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 damusix/atomic-claude --skill atomic-writinggit clone --depth 1 https://github.com/damusix/atomic-claudeWrote 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/damusix/atomic-claude/atomic-writing)<a href="https://agentmods.dev/skills/damusix/atomic-claude/atomic-writing"><img src="https://agentmods.dev/badge/skills/damusix/atomic-claude/atomic-writing/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/damusix/atomic-claude/atomic-writing"><img src="https://agentmods.dev/badge/skills/damusix/atomic-claude/atomic-writing.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium MCP Rug Pull · line 130 npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.Fix: Pin the version: npx @scope/[email protected]
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 | $0.00281 | $0.05986 |
| Opus 5.5 | $0.00112 | $0.02394 |
| Sonnet 5.5 | $0.00056 | $0.01197 |
| Haiku 4.5 | $0.00028 | $0.00599 |
Grade A, and why
atomic-writing 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 1mo 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 — 296 lines — stays where its author put it; the contents beside it link to each section on GitHub.
- "draft the README", "write the docs", "improve this prose", "edit the guide"
- "write the spec", "write the design doc", "clean up this doc", "make this readable"
- "clean this up", "tighten this", "edit for tone" — on any file the repo ships
/documentationediting any indexed surface- Writing or editing any
.mdfile that ships in the repo
Every file this repo ships has one voice: plain, specific, technical, and visual where the content has a shape. A spec, a README, a design doc, and a command artifact differ in length and structure. They do not differ in voice.
The reason is a contract that reads well to only one party is broken. A spec an agent can walk but a human cannot review is not a contract, and a guide a human enjoys but an agent cannot follow is not documentation. Write for the human. A model reads what a human reads.
<voice_rules>
The one boundary
| Atomic output style | Atomic-writing (this skill) | |
|---|---|---|
| Governs | How Claude talks in the terminal | What Claude writes into files |
| Where | TUI replies to the user | Every .md file that ships in the repo |
| Form | Fragments OK, drop articles, ASCII only | Full sentences where prose is right, Mermaid where a picture is right |
| Lives in | output-styles/atomic.md |
This skill |
Nothing else splits. There is no separate "terse technical" voice for specs, designs, CLAUDE.md, or agent prompts.
Same voice, different length
Length is set by the job the surface does, not by a compression quota and not by a house maximum.
| Surface | Job | Length |
|---|---|---|
README.md, docs/guides/ |
Teach the system to someone new | As long as the explanation needs |
docs/reference/ |
Answer a lookup fast | Tables and lists first, prose for what a table cannot hold |
docs/spec/, docs/design/ |
Carry a contract a human approves and an agent implements | Shortest that carries the contract in full; the structure is the contract |
docs/wiki/ |
Orient a reader to a codebase | Dense. Facts with paths, no throat-clearing |
docs/research/ |
Record what was found and why a path was chosen | As long as the evidence needs |
CLAUDE.md, rules/ |
Instruct, in every session | Tightest. Every line costs tokens on every turn |
commands/, agents/, skills/, output-styles/ |
Instruct an agent mid-task | Tight. Instruct plainly, cut rationale that only defends the instruction |
What ships with it
3 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.
- 1mo ago Changed · +23 lines · +13 tokens per session d09bbedd30dc
- 2mo ago First seen · 273 lines · 268 tokens per session scan A 1b50a8037044
atomic-writing is a skill published in the GitHub repository damusix/atomic-claude (116 stars, last pushed 7d ago), licensed MIT. It adds 281 tokens to every session and 5,986 once invoked, about $0.0011 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 2026-08-30.
atomic-writing compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| atomic-writingdamusix/atomic-claude | Skill | 116 | 7d ago | MIT | A | 281 | Claude Code, Codex |
| loongsuite-pilot-insightalibaba/loongsuite-pilot | Skill | 243 | 2d ago | Apache-2.0 | A | 111 | Claude Code, Codex |
| agentloop-audit-queryalibaba/loongsuite-pilot | Skill | 243 | 2d ago | Apache-2.0 | A | 114 | Claude Code, Codex |
| loongsuite-pilot-opsalibaba/loongsuite-pilot | Skill | 243 | 2d ago | Apache-2.0 | A | 15 | Claude Code, Codex |
| sipcode-regressAnuj7411/sipcode | Skill | 46 | 23d ago | MIT | A | 105 | Claude Code |
| Codex-apiopencue/cuecards | Skill | 8 | today | MIT | A | 294 | Claude Code, Codex |
| context-mode-opsopencue/cuecards | Skill | 8 | today | MIT | A | 75 | Claude Code, Codex |