writing-great-skills

writing-great-skills is a skill for Claude Code, Codex from stainless-code/codemap. It costs 24 tokens per session (2,002 once invoked), scanned A, a copy of writing-great-skills, MIT.

A reference for writing and editing predictable skills for coding agents. It defines terms and explains how invocation, information hierarchy, completion criteria, and failure handling should be designed.

In plain words
What is it for?
Use it when authoring or reviewing skills, choosing between automatic and user-triggered invocation, or improving a skill’s instructions.
Why use it?
It helps agents follow a repeatable process instead of relying on vague instructions or overly large skill descriptions.

Skill for Claude CodeCodex

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

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-great-skills

README.md
[![agentmods](https://agentmods.dev/badge/skills/stainless-code/codemap/writing-great-skills.svg)](https://agentmods.dev/skills/stainless-code/codemap/writing-great-skills)
Your own site
<a href="https://agentmods.dev/skills/stainless-code/codemap/writing-great-skills"><img src="https://agentmods.dev/badge/skills/stainless-code/codemap/writing-great-skills.svg" alt="Measured on agentmods" height="20"></a>
Per session 24 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,002 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin 100% copy Near-identical to another mod 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 $0.00024 $0.02002
Opus 5 $0.00012 $0.01001
Sonnet 5 $0.00005 $0.00400
Haiku 4.5 $0.00002 $0.00200

Measured 5d ago against content hash 7d80554eac9b, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

writing-great-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 5d 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.

Origin

This is a copy

100% identical to writing-great-skills — 2 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.

.agents/skills/writing-great-skills/SKILL.md · 83 lines

How it starts

The opening of the file, as written. The whole thing — 83 lines — stays where its author put it; the contents beside it link to each section on GitHub.

A skill exists to wrangle determinism out of a stochastic system. Predictability — the agent taking the same process every run, not producing the same output — is the root virtue; every lever below serves it.

Bold terms are defined in GLOSSARY.md; look them up there for the full meaning.

Invocation

Two choices, trading different costs:

  • A model-invoked skill keeps a description, so the agent can fire it autonomously and other skills can reach it (you can still type its name too). It contributes to context load — the description sits in the window every turn. Mechanics: omit disable-model-invocation, and write a model-facing description with rich trigger phrasing ("Use when the user wants…, mentions…").
  • A user-invoked skill strips the description from the agent's reach: only you, typing its name, can invoke it — and no other skill can. Zero context load, but it spends cognitive load: you are the index that must remember it exists. Mechanics: set disable-model-invocation: true; the description becomes human-facing — a one-line summary, trigger lists stripped.

Pick model-invocation only when the agent must reach the skill on its own, or another skill must. If it only ever fires by hand, make it user-invoked and pay no context load.

When user-invoked skills multiply past what you can remember, that piled-up cognitive load is cured by a router skill: one user-invoked skill that names the others and when to reach for each.

Writing the description

A model-invoked description does two jobs — state what the skill is, and list the branches that should trigger it. Every word increases context load, so a description earns even harder pruning than the body:

  • Front-load the skill's leading word — the description is where it does its invocation work.
  • One trigger per branch. Synonyms that rename a single branch are duplication — "build features using TDD … asks for test-first development" is one branch written twice. Collapse them; keep only genuinely distinct branches.
  • Cut identity that's already in the body. Keep the description to triggers, plus any "when another skill needs…" reach clause.

Read the full file on GitHub · 83 lines

Files

What ships with it

1 file 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.

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. 5d ago First seen · 83 lines · 24 tokens per session scan A 7d80554eac9b

Subscribe to this mod's changes

writing-great-skills is a skill published in the GitHub repository stainless-code/codemap (8 stars, last pushed today), licensed MIT. It adds 24 tokens to every session and 2,002 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 0 findings. It is 100% identical to writing-great-skills, differing in 2 lines, and is treated as a copy.

Related

Other skills, from other repositories

roam

Codebase comprehension via roam-code CLI. Use when exploring codebases, planning modifications, debugging failures, assessing PR risk, or checking architecture health. Triggers on: understanding project structure, pre-change safety checks, finding symbols/files, blast radius analysis, affected tests, health scoring…

Cranot/roam-code · 86 tokens

release

Publishing a jMunch release (jcodemunch-mcp, jdocmunch-mcp, jdatamunch-mcp, jragmunch-cli), reviewing/merging/closing PRs, and responding to the community. Load before any version bump, PyPI upload, tag, GitHub release, MCP registry publish, or PR merge.

jgravelle/jcodemunch-mcp · 75 tokens

observatory

Context for the jcodemunch-observatory weekly scorecard — what it tracks, the Monday 06:00 UTC cron, why scores must be pulled live rather than transcribed, the NestJS grade story, and the workflow's version dispatch input. Load before quoting, interpreting, or editing observatory scores or config.

jgravelle/jcodemunch-mcp · 69 tokens

benchmark-methodology

Rules for measuring or quoting any benchmark number in this repo. Load before running the bench tier, writing a delta into a PR or CHANGELOG, or touching anything under benchmarks/.

jgravelle/jcodemunch-mcp · 39 tokens

claude-md-budget

How to keep CLAUDE.md under its character Floor without deleting a rule: measure sections first, rotate by derivability, two edits per rotation. Load in /release step 6 and before any CLAUDE.md rotation or split.

jgravelle/jcodemunch-mcp · 53 tokens

pr-description

The PR title and body template, and the rules for any comment drafted for a reporter or contributor. Load when writing a PR body, a release PR, or a triage response.

jgravelle/jcodemunch-mcp · 40 tokens