agentmods.dev

build-agent: Instructions file for Claude Code

CLAUDE.md

build-agent CLAUDE.md is an instructions file for Claude Code from duyet/build-agent. It costs 312 tokens per session, scanned A, original, MIT.

A set of instructions for maintaining the build-agent package, including its main skill, adapters, references, and validation process.

In plain words
What is it for?
Use it when editing build-agent behavior or reference files, checking its Claude and Codex adapters, or validating the skill and its triggering.
Why use it?
It identifies which file is the authoritative source and helps prevent duplicated or outdated instructions in the package.

Instructions file for Claude Code

Written for Claude Code: the file is CLAUDE.md. Also seen: mentions .claude-plugin; mentions CLAUDE.md; mentions Claude Code.

This is duyet/build-agent's own configuration. It tells Claude Code how to work on build-agent itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything build-agent configures →

not rated 2repo 28d ago A scan 312 tokens original MIT
View source ↗ duyet/build-agent
Reuse

Borrowing it

Nothing to install: this file belongs to duyet/build-agent. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/duyet/build-agent/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/duyet/build-agent

Made for: Claude Code.

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 build-agent CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/duyet/build-agent/claude-md/github.svg)](https://agentmods.dev/instructions/duyet/build-agent/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/duyet/build-agent/claude-md"><img src="https://agentmods.dev/badge/instructions/duyet/build-agent/claude-md/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for build-agent CLAUDE.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/duyet/build-agent/claude-md"><img src="https://agentmods.dev/badge/instructions/duyet/build-agent/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 312 This file is loaded in full into every session.
When invoked 312 The same file — it is already loaded in full.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.00312 $0.00312
Opus 5.5 $0.00125 $0.00125
Sonnet 5.5 $0.00062 $0.00062
Haiku 4.5 $0.00031 $0.00031

Measured 2mo ago against content hash 6cc6e5152820, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

build-agent CLAUDE.md 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 2mo 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.md · 27 lines

What it actually says

CLAUDE.md

This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.

This repo is content, not an app — no build/test/lint. It packages one Agent Skill (skills/build-agent/) distributed as a Claude plugin (.claude-plugin/plugin.json) and a Codex plugin (codex/).

Single source of truth

skills/build-agent/SKILL.md is canonical. The Codex adapter (codex/AGENTS.md, codex/prompts/build-agent.md) only points at it — never duplicate skill logic there. Change behavior in SKILL.md and the workflows/references, not in the adapters.

Editing the references

skills/build-agent/references/** is deliberately thin: glossary + live-doc links, to avoid going stale. When editing:

  • Keep framework files to concepts + canonical URLs; don't paste full API docs.
  • If a section starts mirroring real API docs, trim it and link out instead.
  • Treat any code snippet as illustrative; the skill must verify against live docs (Context7 / llms.txt / WebFetch) before generating code.

Validating the skill

Use the skill-creator skill/plugin to lint frontmatter and test triggering: /skill-creator build-agent. The description in SKILL.md is the trigger router — keep it dense with real user phrasings.

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. 2mo ago First seen · 27 lines · 312 tokens per session scan A 6cc6e5152820

Subscribe to this mod's changes

build-agent CLAUDE.md is an instructions file published in the GitHub repository duyet/build-agent (2 stars, last pushed 28d ago), licensed MIT. It adds 312 tokens to every session, about $0.0012 per session on Opus 5.5. 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.

Building agents
Related

build-agent CLAUDE.md compared with instructions from other repositories

build-agent CLAUDE.md next to 6 instructions from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
build-agent CLAUDE.mdduyet/build-agentInstructions file228d agoMITA312Claude Code
vscode buildNext.instructions.mdmicrosoft/vscodeInstructions file195ktodayMITA9,719GitHub Copilot
next.js AGENTS.mdvercel/next.jsInstructions file143ktodayMITA7,461Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscodeInstructions file195ktodayMITA5,516GitHub Copilot
langchain AGENTS.mdlangchain-ai/langchainInstructions file149ktodayMITA4,680Codex, OpenCode
vscode copilot-instructions.mdmicrosoft/vscodeInstructions file195ktodayMITA3,093GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harnessInstructions file275k3d agoMITA4,313Codex, OpenCode