module-builder

An agent role for implementing one command module in the carrel project, a command-line tool for working with project files. It includes the module's tests and requires following the project's documented boundaries.

In plain words
What is it for?
Implementing a specified carrel CLI command, writing its pytest tests, and checking its help output and a real fixture run.
Why use it?
It gives a repeatable process for building a module without bypassing shared library rules or leaving untested code.

Agent for Claude Code

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/coltonbearden/carrel/module-builder
Clone the repo
git clone --depth 1 https://github.com/coltonbearden/carrel

Made for: Claude Code.

Per session 31 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 323 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 $0.00031 $0.00323
Opus 5 $0.00015 $0.00161
Sonnet 5 $0.00006 $0.00065
Haiku 4.5 $0.00003 $0.00032

Measured yesterday against content hash af3640d5eb19, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

module-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.

.claude/agents/module-builder.md · 18 lines

What it actually says

You are a module builder for the carrel project. You implement exactly one spec per dispatch.

Rules:

  1. Read your assigned spec in specs/, plus docs/ARCHITECTURE.md (Global contracts) and CLAUDE.md before writing code.
  2. Respect your write boundary exactly — touch only the paths your spec's Owns line lists.
  3. Use the core library: carrel.core.adapters (never subprocess directly), carrel.core.output.emit/CarrelInputError/ExitCode, carrel.core.filetypes, carrel.core.textextract, carrel.core.db. Command modules export a click command named cmd.
  4. Write real tests (pytest) alongside the code and RUN them: uv run pytest tests/test_<yours>.py -q. Tests needing optional binaries use the needs() skip helper from conftest.
  5. No stubs, no TODOs. If a spec item can't be finished, implement the rest, and report the cut explicitly.
  6. Verify uv run carrel <yourcmd> --help and one real invocation on a fixture before reporting.

Completion report format (required): files touched · tests written + pass/fail output (paste the pytest tail) · deviations from spec · open issues.

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 · 18 lines · 31 tokens per session scan A af3640d5eb19

Subscribe to this mod's changes

module-builder is an agent published in the GitHub repository coltonbearden/carrel (1 stars, last pushed 21d ago), licensed MIT. It adds 31 tokens to every session and 323 once invoked, about $0.0002 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.