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 agentmods add commands/damusix/atomic-claude/quick-fixgit clone --depth 1 https://github.com/damusix/atomic-claudeWhat 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 | $0.00112 | $0.03082 |
| Opus 5 | $0.00056 | $0.01541 |
| Sonnet 5 | $0.00022 | $0.00616 |
| Haiku 4.5 | $0.00011 | $0.00308 |
Grade A, and why
quick-fix 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 2d 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 — 191 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are the orchestrator. The user has handed you a task whose cause is known and whose fix has one obvious shape. You will NOT implement it yourself — you drive the same fresh-context implement→review loop as /subagent-implementation, minus the spec gate, the worktree gate, and the finalize ceremony. Speed is the point: no spec authored, no worktree created, no implementation log, no docs/signals refresh at the end. The audit stays: atomic-auditor reads the finished range once, because a fast loop is exactly where comment noise and a duplicated helper slip past per-iteration review.
$ARGUMENTS: <task description>. If empty, refuse: usage: /quick-fix <task description>. Stop.
Fit gate
Before dispatching anything, check whether this task actually fits /quick-fix. HOLD means proceed; EXIT means stop and hand off before any subagent runs.
| Signal | Verdict | Why |
|---|---|---|
| Root cause is known; one fix shape is obvious | HOLD | exactly what /quick-fix is for |
| Change spans many files but is one cohesive, mechanically obvious slice (e.g. one param threaded through DTO → validator → controller → repo → client) | HOLD | cohesion-bounded, not file-count-bounded — axiom 1 |
| Root cause is unknown or unclear | EXIT → /subagent-diagnose (or the atomic-debug skill) |
/quick-fix assumes the cause is already known; diagnosing an unknown cause is different work |
| Multiple viable approaches to the fix | EXIT → /atomic-plan |
needs a decision, not just execution |
| Success criteria are fuzzy or debatable | EXIT → /atomic-plan |
needs criteria fixed before dispatch |
| An architectural or contract choice is implied (new public API, schema/migration, cross-service contract change) | EXIT → /atomic-plan |
needs design, not just a fix |
On EXIT: state the signal that fired in one line, print the handoff text from the Escape hatch section below, and stop before any dispatch. No numeric file threshold appears anywhere in this gate.
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.
- 2d ago First seen · 191 lines · 112 tokens per session scan A c534f8e3d804
quick-fix is a command published in the GitHub repository damusix/atomic-claude (83 stars, last pushed 8d ago), licensed MIT. It adds 112 tokens to every session and 3,082 once invoked, about $0.0006 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 2026-08-30.
Other commands, from other repositories
icpg-bootstrap
Infer ReasonNodes from existing git commit history. One-time setup for existing codebases.
version
Display current guide and Claude Code versions.
go-review
Go code review for idiomatic patterns.
execute
Executa o plano aprovado em .first-plan/07-state/plans/. Segue o plano à risca, para se algo invalidar premissa, gera relatório ao final.
dispatcher
Pick the next-best repo to work on across the portfolio — rank free repos, recommend one, claim its lease atomically, and route to the entry command.
docs-review
Phase 4 of documenting-projects: Quality gate with 8 measurable criteria and iteration. Triggers: '/docs-review', invoked by documenting-projects orchestrator.