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.
npx agentmods add skills/neul-labs/brat/brat-implementationnpx skills add neul-labs/brat --skill brat-implementationgit clone --depth 1 https://github.com/neul-labs/bratWrote 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.
[](https://agentmods.dev/skills/neul-labs/brat/brat-implementation)<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="Measured on agentmods" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00027 | $0.00467 |
| Opus 5 | $0.00014 | $0.00234 |
| Sonnet 5 | $0.00005 | $0.00093 |
| Haiku 4.5 | $0.00003 | $0.00047 |
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 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.
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
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.
- 5d ago First seen · 81 lines · 0 tokens per session scan A e3c28b788886
brat-implementation is a skill published in the GitHub repository neul-labs/brat (5 stars, last pushed 2mo ago), licensed MIT. It adds 27 tokens to every session and 467 once invoked, about $0.0001 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.
Other skills, from other repositories
cmux-testing
A regression test for a bug fix ships as two commits so CI proves the test catches the bug.
tdd-ask-help
Interactive AI Guide and Navigator for the TDD-Spec SDLC ecosystem. Diagnoses current project phase, recommends next actions, routes scenarios, and explains skill purposes.
tdd-explore-ideas
Systematic codebase exploration, architectural critique, and 5-step Idea Assessment with TDD hypothesis verification for Phase 0.
tdd-pair-coach
Interactive AI Pair Programming & TDD Mentor that guides developers step-by-step through the Red-Green-Refactor cycle and plan execution without writing the final code for them.
tdd-retro
Conducts comprehensive session & phase retrospectives to optimize test runner speed, eliminate flaky tests, update project memory, and continuously improve SDLC velocity.
gem-devops-guidelines
Design or review infrastructure, deployment, CI/CD, Docker, Kubernetes, health checks, rollback, feature flags, production readiness, and mobile release workflows. Use for DevOps, platform, container, pipeline, or release tasks.