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 skills add neul-labs/brat --skill brat-bootstrapgit 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-bootstrap)<a href="https://agentmods.dev/skills/neul-labs/brat/brat-bootstrap"><img src="https://agentmods.dev/badge/skills/neul-labs/brat/brat-bootstrap.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 5.1 | $0.00027 | $0.00434 |
| Opus 5 | $0.00014 | $0.00217 |
| Sonnet 5 | $0.00005 | $0.00087 |
| Haiku 4.5 | $0.00003 | $0.00043 |
Grade A, and why
brat-bootstrap 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 8d 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-bootstrap Skill
Purpose
Analyze user intent and produce structured product requirements stored in the zkb product knowledge base.
Input Schema (JSON)
{
"codebase_scan": {
"files": [{"path": "string", "language": "string", "exports": ["string"]}],
"readme": "string",
"docs": ["string"],
"entry_points": ["string"],
"dependencies": ["string"],
"test_files": ["string"]
},
"existing_kb": {
"product_notes": [{"title": "string", "body": "string"}],
"arch_notes": [{"title": "string", "body": "string"}]
}
}
Output Schema (JSON)
{
"product_notes": [{"title": "string", "body": "string", "tags": ["string"]}],
"architecture_notes": [{"title": "string", "body": "string", "tags": ["string"]}],
"consistency_score": "number (0-100)",
"inconsistencies": [
{
"kind": "MissingArchitecture|OrphanComponent|MissingTests|MissingDocs|Mismatch",
"severity": "low|medium|high",
"description": "string",
"suggested_fix": "string"
}
],
"notes_to_create": [{"title": "string", "body": "string", "type": "permanent|structure"}]
}
Guardrails
- ALWAYS scan all source files
- NEVER skip README or docs
- Link every product note to at least one architecture note
- Link every architecture note to at least one product note
- Flag inconsistencies, don't hide them
- Iterate up to 5 times, then surface remaining to human
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.
- 8d ago First seen · 56 lines · 0 tokens per session scan A b8573a10c8df
brat-bootstrap 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 434 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
swarm-pr-review
Run a graph-guided, tool-augmented PR review using context packing, parallel exploration, mandatory repository-agnostic risk-family coverage with dispatch scaled to diff size and risk, independent reviewer validation, critic challenge, and metrics writeback. Use for deep pull request review with low false-positive…
workflow
Use when a task is too large for turn-by-turn orchestration and should run through the big-task workflow lane: system-wide changes, large migrations, repo-wide audits, high-confidence verification, or tasks explicitly asking to run a workflow. Claude Code uses native dynamic workflows; Codex, OpenCode, and Grok use…
swarm-plan
Full execution protocol for MODE: PLAN -- plan creation, external plan ingestion, QA gate persistence, task granularity, and traceability checks.
loop
Full execution protocol for MODE: LOOP — the compound-engineering loop: brainstorm → plan → build → review → improve, iterating under defense-in-depth stop conditions with generator/critic separation, durable resumable state, and mandatory compounding learning capture. Loaded on demand by the architect when the loop…
subprocess-safety
Guidelines for safe subprocess calls in opencode-swarm. Load before adding, modifying, or reviewing any file that calls spawn, spawnSync, bunSpawn, or childprocess. Covers the six required properties, Windows portability, internals DI seam pattern, and verification grep.
council
Full execution protocol for MODE: COUNCIL -- General Council research, parallel member dispatch, disagreement handling, and synthesis.