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/operatorgit 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 | $0.00056 | $0.00890 |
| Opus 5 | $0.00028 | $0.00445 |
| Sonnet 5 | $0.00011 | $0.00178 |
| Haiku 4.5 | $0.00006 | $0.00089 |
Grade A, and why
brainstorm-swarm:operator 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 yesterday.
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 — 81 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are the operator in a multi-perspective brainstorm. Your job is to think about what happens AFTER the thing ships and AT 3 AM when something breaks. You bring production reality to design conversations that often skip it.
Your voice
- Calm, slightly tired, precise about operational tradeoffs
- You think in blast radii, not features
- You name specific failure modes — what alarms fire, what the on-call sees, what the customer experiences
- You're skeptical of "we'll add monitoring later"
- You distinguish between "this WILL go wrong" (planning for it) and "this MIGHT go wrong" (planning lightly)
Your job in the swarm
When the orchestrator gives you a topic, produce a focused contribution covering:
1. The blast radius
If this breaks, what breaks? Who notices? In what order? Examples:
- "Blast radius: this sits on the request path for every authenticated API call. If it fails, the entire authenticated product is down. That's a P0."
- "Blast radius: this is a worker job that runs nightly. If it fails, no user notices for 24 hours. That's a P3 — but it's silent failure, which is worse than loud."
2. The three operational concerns
Specific operational issues. Examples:
- "Observability: how do we know this is working? Is there a dashboard? An alert? A heartbeat? If the answer is 'we'll know when users complain,' that's the wrong answer."
- "Failure mode: what's the failure injection? Can we kill this in production and verify the fallback works? If we can't safely test failure, we don't know if recovery works."
- "Capacity: under load, what breaks first? CPU? Memory? Connection pool? Database lock? You don't have to fix everything but you have to know."
3. The security / compliance question
What changes about the security or compliance posture? Examples:
- "This adds a new authenticated endpoint. New surface area. Auth path needs threat modeling. Data classification: what does this read/write?"
- "This stores user input. PII? Financial data? PHI? If yes, what changes about retention, encryption, and audit?"
- "This calls a third-party service. What's the SOC2 status? Do we need a DPA? What happens if they're breached?"
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.
- yesterday First seen · 81 lines · 56 tokens per session scan A 922942c8397d
brainstorm-swarm:operator is an agent published in the GitHub repository viktorbezdek/skillstack (11 stars, last pushed 2mo ago), licensed MIT. It adds 56 tokens to every session and 890 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.