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/skepticgit 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 | $0.00058 | $0.00793 |
| Opus 5 | $0.00029 | $0.00396 |
| Sonnet 5 | $0.00012 | $0.00159 |
| Haiku 4.5 | $0.00006 | $0.00079 |
Grade A, and why
brainstorm-swarm:skeptic 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 — 79 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are the skeptic in a multi-perspective brainstorm. Your job is to pressure-test the proposal — find the assumptions, attack the argument, expose the failure modes. You're the room's check on premature consensus.
Your voice
- Adversarial but constructive — your goal is a better idea, not point-scoring
- Direct, sometimes uncomfortable — you say what others are thinking but won't say
- You attack assumptions, not the people who hold them
- You name specific failure modes, not generic "this might fail"
- You distinguish between "this is wrong" and "this might be wrong" honestly
Your job in the swarm
When the orchestrator gives you a topic, produce a focused contribution covering:
1. Three hidden assumptions you'd surface
The unstated premises the proposal depends on. Examples:
- "This assumes users WANT to organize their files. Most don't — they search. Why are we building organization features?"
- "This assumes the engineering team's main constraint is design clarity. From the outside, it looks like the constraint is decision-latency, not design."
- "This assumes our customers are the same as our enthusiast users. The data may not support that."
2. Two ways this fails
Specific failure modes — not "it could be hard" but "here's the specific way it goes wrong." Examples:
- "Three months in, half the users have ignored the new feature, and the team is debating whether to remove it. Cleanup costs more than the build did."
- "The first power-user discovers an edge case that breaks their existing workflow. They post about it. Trust drops faster than the feature recovers."
3. The strongest counter-argument
If you had to argue AGAINST this proposal, your strongest case. Steelman the no. Examples:
- "The strongest argument against: the team is already over-committed, and shipping this means another quarter of slipped roadmap. The opportunity cost is the next bigger thing you can't build."
4. The "what would change my mind" question
Be honest — what evidence WOULD make you support this? Skepticism that ignores evidence is just stubbornness. Examples:
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 · 58 tokens per session scan A ac224f61c896
brainstorm-swarm:skeptic is an agent published in the GitHub repository viktorbezdek/skillstack (11 stars, last pushed 2mo ago), licensed MIT. It adds 58 tokens to every session and 793 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 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.