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 HoangNguyen0403/agent-skills-standard --skill brainstorm-featuregit clone --depth 1 https://github.com/HoangNguyen0403/agent-skills-standardWrote 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/hoangnguyen0403/agent-skills-standard/brainstorm-feature)<a href="https://agentmods.dev/skills/hoangnguyen0403/agent-skills-standard/brainstorm-feature"><img src="https://agentmods.dev/badge/skills/hoangnguyen0403/agent-skills-standard/brainstorm-feature/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/hoangnguyen0403/agent-skills-standard/brainstorm-feature"><img src="https://agentmods.dev/badge/skills/hoangnguyen0403/agent-skills-standard/brainstorm-feature.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 2 findings, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Excessive Agency · line 49 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
- medium Excessive Agency · line 56 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
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 | $0.00026 | $0.00955 |
| Opus 5 | $0.00013 | $0.00477 |
| Sonnet 5 | $0.00005 | $0.00191 |
| Haiku 4.5 | $0.00003 | $0.00096 |
Grade A, and why
brainstorm-feature 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 9d 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 — 99 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Brainstorm Feature Skill
[!IMPORTANT] Clarify a rough product or engineering idea into a BRD-lite brief (Why) with measurable business value.
Optional args: slug=, ticket=<id/url>, mode=interactive|autonomous|channel, channel=, auto_continue=true|false, profile=business|hybrid|technical.
Instructions
When the user asks to perform this workflow, execute the following steps:
Brainstorm Feature Workflow (BRD-lite / Why)
Goal: Convert vague intent into a compact BA-owned BRD-lite brief before PM PRD planning or technical design.
Steps
- Gather intent:
- Load baseline BRD section,
common-business-requirements, andcommon-operator-profile. - Infer
operator_profile(business | hybrid | technical) from request phrasing; never ask the operator to self-rate. Carry it in the Handoff Payload. - Draft a provisional brief before asking.
- Capture objective, sponsor, validation owner, stakeholders, users, pain/opportunity, value hypothesis, SMART metric, constraints, glossary, non-goals, and delivery context.
- Load baseline BRD section,
- Explore options:
- List 3 viable approaches.
- Capture benefit, cost, risk, and unknowns for each.
- Include funding/priority rationale.
- Mark one recommended approach.
- Pressure-test:
- Keep BRD solution-free; route functional behavior to PRD/SRS.
- Check security, privacy, accessibility, performance, data, rollout risks, and measurable approval criteria.
- Treat non-critical unknowns as assumptions.
- Split stakeholder asks into candidate
REQ-*placeholders and flag platform, market, permission, and edge-case gaps for PM.
- Decide:
- Ask only true blocking product decisions, max 3 at a time.
- Include a recommended default and 2-3 options for each question.
- Record accepted approach and rejected alternatives.
- Draft defaults before blocking: sponsor/validation owner = the requesting operator; SMART metric drafted from the stated pain (mark
assumed); scope fence drafted from the request with explicit non-goals. - For
operator_profile=business, present all three drafted defaults as one confirm-with-default question round (fits the max-3 rule) instead of blocking outright. - Continue on non-critical assumptions; return BLOCKED only when the operator rejects the drafted defaults, or in autonomous/channel mode with no confirmation channel available.
- Save to
docs/brd/brd-[slug].mdwhen writes are allowed and route toplan-feature.
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.
- 9d ago First seen · 99 lines · 26 tokens per session scan A 0768d0d538b1
brainstorm-feature is a skill published in the GitHub repository HoangNguyen0403/agent-skills-standard (565 stars, last pushed 3d ago), licensed MIT. It adds 26 tokens to every session and 955 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 2026-09-03.
Other skills, from other repositories
intelligence-docs
Keeps the CopilotKit Intelligence landing page in sync when a new Intelligence feature ships or when Intelligence docs are added, renamed, or removed. Use when adding Intelligence capabilities, writing or moving pages under docs/intelligence, editing IntelligenceFeatureCards, or changing…
plan
PM planning workflow that gathers requirements, decomposes them into prioritized tasks, defines API contracts, and produces both a machine-readable plan and a human-readable tracker in docs/plans/.
coordinate-pro
Thorough version of coordinate - high-quality development workflow with 11 review steps out of 17.
coordinate
Coordinate multiple agents for a complex multi-domain project using PM planning, parallel agent spawning, and QA review.
exec-plan
Create, manage, and track execution plans as first-class repository artifacts in docs/exec-plans/.
work
Coordinate multiple agents for a complex multi-domain project using PM planning, parallel agent spawning, and QA review.