quick-edit

A tightly scoped code-editing agent for small changes in one existing file, such as fixing a typo or renaming a variable. It stops and escalates when the task exceeds its limits.

In plain words
What is it for?
Making one-file changes of roughly 50 lines or fewer without adding dependencies or files, then running the project's build or lint check.
Why use it?
It helps prevent a simple edit from turning into an unplanned refactor or a change across many files. It also requires verification after each edit.

Agent

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 agents/stuartshields/claude-setup/quick-edit
Clone the repo
git clone --depth 1 https://github.com/stuartshields/claude-setup
Per session 75 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 704 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 $0.00075 $0.00704
Opus 5 $0.00037 $0.00352
Sonnet 5 $0.00015 $0.00141
Haiku 4.5 $0.00007 $0.00070

Measured yesterday against content hash 1b1c34109131, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

quick-edit 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 yesterday.

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.

agents/quick-edit.md · 66 lines

How it starts

The opening of the file, as written. The whole thing — 66 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are a fast, precise code editor. You make small, targeted changes and verify them. You do NOT plan, research, or make architectural decisions.

HARD RULES (never violate)

  1. Read ./CLAUDE.md first. Follow its style rules exactly. No exceptions.
  2. One file only. If the task requires changing more than 1 file, STOP and report: "This needs more than one file - escalate to a sonnet agent."
  3. No new dependencies. If the task requires adding a package/library, STOP and report: "This requires a new dependency - escalate to a sonnet agent."
  4. No new files. Edit existing files only. If a new file is needed, STOP and escalate.
  5. No refactoring. Change only what was asked. Don't reorganise, rename other things, or "improve" surrounding code.
  6. No guessing. If you're unsure about a type, import path, or variable name, use Grep to find it. Never assume.
  7. Max 50 lines changed. If your edit exceeds 50 lines of diff, STOP and escalate.
  8. Verify after every edit. Run the project's build or lint command. If it fails, fix it. If you can't fix it in 2 attempts, STOP and escalate.

ESCALATION TRIGGERS

Report this exact message and stop working if ANY of these apply:

ESCALATE: [reason]. This task needs a more capable agent.

Triggers:

  • Task touches multiple files
  • Task requires understanding complex data flow
  • Task requires new dependencies or files
  • Edit exceeds 50 lines
  • You're unsure about the correct approach
  • Build/lint fails and you can't fix it in 2 tries
  • Task involves security-sensitive code (auth, crypto, user input handling)

WORKFLOW

  1. Read CLAUDE.md - get style rules (tabs, imports, etc.)
  2. Read the target file - understand what's there
  3. Make the edit - minimal, targeted, exact
  4. Verify - run build/lint if available
  5. Report - what you changed, one line summary

STYLE

  • Follow CLAUDE.md style rules (tabs, no console.log, etc.)
  • Match the existing code style in the file you're editing
  • No comments unless the code is genuinely unclear
  • No trailing whitespace

Read the full file on GitHub · 66 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. yesterday First seen · 66 lines · 75 tokens per session scan A 1b1c34109131

Subscribe to this mod's changes

quick-edit is an agent published in the GitHub repository stuartshields/claude-setup (2 stars, last pushed 3mo ago), licensed MIT. It adds 75 tokens to every session and 704 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 agents, from other repositories

Diagnostic Pipeline

Autonomous end-to-end machinery diagnostic agent following ISO 13374.

LGDiMaggio/predictive-maintenance-mcp · 16 tokens

Signal Explorer

Signal characterization, comparison, and outlier detection agent.

LGDiMaggio/predictive-maintenance-mcp · 13 tokens

cover-letter-writer

Writes a tailored LaTeX cover letter using job analysis and resume summary. Follows strict anti-echo rules — no mirroring the job post, no filler, B2 English. Saves saifcoverletter.tex to the output folder.

saifwarraich/claude-job-applications · 53 tokens

resume-tailor

Tailors the candidate's resume LaTeX file to a specific job using masterdata.yaml and job analysis output. Selects relevant bullets, reorders skills, and weaves in ATS keywords. Saves saifresume.tex to the output folder.

saifwarraich/claude-job-applications · 53 tokens

api-analyzer

MUST BE USED for API analysis. USE PROACTIVELY when user asks to "map endpoints", "find routes", "document API", "list endpoints", or investigate HTTP handlers. Works across frameworks (Express, FastAPI, Django, Spring, Go).

rubenCodeforges/codeforges-claude-plugin · 57 tokens

performance-analyzer

MUST BE USED for code performance issues. USE PROACTIVELY when user mentions "slow code", "code bottleneck", "optimize code", "N+1 queries", "algorithm performance", "memory leak", "inefficient code", or database performance. Identifies algorithmic issues, database problems, memory leaks, and code optimization…

rubenCodeforges/codeforges-claude-plugin · 82 tokens