agentmods.dev

brat-implementation

brat-implementation is a skill for Claude Code, Codex from neul-labs/brat. It costs 27 tokens per session (467 once invoked), scanned A, original, MIT.

An implementation workflow that divides an architecture into components and builds them in parallel using TDD, a method of writing tests before the code.

In plain words
What is it for?
Use it to assign components to coding engines, write unit and integration tests, implement the code, and record test checkpoints.
Why use it?
It provides a defined path from system design to tested code and lets separate work areas handle different components.

Skill for Claude CodeCodex

Which agent this was written for is unclear — built for aider. Also seen: mentions Codex; built for aider.

not rated 6repo 4mo ago A scan 27 tokens original MIT

Good fit Use it to assign components to coding engines, write unit and integration tests, implement the code, and record test checkpoints.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/neul-labs/brat/brat-implementation
View source ↗ neul-labs/brat brat.neullabs.com
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.

Any agent
npx skills add neul-labs/brat --skill brat-implementation
Clone the repo
git clone --depth 1 https://github.com/neul-labs/brat

Made for: Claude Code, Codex.

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 brat-implementation

README.md
[![agentmods](https://agentmods.dev/badge/skills/neul-labs/brat/brat-implementation/github.svg)](https://agentmods.dev/skills/neul-labs/brat/brat-implementation)
Your own site
<a href="https://agentmods.dev/skills/neul-labs/brat/brat-implementation"><img src="https://agentmods.dev/badge/skills/neul-labs/brat/brat-implementation/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 brat-implementation

Your own site · 80×15
<a href="https://agentmods.dev/skills/neul-labs/brat/brat-implementation"><img src="https://agentmods.dev/badge/skills/neul-labs/brat/brat-implementation.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 27 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 467 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. 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 $0.00027 $0.00467
Opus 5.5 $0.00011 $0.00187
Sonnet 5.5 $0.00005 $0.00093
Haiku 4.5 $0.00003 $0.00047

Measured 2mo ago against content hash e3c28b788886, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

brat-implementation 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 2mo 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.

crates/brat-skills/skills/brat-implementation/SKILL.md · 81 lines

What it actually says

brat-implementation Skill

Purpose

Read architecture design and implement components in parallel using TDD. Write tests first, then implementation.

Input Schema (JSON)

{
  "architecture": {
    "components": [
      {
        "name": "string",
        "responsibility": "string",
        "interfaces": ["string"],
        "dependencies": ["string"],
        "file_paths": ["string"]
      }
    ],
    "test_strategy": {
      "unit_tests": ["string"],
      "integration_tests": ["string"]
    }
  },
  "swimlane": {
    "lane_id": "string",
    "engine": "claude|codex|aider",
    "worktree": "string"
  },
  "assigned_component": {
    "name": "string",
    "file_paths": ["string"]
  }
}

Output Schema (JSON)

{
  "implemented_files": [
    {
      "path": "string",
      "description": "string",
      "tests_passing": "boolean"
    }
  ],
  "tests_written": [
    {
      "path": "string",
      "test_type": "unit|integration",
      "status": "passing|failing"
    }
  ],
  "checkpoints": [
    {
      "timestamp": "string (ISO 8601)",
      "milestone": "string",
      "tests_run": "string (command + result)"
    }
  ],
  "memory": "string (findings to store in KB)",
  "state": "completed|blocked|failed"
}

Guardrails

  • ALWAYS write tests BEFORE implementation code
  • Run tests after every milestone
  • Post checkpoint comments with test results
  • Acquire path: locks before editing files
  • If blocked, post blocker comment and set state=blocked
  • On completion, write memory note with findings
  • NEVER modify architecture notes during implementation
  • NEVER skip tests
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. 2mo ago First seen · 81 lines · 0 tokens per session scan A e3c28b788886

Subscribe to this mod's changes

brat-implementation is a skill published in the GitHub repository neul-labs/brat (6 stars, last pushed 4mo ago), licensed MIT. It adds 27 tokens to every session and 467 once invoked, about $0.0001 per session on Opus 5.5. 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.

Claude CodePlanningTDDTesting[brat, implementation, tdd, swimlanes]agent-swarmai-agentsautomationopencode
Related

brat-implementation compared with skills from other repositories

brat-implementation next to 6 skills from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
brat-implementationneul-labs/bratSkill64mo agoMITA27Claude Code, Codex
sddYeachan-Heo/oh-my-claudecodeSkill41ktodayMITA34Claude Code
tddYeachan-Heo/oh-my-claudecodeSkill41ktodayMITA43Claude Code
cmux-testingmanaflow-ai/cmuxSkill29ktodaynoneA37Codex
tdd-ask-helpGulajavaMinistudio/awesome-copilot-idSkill9417d agoMITA39Claude Code, Codex
tdd-explore-ideasGulajavaMinistudio/awesome-copilot-idSkill9417d agoMITA32Claude Code, Codex
tdd-retroGulajavaMinistudio/awesome-copilot-idSkill9417d agoMITA34Claude Code, Codex