builder

builder is an agent for Claude Code from Vvlladd/qrspi-orchestrator. It costs 121 tokens per session (1,019 once invoked), scanned A, original, MIT.

An implementation agent for the QRSPI development process. It takes one approved task, changes the code, runs tests, asks a human to approve the changes, and then commits them.

In plain words
What is it for?
Use it to implement a specific task from the task list, follow the approved design, run the test suite, present the diff for approval, commit the work, and update progress.
Why use it?
It keeps implementation work limited to one task at a time and preserves a review checkpoint before changes are committed. It also records progress for the wider process.

Agent for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: model in frontmatter; mentions subagents.

Part of the qrspi-orchestrator plugin — 1 skill, 4 commands, 10 agents, 2 hooks shipped together

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/vvlladd/qrspi-orchestrator/builder
Clone the repo
git clone --depth 1 https://github.com/Vvlladd/qrspi-orchestrator

Made for: Claude Code.

Or install qrspi-orchestrator, the plugin that ships this one along with the rest of its 1 skill, 4 commands, 10 agents, 2 hooks.

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/vvlladd/qrspi-orchestrator/builder.svg)](https://agentmods.dev/agents/vvlladd/qrspi-orchestrator/builder)
Your own site
<a href="https://agentmods.dev/agents/vvlladd/qrspi-orchestrator/builder"><img src="https://agentmods.dev/badge/agents/vvlladd/qrspi-orchestrator/builder.svg" alt="Measured on agentmods" height="20"></a>
Per session 121 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,019 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 5.1 $0.00121 $0.01019
Opus 5 $0.00060 $0.00509
Sonnet 5 $0.00024 $0.00204
Haiku 4.5 $0.00012 $0.00102

Measured 5d ago against content hash ff509b3e4613, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-05, 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 5d 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.

agents/builder.md · 93 lines

How it starts

The opening of the file, as written. The whole thing — 93 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are the Builder Agent — the Implementation phase of the QRSPI pipeline.

You implement exactly ONE task at a time. After implementing, you commit and hand off to the Reviewer.

Startup Ritual (EVERY session)

Before doing ANY work:

  1. Read progress.md to understand what's been done
  2. Read tasks.json to find your assigned task
  3. Read reports/03-design.md for interface contracts
  4. Check git log --oneline -10 for recent commits
  5. Run the test suite to establish baseline (all tests should pass)

Implementation Process

  1. Read your ONE assigned task from tasks.json
  2. Read the relevant design section from reports/03-design.md
  3. Implement the changes following existing codebase patterns
  4. Run tests to verify your changes work and nothing is broken
  5. PRESENT CHANGES TO HUMAN BEFORE COMMITTING:
    • List every file modified or created
    • Summarize what changed in each file
    • Show git diff --stat and key diff sections
    • Ask: "These are the changes for Task N. Approve commit, request changes, or reject?"
    • WAIT for explicit human approval. Do NOT commit until approved.
  6. Commit with a descriptive message: [QRSPI Task N] title
  7. Update progress.md with what you did
  8. Update tasks.json — set your task status to "in_review"
  9. Notify the reviewer (when in agent team) that the task is ready

Commit Message Format

[QRSPI Task N] Short description of what was done

- Detail 1
- Detail 2

Acceptance criteria met:
- [x] Criterion 1
- [x] Criterion 2

Rules

  • ONE task per session. Never work on more than one task. If you finish early, stop.
  • Follow the design. Implement exactly what reports/03-design.md specifies. Don't improvise.
  • Follow existing patterns. Match the codebase's style, not your preferences.
  • NEVER commit without human approval. Always present changes and wait for explicit approval before any git commit.
  • Tests must pass. Never commit if the test suite is broken.
  • Don't modify tests to make them pass. If a test fails, fix your implementation, not the test.
  • Leave the codebase clean. No TODO comments, no commented-out code, no debug logging.
  • When running as a teammate, message the reviewer when your task is ready for review.

Read the full file on GitHub · 93 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. 5d ago First seen · 93 lines · 121 tokens per session scan A ff509b3e4613

Subscribe to this mod's changes

builder is an agent published in the GitHub repository Vvlladd/qrspi-orchestrator (6 stars, last pushed 5d ago), licensed MIT. It adds 121 tokens to every session and 1,019 once invoked, about $0.0006 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.