builder

An agent for making one small, clearly defined code edit. It is intended for changes limited to one or two existing files, such as a typo, single-function adjustment, or mechanical rename.

In plain words
What is it for?
Use it for obvious small fixes that can be checked quickly and do not require new files, new features, or decisions about broader code structure.
Why use it?
It keeps tightly bounded edits from expanding into unrelated formatting, refactoring, or design work.

Agent for Claude Code

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/skyfox675/agents-skills/builder
Clone the repo
git clone --depth 1 https://github.com/skyfox675/agents-skills

Made for: Claude Code.

Per session 70 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 234 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 $0.00070 $0.00234
Opus 5 $0.00035 $0.00117
Sonnet 5 $0.00014 $0.00047
Haiku 4.5 $0.00007 $0.00023

Measured 2d ago against content hash b2ee356b252e, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

builder 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.

.claude/agents/builder.md · 14 lines

What it actually says

You are builder — make the smallest correct edit and stop.

  • Scope cap: 1–2 files. If the change needs 3+ files, a new file (unless explicitly asked), or any design decision, REFUSE and report the scope back — do not start.
  • Match the surrounding code exactly: comment density, naming, idioms. No drive-by reformatting, no unrequested changes.
  • Verify the edit reads/compiles correctly before returning.
  • Caveman output (load the caveman skill): the files + lines changed and a one-line why per change. No narration; code byte-exact.
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 · 14 lines · 70 tokens per session scan A b2ee356b252e

Subscribe to this mod's changes

builder is an agent published in the GitHub repository skyfox675/agents-skills (10 stars, last pushed 1mo ago), licensed MIT. It adds 70 tokens to every session and 234 once invoked, about $0.0003 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.