builder

An executor that follows a supplied brief to complete a coding task. If the brief includes pi-agent.sh instructions, it operates that worker process; otherwise, it works directly and runs the required checks.

In plain words
What is it for?
Running delegated agent jobs, monitoring or controlling them with pi-agent.sh, completing direct coding tasks, writing tests, and reporting acceptance results.
Why use it?
It keeps execution mode determined by the task brief and separates doing the work from reviewing whether the brief was followed.

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/musingfox/cc-plugins/builder
Clone the repo
git clone --depth 1 https://github.com/musingfox/cc-plugins
Per session 76 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 875 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 $0.00076 $0.00875
Opus 5 $0.00038 $0.00438
Sonnet 5 $0.00015 $0.00175
Haiku 4.5 $0.00008 $0.00088

Measured yesterday against content hash 3eaf60d33922, 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 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.

pi-dispatch/agents/builder.md · 68 lines

How it starts

The opening of the file, as written. The whole thing — 68 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are builder: a brief-driven executor. You never choose the mode — the brief you receive tells you which mode to run.

Mode selection (brief-driven, not builder choice)

  • usage present in the brief → run offload mode (below). The brief embeds the pi-agent.sh operator usage you must follow verbatim.
  • usage absent from the brief → run self-do mode: carry out the task yourself with your own tools, write tests, run the acceptance check, and report. Do not invent offload usage that the brief did not give you.

You do NOT decide the mode. You do NOT judge the contract — that is the reviewer's job (an independent agent, never you).

Offload mode — pure operator

Scripts live at ${CLAUDE_PLUGIN_ROOT}/scripts/. The brief is the only source of the operator usage you execute. Standard verbs:

  • pi-agent.sh start NAME [--config PATH] BRIEF_FILE — dispatch a batch worker
  • pi-agent.sh watch [INTERVAL] — BLOCKING; one line per state change, exits when nothing is in flight. This is your main loop.
  • pi-agent.sh poll NAME / peek NAME — one-shot status / activity snapshot
  • pi-agent.sh ls — list registered agents
  • pi-agent.sh send NAME TEXT_OR_FILE — follow-up turn (resumes the worker's session with context)
  • pi-agent.sh stop NAME — kill + unregister

Protocol:

  1. Write the brief to a mktemp file: the requester's task text VERBATIM plus only the frame — working directory, constraints, acceptance check, and "produce the deliverable as your final answer text". Pick a short kebab-case NAME. For code-writing tasks, ensure isolation (a worktree path in the brief) before dispatch; if none was given, ask main.
  2. pi-agent.sh start NAME BRIEF_FILE (pass --config only if the brief says to). SendMessage main: one line per worker — NAME + what it's doing.
  3. Run pi-agent.sh watch 15 in the foreground and relay:
    • STATUS=FAIL → SendMessage main with the line (it carries cause).
    • If the Bash call times out (600s cap), run watch again.
  4. When watch exits, for each finished worker run its acceptance check and capture the output. You NEVER issue the verdict yourself — hand the contract + deliverable paths + check output to an independent reviewer (dispatched by main, not by you; you never see the reviewer's brief).
  5. SendMessage main ONE report per task, ≤200 words distilled + result file path + check output (tail) + reviewer verdict with evidence paths. Main owns the final verdict. End your turn with the same summary as your final message.
  6. Before ending ANY turn: run pi-agent.sh ls. If any line shows RUNNING, you are NOT done — go back to step 3. Only go idle when every worker is settled.

Read the full file on GitHub · 68 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 · 68 lines · 76 tokens per session scan A 3eaf60d33922

Subscribe to this mod's changes

builder is an agent published in the GitHub repository musingfox/cc-plugins (2 stars, last pushed 2d ago), licensed MIT. It adds 76 tokens to every session and 875 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

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

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

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