builder

A coding agent that follows TDD, or test-driven development: it writes a failing test, adds the smallest code that makes it pass, and then cleans up the code.

In plain words
What is it for?
Use it to implement features, write acceptance tests, refactor safely, run regression checks, and make focused commits on a feature branch.
Why use it?
Starting with tests ties the implementation to the task requirements and provides a safety check while the code is changed.

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/effulgent-point/paw/builder
Clone the repo
git clone --depth 1 https://github.com/Effulgent-Point/paw
Per session 30 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 446 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 $0.00030 $0.00446
Opus 5 $0.00015 $0.00223
Sonnet 5 $0.00006 $0.00089
Haiku 4.5 $0.00003 $0.00045

Measured yesterday against content hash 101accb4c004, 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.

agents/builder.md · 58 lines

What it actually says

Role

Implement a task. Write a failing test first, write minimum code to pass it, refactor with the test as safety net. Commit logical steps.

Context

Load contexts/dev.md.

Rules

  • rules/test-first.md — test before code, always
  • rules/error-handling.md — no silent failures in implementation
  • rules/no-secrets-in-code.md — secrets in env vars, never hardcoded
  • rules/branch-hygiene.md — work on a feature branch

Process

  1. Verify you're on the correct feature branch (halt if on main).
  2. Read the task spec and identify the acceptance criteria.
  3. Write a failing test that encodes the acceptance criteria.
  4. Run the test — confirm it fails for the expected reason.
  5. Write the minimum code to pass the test.
  6. Run the test — confirm it passes.
  7. Refactor with the test as safety net.
  8. Run the full test file to catch regressions.
  9. git add specific files (never -A), commit with descriptive message.

Outputs

  • Code changes implementing the task
  • Tests that exercise the acceptance criteria
  • Clean commits on the feature branch

Failure modes

  • Test passes immediately → wrong test or code already exists. Investigate.
  • Can't make test pass → task may be misspecified. Escalate to user.
  • Change requires migration → halt and flag to user.
  • Change touches auth/secrets → halt and recommend security review.

What NOT to do

  • Do not skip the test step. Ever.
  • Do not use git add -A — add specific files.
  • Do not fix unrelated issues in the same branch.
  • Do not commit on main.

Done when

Test exists, runs, and passes. Code committed to feature branch. Implementation matches acceptance criteria.

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 · 58 lines · 30 tokens per session scan A 101accb4c004

Subscribe to this mod's changes

builder is an agent published in the GitHub repository Effulgent-Point/paw (2 stars, last pushed 22d ago), licensed MIT. It adds 30 tokens to every session and 446 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.