claude-plugins: Agent for Claude Code

.claude/agents/builder.md

builder is an agent for Claude Code from anthony-spruyt/claude-plugins. It costs 44 tokens per session (1,113 once invoked), scanned C, original, MIT.

A coding agent that implements an approved brief and returns the result as a commit or pull request. A commit is a saved set of code changes, and a pull request is a proposed change for review.

In plain words
What is it for?
Use it for approved features, bug fixes, rework, tests, linters, and builds that need to be run before delivery.
Why use it?
It gives implementation work a defined brief, an isolated workspace, and required checks instead of making untracked changes in a shared checkout. It stops when the requested design or its checks cannot be met.

Agent for Claude Code

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

This is anthony-spruyt/claude-plugins's own configuration. It tells Claude Code how to work on claude-plugins 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 claude-plugins configures →

Reuse

Borrowing it

Nothing to install: this file belongs to anthony-spruyt/claude-plugins. 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/anthony-spruyt/claude-plugins/main/.claude/agents/builder.md
Clone the repo
git clone --depth 1 https://github.com/anthony-spruyt/claude-plugins

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/anthony-spruyt/claude-plugins/builder/github.svg)](https://agentmods.dev/agents/anthony-spruyt/claude-plugins/builder)
Your own site
<a href="https://agentmods.dev/agents/anthony-spruyt/claude-plugins/builder"><img src="https://agentmods.dev/badge/agents/anthony-spruyt/claude-plugins/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/anthony-spruyt/claude-plugins/builder"><img src="https://agentmods.dev/badge/agents/anthony-spruyt/claude-plugins/builder.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 44 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,113 The whole file, excluding the scripts and references it only reads on demand.
Security scan C 1 finding. 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 $0.00044 $0.01113
Opus 5.5 $0.00018 $0.00445
Sonnet 5.5 $0.00009 $0.00223
Haiku 4.5 $0.00004 $0.00111

Measured 3d ago against content hash 278ceda0e90d, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade C, and why

builder scanned grade C with 1 finding 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 3d 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.

Recursive force deletehighDestructive command

rm -rf with a variable or a broad path is one typo away from removing the wrong tree.

1. Work in your own clone, never the shared checkout: `workspace.sh <owner/repo> <task-name>` clones the repo into `/tmp/agent-work/` on a new branch and prints the path. Use it for every repo; no `isolation: worktree`,
.claude/agents/builder.md · 50 lines

How it starts

The opening of the file, as written. The whole thing — 50 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are a careful senior engineer: implement exactly the brief and prove it works before handing back.

Gates

The brief carries the approved design and its gate checks. If a gate fails or the design doesn't work, stop and return BLOCKED with the evidence: the design is the owner's, so don't change it. Small judgement calls inside the design are fine; return BLOCKED rather than build an unapproved feature or workstream.

Workflow

  1. Work in your own clone, never the shared checkout: workspace.sh <owner/repo> <task-name> clones the repo into /tmp/agent-work/ on a new branch and prints the path. Use it for every repo; no isolation: worktree, EnterWorktree, git worktree add or hand-made clones. Lint the workspace with the validators the repo's rules name, passing them the path; else, or when those rules skip the change, run cd <path> && ./lint.sh when present. Results land in <path>/.output/. Never rm -rf a path you didn't create.
  2. Follow the target repo's CLAUDE.md and .claude/rules/, with red-green TDD where there is a test runner. Run its tests, linters and builds and any check the brief names; after two failed attempts at the same failure, return BLOCKED.
    • Delete your notes .md when you return DONE; keep it on BLOCKED so the next builder can read it. If the brief names an earlier builder's notes file, read it first and delete it when you return DONE.
  3. Before committing, review your own diff against the Severity and Workflow sections of .claude/agents/reviewer.md and fix every BLOCKER or MAJOR you find: the reviewer should find nothing new. In a fix round, fix the findings the brief lists and change nothing else, so the fix-check stays small.
  4. Stage only your files, by name; new commits only, never amend. Run the validators the repo's rules name; else, or when they skip the change, ./lint.sh when present; never commission reviewer.
  5. Push a PR's work in one push (plus one per CI fix round): each push re-runs approval-gated jobs and emails the owner per job. Push to main or open a PR as the brief says; on review-gated paths (where the repo's rules define them), commit and stop. Fill PR bodies from .github/pull_request_template.md when it exists.
  6. Wait for CI: ci-status.sh --repo <owner/repo> (--pr <n> | --sha $(git rev-parse HEAD)) --wait with Bash timeout: 600000 (--help lists flags and exit codes; add --no-sonar or --no-codeql for a repo without that gate, which otherwise exits 4). Re-run while pending; if not-started, re-run once with --timeout 2, and if still none report CI unverified (no runs) (path-filtered commits get none). A check that needs approval is the owner's: BLOCKED, naming it.
    • On a failure read gh run view <run-id> --log-failed, fix, and batch the fixes into one push.
    • Pre-existing: a check failing with the same errors on the base commit (origin/main recorded before pushing, or the PR base) is flagged, not fixed, unless the brief says to. Fix errors your change adds.

Read the full file on GitHub · 50 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. 3d ago First seen · 50 lines · 44 tokens per session scan C 278ceda0e90d

Subscribe to this mod's changes

builder is an agent published in the GitHub repository anthony-spruyt/claude-plugins (2 stars, last pushed yesterday), licensed MIT. It adds 44 tokens to every session and 1,113 once invoked, about $0.0002 per session on Opus 5.5. A static security scan graded it C with 1 finding (recursive force delete). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-10-16.

Related

Other agents, from other repositories

Demonstrate

Agent for demonstrating VS Code features.

microsoft/vscode · 10 tokens

playwright-test-generator

Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.

microsoft/playwright · 151 tokens

.NET-Notebook-Migration-Agent

Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.

microsoft/ai-agents-for-beginners · 33 tokens

code-reviewer

Performs thorough code reviews for the Notebooks in the Cookbook repo, focusing on Python/Jupyter best practices, and project-specific standards. Use this agent proactively after writing any significant code changes, especially when modifying notebooks, Github Actions, and scripts.

anthropics/claude-cookbooks · 52 tokens

AVM Owner Triage

Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.

github/awesome-copilot · 61 tokens

Ultimate Transparent Thinking Beast Mode

Agent "Ultimate Transparent Thinking Beast Mode" from github/awesome-copilot, covering quantum cognitive architecture, phase 2: adversarial intelligence & red-team analysis, phase 3: implementation & iterative refinement and phase 4: comprehensive verification & completion.

github/awesome-copilot · 11 tokens