agentmods.dev

ai-coding-blueprint: Agent for Claude Code

.claude/agents/builder.md

builder is an agent for Claude Code from ikhanux/ai-coding-blueprint. It costs 62 tokens per session (420 once invoked), scanned A, original, MIT.

A general implementation guide for building one clearly defined piece of application code. It follows the repository's architecture and coding conventions instead of introducing unrelated changes.

In plain words
What is it for?
Use it for a component, function, page, or focused fix when the scope is already clear.
Why use it?
It keeps a coding task focused and reduces accidental refactors, new dependencies, or code that conflicts with project rules. It also requires the project's checks before reporting completion.

Agent for Claude Code

Written for Claude Code: installed under .claude/. Also seen: model in frontmatter; mentions CLAUDE.md.

This is ikhanux/ai-coding-blueprint's own configuration. It tells Claude Code how to work on ai-coding-blueprint 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 ai-coding-blueprint configures →

not rated 2repo 1mo ago A scan 62 tokens original MIT
View source ↗ ikhanux/ai-coding-blueprint
Reuse

Borrowing it

Nothing to install: this file belongs to ikhanux/ai-coding-blueprint. 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/ikhanux/ai-coding-blueprint/main/.claude/agents/builder.md
Clone the repo
git clone --depth 1 https://github.com/ikhanux/ai-coding-blueprint

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 builder

README.md
[![agentmods](https://agentmods.dev/badge/agents/ikhanux/ai-coding-blueprint/builder/github.svg)](https://agentmods.dev/agents/ikhanux/ai-coding-blueprint/builder)
Your own site
<a href="https://agentmods.dev/agents/ikhanux/ai-coding-blueprint/builder"><img src="https://agentmods.dev/badge/agents/ikhanux/ai-coding-blueprint/builder/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 builder

Your own site · 80×15
<a href="https://agentmods.dev/agents/ikhanux/ai-coding-blueprint/builder"><img src="https://agentmods.dev/badge/agents/ikhanux/ai-coding-blueprint/builder.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 62 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 420 The whole file, excluding the scripts and references it only reads on demand.
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 $0.00062 $0.00420
Opus 5.5 $0.00025 $0.00168
Sonnet 5.5 $0.00012 $0.00084
Haiku 4.5 $0.00006 $0.00042

Measured 1mo ago against content hash d4a209bc9e6b, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, 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 1mo 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 · 40 lines

What it actually says

You implement exactly one unit of work in this repo. The brief you were given is the whole task: build that, nothing more.

Before writing

  1. Read CLAUDE.md (Architecture, Conventions, Commands) and skim .ai/PROJECT.md for the terms and global rules that apply.
  2. Read the closest existing example of what you're about to build and follow its pattern. Do not invent a new idiom when one exists.
  3. If the brief conflicts with CLAUDE.md or with "Explicit cuts" in .ai/PROJECT.md, stop and say so instead of building.

While building

  • Only the files the brief names, plus any it clearly requires (e.g. registering a new page in the router). No drive-by refactors, no "while I was here" changes.
  • No new dependencies unless the brief says so.
  • Match the conventions in CLAUDE.md exactly: formatting, import style, naming, where files live.

Before reporting

Run the Check command from CLAUDE.md § Commands, then the Format command if one exists. Fix any failure the Check reports in the code you touched. If a failure is outside your files, report it rather than fixing it.

Report back

  • What was built, and the files created or modified
  • The Check command output, pasted
  • Anything the brief asked for that you did not do, and why
  • Never write "verified", "working" or "done" without the output that proves it
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. 1mo ago First seen · 40 lines · 62 tokens per session scan A d4a209bc9e6b

Subscribe to this mod's changes

builder is an agent published in the GitHub repository ikhanux/ai-coding-blueprint (2 stars, last pushed 1mo ago), licensed MIT. It adds 62 tokens to every session and 420 once invoked, about $0.0002 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 2026-09-21.

Related

builder compared with agents from other repositories

builder next to 6 agents from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
builderikhanux/ai-coding-blueprintAgent21mo agoMITA62Claude Code
playwright-test-generatormicrosoft/playwrightAgent99kyesterdayApache-2.0A151Claude Code
.NET-Notebook-Migration-Agentmicrosoft/ai-agents-for-beginnersAgent79k4d agoMITA33Claude Code
code-revieweranthropics/claude-cookbooksAgent54k2d agoMITA52Claude Code
AVM Owner Triagegithub/awesome-copilotAgent41kyesterdayMITA61Claude Code
Ultimate Transparent Thinking Beast Modegithub/awesome-copilotAgent41kyesterdayMITA11Claude Code
WinForms Expertgithub/awesome-copilotAgent41kyesterdayMITA19Claude Code