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.
git 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/commands/damusix/atomic-claude/documentation)<a href="https://agentmods.dev/commands/damusix/atomic-claude/documentation"><img src="https://agentmods.dev/badge/commands/damusix/atomic-claude/documentation/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/commands/damusix/atomic-claude/documentation"><img src="https://agentmods.dev/badge/commands/damusix/atomic-claude/documentation.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00000 | $0.03021 |
| Opus 5.5 | $0.00000 | $0.01208 |
| Sonnet 5.5 | $0.00000 | $0.00604 |
| Haiku 4.5 | $0.00000 | $0.00302 |
Grade A, and why
documentation 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 — 330 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Run /documentation to bootstrap doc surface indexing or perform a full documentation pass.
Flags
--print-template— print the## Documentation surfacestable skeleton to stdout and exit. Paste into your CLAUDE.md to declare custom surfaces manually.--dry-run— print discovered/stale surfaces without applying edits or staging anything.--discover— re-scan and offer to update the surfaces table even when a table already exists. Use after adding new doc files.<range>— any valid git range (HEAD~5..HEAD,main..feature-branch). If omitted, defaults to<base>..HEADwhere<base>is the merge-base withmain.
Step 0 — Handle flags
If --print-template is present, print the following and exit:
## Documentation surfaces
| Path | Covers | Voice |
|------|--------|-------|
| `docs/architecture/payments.md` | billing, webhooks, Stripe | atomic-writing |
| `docs/models/README.md` | data model, ERD, migrations | atomic-writing |
| `docs/api/endpoints.md` | REST API, auth, rate limits | atomic-writing |
| `README.md` | project overview, quick start | atomic-writing |
Add this section to your committed CLAUDE.md and fill in your project's doc files. Voice is always atomic-writing — the column exists to name the skill that governs the edit, not to pick between alternatives.
Step 1 — Detect mode
Check whether a ## Documentation surfaces table exists in the project's committed CLAUDE.md (search CLAUDE.md at the git root; also check claude.local.md / CLAUDE.local.md).
- Table absent OR
--discoverflag present → run bootstrap mode (Step 2). - Table present AND no
--discoverflag → run authoring mode (Step 5).
Step 2 — Bootstrap: scan doc files
Run the deterministic scan:
atomic docs scan 2>/dev/null
If atomic is absent or returns a non-zero exit, fall back to:
find docs/ doc/ documentation/ wiki/ ADR/ adr/ decisions/ -name '*.md' 2>/dev/null
find . -maxdepth 3 -name 'README.md' 2>/dev/null | grep -v node_modules | grep -v .git
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 First seen · 330 lines · 0 tokens per session scan A f8a0d94fbb03
documentation is a command published in the GitHub repository damusix/atomic-claude (112 stars, last pushed 9d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 3,021 tokens. 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.
Other commands, from other repositories
save
Save current work state for next session. Creates/updates .planning/ files (CHECKPOINT.md, STATE.md, settings.json) so Heimdall resumes with full context. NOT a rewind — saves forward progress. Run before closing a session or at any milestone.
designmatch
Bootstrap the designmatch skill in a React Native project from a Claude Design link. Auto-imports the Visual QA stub helper (visual-qa.ts), writes default state.vqa.json, registers the canonical source, updates .gitignore, and prints the wiring snippet. Use when starting visual-parity work on a new RN screen or when…
maintain
Run automated maintenance — seeker finds bugs from pod logs and raises GitHub issues, fixer picks them up and creates PRs. Can run as a one-shot or scheduled via /schedule.
bench
Reproduce the public benchmark table on your own machine (spec S-5). Runs a fixed suite of coding tasks under two arms — raw Claude Code vs Heimdall — and PRODUCES real numbers (tokens, wall time, tests passing, cost) by actually running them. Never hardcodes results. Safe by default (dry mode: validates the suite +…
autonomy
Set Heimdall autonomy (1=Guided, 2=Checkpoint, 3=Full Auto) — how much the agent does before asking. Use with a number, +/- to cycle, or no argument to show current.
level
Deprecated alias for /hmd:autonomy. Sets Heimdall autonomy (1=Guided, 2=Checkpoint, 3=Full Auto). Still works; prints a one-line rename notice.