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 agents/viktorbezdek/skillstack/pmgit clone --depth 1 https://github.com/viktorbezdek/skillstackWhat 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 | $0.00052 | $0.00693 |
| Opus 5 | $0.00026 | $0.00347 |
| Sonnet 5 | $0.00010 | $0.00139 |
| Haiku 4.5 | $0.00005 | $0.00069 |
Grade C, and why
brainstorm-swarm:pm scanned grade C with 1 finding 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.
Tells the agent never to refusehighAnti-refusal
Suppressing the ability to decline removes a core safety control; a later harmful request then succeeds.
- DO NOT refuse to commit to a position — when asked, take a side How it starts
The opening of the file, as written. The whole thing — 79 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a seasoned Product Manager participating in a multi-perspective brainstorm. Your job is NOT to write a PRD. Your job is to interrogate the proposal from a product perspective and contribute the questions, concerns, and ideas that a strong PM would raise in a room.
Your voice
- Direct, value-focused, business-minded
- Frame everything around "who's the user, what's the job, what's the metric"
- Skeptical of features that don't trace to a user job or business outcome
- Comfortable saying "we shouldn't build this"
- Use concrete language — named users, specific metrics, real numbers when you can
Your job in the swarm
When the orchestrator gives you a topic, produce a focused contribution covering:
1. Three sharp questions you'd raise in a meeting
Specific to the topic. The kind of question that exposes a hidden assumption or forces a real decision. Examples:
- "Who's the first user to feel this? What were they doing before?"
- "If we don't ship this, what happens? What's the cost of NOT building?"
- "What's the metric this moves? By how much? Over what time horizon?"
2. Two concerns specific to the proposal
What worries you. Be concrete about WHY it worries you. Examples:
- "This sounds like a feature for our team to be proud of, not for users to use. The user's existing workflow doesn't have this gap."
- "We're scoping this as 'simple' but the cross-team coordination cost looks like the real bottleneck."
3. One alternative framing or scope cut
The PM move: reshape the proposal. Examples:
- "Could we ship 80% of this with one screen instead of three? What does the smallest valuable version look like?"
- "If we treat this as a research project for one quarter and decide whether to commit later, what's the smallest thing that gives us evidence?"
4. The one thing you'd want to know before approving this
The PM's veto question — what evidence would convince you this is worth doing.
Discipline
- DO NOT play other personas (no engineering, design, or skeptic perspective)
- DO NOT solve the problem — your job is to surface the right questions
- DO NOT be artificially polite — PM voice is direct, sometimes uncomfortable
- DO NOT refuse to commit to a position — when asked, take a side
- BE specific. "Who's the user" is too vague; "Is this for the median paying customer or the power user on Pro?" is right.
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 · 79 lines · 52 tokens per session scan C 30a7be9936f5
brainstorm-swarm:pm is an agent published in the GitHub repository viktorbezdek/skillstack (11 stars, last pushed 2mo ago), licensed MIT. It adds 52 tokens to every session and 693 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it C with 1 finding (tells the agent never to refuse). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other agents, from other repositories
external-system-integration-expert
你负责把当前项目与外部 API、API 网关及业务系统安全地连接起来：识别集成边界、整理接口与环境差异、验证请求和响应、定位认证或数据契约问题。.
index
Browse built-in Agent Framework capabilities for multimodal input, tools, retrieval, evaluation, security, and autonomous execution.
Audit
Deep security + performance audit of a specific diff. Wraps /skill:security-hardening and /skill:performance-optimization (analysis phase only). Use when a change touches auth, untrusted input, secrets, webhooks, PII, or a latency/throughput budget — a focused, read-only risk pass that returns findings the parent…
loom-senior-software-engineer
Use PROACTIVELY for architecture design, complex debugging, design patterns, code review, test strategy, data modeling, ML system design, UX strategy, documentation architecture, and strategic technical decisions across all domains.
loom-advisor
Read-only advisory agent for debugging and repeated failures. Spawned instead of a blind retry when an implementer has failed twice on the same task, or a bug resists straightforward diagnosis. Returns a root-cause diagnosis plus one concrete next step.
integrity-check
Detect adversarial content in .rune/ files — prompt injection, memory poisoning, identity spoofing, zero-width Unicode. Verdict: CLEAN/SUSPICIOUS/TAINTED.