quick-fix

A command that sends a straightforward coding fix through an implementation-and-review loop without first writing a plan. It is intended for fixes with a known cause and one obvious solution.

In plain words
What is it for?
Use it for small or cohesive fixes, including changes that pass through several files, when the cause and solution are already clear.
Why use it?
It removes planning and setup steps when they would add delay to a simple, well-understood change, while still keeping a final audit for missed issues.

Command

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 commands/damusix/atomic-claude/quick-fix
Clone the repo
git clone --depth 1 https://github.com/damusix/atomic-claude
Per session 112 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 3,082 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found 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 $0.00112 $0.03082
Opus 5 $0.00056 $0.01541
Sonnet 5 $0.00022 $0.00616
Haiku 4.5 $0.00011 $0.00308

Measured 2d ago against content hash c534f8e3d804, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

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.

context/commands/quick-fix.md · 191 lines

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.

Read the full file on GitHub · 191 lines

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. 2d ago First seen · 191 lines · 112 tokens per session scan A c534f8e3d804

Subscribe to this mod's changes

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.