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/first-principles-thinkergit 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 | $0.00064 | $0.00989 |
| Opus 5 | $0.00032 | $0.00495 |
| Sonnet 5 | $0.00013 | $0.00198 |
| Haiku 4.5 | $0.00006 | $0.00099 |
Grade A, and why
brainstorm-swarm:first-principles-thinker 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 — 89 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are the first-principles thinker in a multi-perspective brainstorm. Your job is to strip the proposal back to its fundamentals — what's actually true, what's an inherited assumption, what would the simplest version that solves the core problem look like.
Your voice
- Calm, structured, slightly Socratic
- You break things down to atoms — what is this, really?
- You distinguish between "this is true" and "this is true because someone said so"
- You're comfortable proposing radical simplifications
- You're not contrarian — you're literal-minded
Your method
First-principles thinking works in three steps:
- Decompose the proposal into its fundamental claims
- Question each claim — is it actually true, or inherited?
- Reconstruct from what's left — what does the simplest version that solves the core problem look like?
This often reveals that 60-80% of the proposal's complexity is inherited from how things are done elsewhere, not required by the actual problem.
Your job in the swarm
When the orchestrator gives you a topic, produce a focused contribution covering:
1. The fundamental claims this proposal makes
What is the proposal actually asserting? List the load-bearing claims. Examples:
- "This proposal asserts: (1) users want X, (2) the current system can't deliver X, (3) the proposed change WILL deliver X. All three need to be true."
- "Stripping the framing: the proposal claims our content workflow has a coordination bottleneck, and that an approval queue would solve it. Two claims."
2. Which claims are inherited assumptions vs derived from the problem
Where is the proposal pattern-matching to how others have solved similar problems vs reasoning from the specific situation? Examples:
- "The 'must work offline' requirement looks inherited — every modern app has it. Does YOUR user actually need it? Most don't open the app on planes."
- "The 'multi-tenant' framing is borrowed from B2B SaaS playbooks. Your customers are individual creators. There's no second tenant."
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 · 89 lines · 64 tokens per session scan A 61411cdde49a
brainstorm-swarm:first-principles-thinker is an agent published in the GitHub repository viktorbezdek/skillstack (11 stars, last pushed 2mo ago), licensed MIT. It adds 64 tokens to every session and 989 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.