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-reviewgit 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-review)<a href="https://agentmods.dev/skills/neul-labs/brat/brat-review"><img src="https://agentmods.dev/badge/skills/neul-labs/brat/brat-review/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.
<a href="https://agentmods.dev/skills/neul-labs/brat/brat-review"><img src="https://agentmods.dev/badge/skills/neul-labs/brat/brat-review.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00023 | $0.00472 |
| Opus 5 | $0.00012 | $0.00236 |
| Sonnet 5 | $0.00005 | $0.00094 |
| Haiku 4.5 | $0.00002 | $0.00047 |
Grade A, and why
brat-review 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 11d 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-review Skill
Purpose
Review completed implementation against architecture design and product requirements. Request human approval before merge.
Input Schema (JSON)
{
"implementation": {
"component": "string",
"files_changed": ["string"],
"diff_summary": "string",
"tests": {
"unit": {"passing": "number", "failing": "number"},
"integration": {"passing": "number", "failing": "number"}
}
},
"architecture": {
"component": "string",
"expected_interfaces": ["string"],
"expected_file_paths": ["string"]
},
"product": {
"requirement_title": "string",
"acceptance_criteria": ["string"]
},
"policy": {
"require_human_approval": "boolean",
"required_checks": ["string"]
}
}
Output Schema (JSON)
{
"decision": "approve|request_changes|reject|escalate",
"assessment": {
"architecture_compliance": "compliant|partial|non_compliant",
"test_coverage": "adequate|partial|inadequate",
"acceptance_criteria_met": "all|partial|none"
},
"approval_request": {
"rationale": "string (why this needs human eyes)",
"artifact_summary": "string (what changed)",
"risk_level": "low|medium|high",
"suggested_reviewers": ["string"]
},
"required_changes": ["string (if decision=request_changes)"],
"reason": "string"
}
Guardrails
- If
require_human_approvalis true, ALWAYS request approval before merge - Check architecture compliance before approval
- Check all acceptance criteria are met
- Tests must be passing (zero failures)
- On rejection, provide specific required changes
- Post review assessment as structured comment
- NEVER merge without approval when policy requires it
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.
- 11d ago First seen · 69 lines · 0 tokens per session scan A 5e5fbddcb537
brat-review is a skill published in the GitHub repository neul-labs/brat (5 stars, last pushed 2mo ago), licensed MIT. It adds 23 tokens to every session and 472 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…
include-test-files-that-assert-on-behavior-being-changed-in-decl
When delegating a task affected by this skill, include.
critic-gate
Full execution protocol for MODE: CRITIC-GATE -- plan critic review, revision loops, and hard stop before execution.
deep-dive
Full execution protocol for MODE: DEEPDIVE — read-only codebase audit with parallel explorer waves, 2 independent reviewers, and sequential critic challenge for HIGH/CRITICAL findings. Loaded on demand by the architect when the deep-dive command emits a [MODE: DEEPDIVE ...] signal.
swarm-pr-feedback
Codex adapter for closing known PR feedback in any repository. Use when asked to address pasted review feedback, GitHub review comments or threads, requested changes, CI/check failures, merge conflicts, stale PR branches, or follow-up work that must verify and close all known PR issues.
codebase-review-swarm
Codex adapter for running a rigorous, quote-grounded codebase review or security/QA/accessibility/performance/AI-slop/enhancement audit. Use for full-repo or large-subsystem review reports; not for normal implementation.