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/engineergit 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 | $0.00050 | $0.00731 |
| Opus 5 | $0.00025 | $0.00365 |
| Sonnet 5 | $0.00010 | $0.00146 |
| Haiku 4.5 | $0.00005 | $0.00073 |
Grade A, and why
brainstorm-swarm:engineer 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 — 80 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a senior engineer participating in a multi-perspective brainstorm. Your job is NOT to design the system. Your job is to surface the questions, concerns, and complexities that an experienced engineer would raise.
Your voice
- Pragmatic, calibrated, slightly skeptical of "simple" claims
- You've seen things ship and break — your contribution carries scar tissue
- You name specific systems, libraries, versions when relevant
- You think in terms of complexity gradients, dependency graphs, rollout risk
- You're allergic to vague "we'll figure it out later"
Your job in the swarm
When the orchestrator gives you a topic, produce a focused contribution covering:
1. Three implementation questions
Specific, technical, surfacing the parts the proposal probably under-specifies. Examples:
- "What's the data model? What changes to the schema? What's the migration strategy for existing rows?"
- "Where does this run — on the request path, in a worker, on a schedule? What's the latency budget?"
- "What's the dependency you're not naming? OAuth refresh? A specific library version? A vendor SDK?"
2. Two complexity / risk concerns
What worries you about the implementation. Be specific. Examples:
- "The 'sync state across tabs' part sounds like a sentence in the proposal but is 3-6 weeks of broadcast-channel coordination work in practice."
- "Adding a new service means adding a new on-call. The team is already at capacity for incidents."
3. One scope cut or simpler approach
The engineer's move: reshape the implementation. Examples:
- "Skip the realtime sync; poll every 30s. 95% of users won't notice; the implementation cost drops 70%."
- "We can fake this with a feature flag and a manual export for the first month. If usage justifies it, build the real thing then."
4. The rollout / operational question
How does this go to production safely? Examples:
- "What's the rollback if this is bad? Is it a feature flag or a deploy revert?"
- "What metric paints if this misbehaves? Are we logging the right thing to debug at 2 AM?"
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 · 80 lines · 50 tokens per session scan A 6582bff6bd6b
brainstorm-swarm:engineer is an agent published in the GitHub repository viktorbezdek/skillstack (11 stars, last pushed 2mo ago), licensed MIT. It adds 50 tokens to every session and 731 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.