quick-fix

quick-fix is a skill for Claude Code, Codex from iampawan/Manifest. It costs 87 tokens per session (1,288 once invoked), scanned A, original, MIT.

A workflow for handling very small software fixes and localized changes. It first checks whether the change is truly limited in scope and does not involve areas such as authentication, billing, schemas, or multiple platforms.

In plain words
What is it for?
Use it for one-line bug fixes, text or CSS edits, configuration changes, dependency updates, and other small changes with one clear root cause.
Why use it?
It avoids applying lengthy feature-development procedures to simple fixes while stopping changes that are too risky or broad for the quick path.

Skill for Claude CodeCodex

Part of the manifest plugin — 28 skills, 15 commands shipped together

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 skills/iampawan/manifest/quick-fix
Any agent
npx skills add iampawan/Manifest --skill quick-fix
Clone the repo
git clone --depth 1 https://github.com/iampawan/Manifest

Made for: Claude Code, Codex.

Or install manifest, the plugin that ships this one along with the rest of its 28 skills, 15 commands.

Wrote 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.

agentmods badge for quick-fix

README.md
[![agentmods](https://agentmods.dev/badge/skills/iampawan/manifest/quick-fix.svg)](https://agentmods.dev/skills/iampawan/manifest/quick-fix)
Your own site
<a href="https://agentmods.dev/skills/iampawan/manifest/quick-fix"><img src="https://agentmods.dev/badge/skills/iampawan/manifest/quick-fix.svg" alt="Measured on agentmods" height="20"></a>
Per session 87 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,288 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 $0.00087 $0.01288
Opus 5 $0.00044 $0.00644
Sonnet 5 $0.00017 $0.00258
Haiku 4.5 $0.00009 $0.00129

Measured 4d ago against content hash d2032d09e747, 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 4d 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.

skills/quick-fix/SKILL.md · 140 lines

How it starts

The opening of the file, as written. The whole thing — 140 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Quick-fix (express lane)

Process proportional to risk. Trivial changes get almost no process — fix it, add a regression test if it's testable, open a PR. No behaviors, no instrumentation fields, no perf budgets, no critics, no SLA timer, no launch report. Those exist to de-risk features; a one-line fix doesn't need them.

Target: minutes, not hours.

Step 1 — Triage. Is this actually trivial?

This is the most important step. The express lane is ONLY valid for changes that are:

  • Localized to a single root cause / small diff
  • In a single repo
  • No NEW analytics event needed (a fix reuses existing events; a feature adds them)
  • No schema change / migration
  • No new platform brought into scope
  • Not touching auth, billing, or payment primitives
  • Not a refactor spanning many files

If ALL of those hold → proceed on the express lane.

If ANY fail → STOP and escalate:

"This is bigger than a quick fix — it [adds a new event / touches two platforms / changes the schema]. Run /contract new instead so the critics catch the edge cases. Want me to start that?"

Don't force a real feature through the express lane. The triage gate is what keeps the fast path safe.

Edge: is it SO trivial that even this is overkill?

For a literal typo, a single CSS value, or a config flag flip, the fastest path is to just make the edit and commit — you don't even need /fix. Say so: "This is a one-character change; I can just make the edit and you commit it, or I can open a tracked PR via /fix. Which do you want?" Respect that sometimes the right amount of process is none.

Step 2 — Understand the change

If given a bug (description or JIRA/Linear link), fetch it and understand: the repro steps, the expected vs actual behavior, and the likely location. If given a change description, just understand the intent.

Locate the relevant code (Grep/Glob/Read, or GitHub MCP). Confirm the root cause before fixing — a fix for the wrong cause is worse than no fix.

Step 3 — Resolve the stack (same as the Implementer)

Read the full file on GitHub · 140 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. 4d ago First seen · 140 lines · 87 tokens per session scan A d2032d09e747

Subscribe to this mod's changes

quick-fix is a skill published in the GitHub repository iampawan/Manifest (5 stars, last pushed 2d ago), licensed MIT. It adds 87 tokens to every session and 1,288 once invoked, about $0.0004 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 2026-08-31.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

brainstorming

You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.

obra/superpowers · 37 tokens

auto-perf-optimize

Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.

microsoft/vscode · 62 tokens

chat-perf

Run chat perf benchmarks and memory leak checks against the local dev build or any published VS Code version. Use when investigating chat rendering regressions, validating perf-sensitive changes to chat UI, or checking for memory leaks in the chat response pipeline.

microsoft/vscode · 51 tokens

chat-pet-sprite-creation

Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.

microsoft/vscode · 53 tokens

cpu-profile-analysis

Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…

microsoft/vscode · 71 tokens