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/commit)<a href="https://agentmods.dev/commands/damusix/atomic-claude/commit"><img src="https://agentmods.dev/badge/commands/damusix/atomic-claude/commit/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/commit"><img src="https://agentmods.dev/badge/commands/damusix/atomic-claude/commit.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 | $0.00055 | $0.00552 |
| Opus 5.5 | $0.00022 | $0.00221 |
| Sonnet 5.5 | $0.00011 | $0.00110 |
| Haiku 4.5 | $0.00006 | $0.00055 |
Grade A, and why
commit 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.
What it actually says
Parse arguments
Read $ARGUMENTS. Scan for escalation tokens: push, pr, merge, squash, squash merge.
Token → escalation mapping:
| Token(s) in args | Path |
|---|---|
| (none) | commit only, then ask |
push |
commit + push |
pr |
commit + push + PR |
merge |
commit + merge to base |
squash (without merge) |
commit + squash branch |
squash merge (both tokens) |
commit + squash + merge to base |
If the args contain none of the tokens above, run the commit step, then prompt (see "Interactive path" below).
Commit
{{ template "commit-flow" . }}
If nothing to commit and branch has commits ahead of base, skip to the escalation step. If nothing to commit and branch is up to date with base, stop.
Escalation
Push path (push token or user picks Push)
{{ template "push-flow" . }}
PR path (pr token or user picks Open PR)
{{ template "push-flow" . }}
{{ template "pr-flow" . }}
Merge path (merge token or user picks Merge to base)
{{ template "merge-flow" . }}
Squash path (squash token, no merge, or user picks Squash branch)
{{ template "squash-flow" . }}
Squash + merge path (squash merge tokens or user picks Squash + merge)
{{ template "squash-flow" . }}
{{ template "merge-flow" . }}
Interactive path
If no escalation token was present in args, after the commit completes, ask via AskUserQuestion:
Committed. Ship further?
- Done — just the commit
- Push to remote
- Open PR
- Merge to base
- Squash + merge
Route the answer to the matching escalation path above. "Done" stops immediately.
{{ template "git-safety" . }}
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 · 73 lines · 55 tokens per session scan A c50832aa0378
commit is a command published in the GitHub repository damusix/atomic-claude (112 stars, last pushed 9d ago), licensed MIT. It adds 55 tokens to every session and 552 once invoked, about $0.0002 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.
Other commands, from other repositories
autocommit
Toggle auto git commits on/off for this project. Run without args to see status, or with "on"/"off" to set.
fix-tests-execute
Phase 2 of fixing-tests: Fix Execution - investigate, classify, fix, verify, and commit each work item.
simplify-transform
Apply verified simplifications with user approval. Part of simplify- family.
verify
Run verification commands and confirm output before making success claims. Use before committing, creating PRs, or claiming work is complete. Evidence before assertions, ALWAYS.
commit
Based on the above changes, create a single git commit.
align
Context-aware alignment. In plan mode it audits the active plan and folds the amendments in. Otherwise it reviews the branch, a named branch, or a pull request against Ion's principles, authors a fix plan, and after approval implements and commits the fixes.