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/friedbotstudio/baseline/brdnpx skills add friedbotstudio/baseline --skill brdgit clone --depth 1 https://github.com/friedbotstudio/baselineWhat 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 | $0.00064 | $0.00729 |
| Opus 5 | $0.00032 | $0.00365 |
| Sonnet 5 | $0.00013 | $0.00146 |
| Haiku 4.5 | $0.00006 | $0.00073 |
Grade A, and why
brd 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 2d 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.
How it starts
The opening of the file, as written. The whole thing — 46 lines — stays where its author put it; the contents beside it link to each section on GitHub.
BRD — Business Requirements Document
You are drafting a BRD. BRDs are heavier than intakes — they exist when a request needs explicit sign-off from named business stakeholders, and when the why and the what must survive independently of the how (the spec).
Use a BRD when:
- Multiple teams or external stakeholders need to align.
- Regulatory, legal, or compliance concerns shape the requirements.
- Business milestones or contractual dates are tied to the work.
- Budget or headcount implications warrant an approved scope.
Don't use a BRD for: single-team feature work, quickfixes, or internal refactors. Those need an intake + spec, nothing more.
Prerequisite
Either /intake has completed (there's a corresponding docs/intake/<slug>.md), OR the user is starting directly at BRD because the intake exists upstream (e.g., in Linear/Jira) and they want to formalize it here.
Inputs
- The intake document (if any) — it supplies Problem and Goal.
- The user's additional context about stakeholders, timelines, and compliance.
template.mdin this skill directory.
Steps
- If a corresponding intake exists at
docs/intake/<slug>.md, read it. Map Problem → Business objective and Goal → Executive summary. - Read
template.md. Every heading must appear in the output. - For each section, write content that answers the questions in the template comments. If unknown, list the gap under Open questions — never fabricate stakeholder names, dates, or dollar amounts.
- Name every requirement with an ID:
BR-001,BR-002, … for business reqs;FR-001, … for functional;NFR-001, … for non-functional. Downstream spec AC will reference these IDs. - Write to
docs/brd/<slug>.md(same slug as the intake, if one exists). - Tell the user: "BRD drafted at
docs/brd/<slug>.md. Sign-offs required from: . Open questions: N. Next:/scout(or get sign-offs first if you want to freeze scope)."
Drafting rules
- Requirements are testable, not aspirational. "The system shall support peak traffic" is aspirational. "The system shall sustain 500 RPS with P95 < 200ms" is testable.
- Separate business from functional from non-functional. A mixed list becomes unactionable.
- Risks must have owners. "Risk: the vendor API could change" with no owner is noise. Either name who monitors it or delete it.
- Sign-offs are names, not titles. "Head of Compliance" can't sign — their replacement, who is a specific person, can.
- Do not write the solution. The BRD says what must be true; the spec says how. If you catch yourself writing "we'll use Kafka", stop — that belongs in
/spec.
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 2d ago First seen · 46 lines · 64 tokens per session scan A 5b2ab80180f7
brd is a skill published in the GitHub repository friedbotstudio/baseline (11 stars, last pushed 6d ago), licensed Apache-2.0. It adds 64 tokens to every session and 729 once invoked, about $0.0003 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 2026-08-30.
Other skills, from other repositories
dev-standards
Enforces development workflows, quality gates, coding standards, and release processes for the deterministic-agent-control-protocol project. Use when implementing features, fixing bugs, refactoring architecture, adding integrations, updating policies, writing tests, updating documentation, or preparing releases.
code-review-with-lsp
Code review with LSP-powered code intelligence. Uses MCP tools (diagnostics, hover, references, definition, symbols) for semantic code understanding, not just text grep.
i18n-check
国际化完整性检查。检查翻译 key 是否缺失、硬编码文本、locale 文件一致性。.
vue-best-practices
Vue 2/3 代码规范检查。包括组件命名、Props 校验、Composition API 规范等。.
python-review
Python 遗留代码审查：bare except、SQL 注入、反序列化、密钥、调试输出.
rust-review
Rust 服务审查：panic、SQL 注入、密钥、错误吞没、遗留标记.