80×15
<a href="https://agentmods.dev/skills/aneja5/forge-skills/writing-skills"><img src="https://agentmods.dev/badge/skills/aneja5/forge-skills/writing-skills.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 53 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,779 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 $0.00053 $0.02779
Opus 5 $0.00026 $0.01389
Sonnet 5 $0.00011 $0.00556
Haiku 4.5 $0.00005 $0.00278

Measured 8d ago against content hash db639282adcf, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, 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 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.

skills/writing-skills/SKILL.md · 211 lines

How it starts

The opening of the file, as written. The whole thing — 211 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Writing Skills

Overview

Writing a forge-skill IS test-driven development applied to documentation.

You write a pressure scenario (test case), watch a fresh agent fail at it without the skill (RED), write the skill (production code), watch the agent comply (GREEN), then close loopholes the agent invents (REFACTOR).

Adapted from Superpowers' writing-skills. See tests/METHODOLOGY.md for the full testing methodology.

When to Use

  • Creating a new skill in skills/<name>/SKILL.md
  • Editing an existing skill's body, frontmatter, or supporting files
  • Promoting a one-off prompt that's been used 3+ times into a reusable skill
  • Verifying a skill works before opening a PR

When NOT to Use

  • Project-specific conventions — those go in CLAUDE.md, not a skill
  • Pure reference material (templates, checklists) that doesn't enforce any rule — put it in references/
  • One-off solutions to one-off problems

The Iron Law

No skill ships without a failing test first.

Applies to new skills AND edits. If you can't show the baseline failure that motivated the skill, you don't know if the skill prevents the right failure.

Wrote the skill before running the test? Delete it. Start over. No exceptions:

  • Not for "simple additions"
  • Not for "just adding a section"
  • Not for "documentation updates"
  • Don't keep the un-tested draft as reference

Common Rationalizations

Excuse Reality
"It's just a documentation file, no need to test" Untested skills have unstated assumptions. Test catches them.
"I'm just adding a rationalization to the table" New rationalizations come from real session failures. If you didn't see one, don't add one.
"The skill is obviously clear to me" Clear to you ≠ clear to a fresh agent. Test it.
"I'll test if a user reports a problem" By then the skill has already shipped broken. Test first.
"Three pressures is too many for one scenario" One pressure agents resist easily. Three pressures forces the genuine choice.
"RED passed but that means the skill works" RED passing means the scenario isn't strong enough OR the skill prevents nothing useful.

Read the full file on GitHub · 211 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. 8d ago First seen · 211 lines · 53 tokens per session scan A db639282adcf

Subscribe to this mod's changes

writing-skills is a skill published in the GitHub repository aneja5/forge-skills (3 stars, last pushed 3mo ago), licensed MIT. It adds 53 tokens to every session and 2,779 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 2026-09-03.