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 skills add deciqAI/knowledge-skills --skill non-consensus-thinkinggit clone --depth 1 https://github.com/deciqAI/knowledge-skillsWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/deciqai/knowledge-skills/non-consensus-thinking)<a href="https://agentmods.dev/skills/deciqai/knowledge-skills/non-consensus-thinking"><img src="https://agentmods.dev/badge/skills/deciqai/knowledge-skills/non-consensus-thinking/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/deciqai/knowledge-skills/non-consensus-thinking"><img src="https://agentmods.dev/badge/skills/deciqai/knowledge-skills/non-consensus-thinking.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
What 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 5.1 | $0.00117 | $0.02086 |
| Opus 5 | $0.00059 | $0.01043 |
| Sonnet 5 | $0.00023 | $0.00417 |
| Haiku 4.5 | $0.00012 | $0.00209 |
Grade A, and why
non-consensus-thinking 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 9d 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 — 122 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Non-Consensus Thinking
Overview
Every market — capital, talent, customers, ideas — prices the consensus view into its current state. By the time an idea is mainstream, its excess return has been arbitraged away. Non-consensus thinking is a disciplined audit of where the crowd's belief might be wrong and whether you hold a specific, articulable advantage that makes the minority position actually correct, not just different.
Compose with: [second-order-thinking] first (trace downstream consequences); [confirmation-bias] audit after (check you haven't built a new blind minority consensus); [first-principles] instead when rebuilding from bedrock evidence, not auditing mispricing.
When to Use
- Entering a market where the "right" strategy feels obvious to most participants.
- Making an allocation decision (capital, time, hiring) where popular and correct may diverge.
- Any situation where "everyone knows that..." appears — consensus may be unexamined.
- A contested present-day narrative where crowd and edge may diverge (e.g. "AI capex is a bubble," chip export controls, "the scaling thesis is dead") — pressure-test whether you hold a real edge or are just picking a side.
When NOT to use: Consensus is correct and well-evidenced; non-consensus position requires information you can't obtain; time horizon too short to vindicate the position; stakes of being wrong are catastrophic and irreversible.
Coaching Novices (Adaptive Front Door)
- Engine mode: user has a concrete case → run The Process directly.
- Coach mode: user is unfamiliar → guide step by step.
In Coach mode, respond one step at a time. Each [WAIT] is a hard stop — output only that step's question, then stop.
- What it is: "What does everyone believe, and why might they be wrong — and do I have a real edge that makes the minority view correct?"
- Check fit: "Tell me your decision. Is there a dominant answer most people in your field would give? Do you have specific conflicting evidence?"
- Elicit their real case: "State the consensus in one sentence. What specific information do you have that most participants don't?"
[WAIT — do not advance until user responds]
- Run The Process one step at a time with their input. Do not jump to asymmetry until edge audit is complete.
[WAIT — do not advance until user responds]
- Close: "If your edge is real and consensus is wrong, what becomes possible? Name that outcome specifically."
[WAIT — do not advance until user responds]
What ships with it
3 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 9d ago First seen · 122 lines · 117 tokens per session scan A b7858a336307
non-consensus-thinking is a skill published in the GitHub repository deciqAI/knowledge-skills (10 stars, last pushed 11d ago), licensed MIT. It adds 117 tokens to every session and 2,086 once invoked, about $0.0006 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 2026-09-03.
Other skills, from other repositories
edge-tts
Text-to-speech conversion using uvx edge-tts for generating audio from text. Use when (1) User requests audio/voice output with the "tts" trigger or keyword. (2) Content needs to be spoken rather than read (multitasking, accessibility, driving, cooking). (3) User wants a specific voice, speed, pitch, or format for TTS…
mcp-deepwiki
Skills for accessing and searching docs in DeepWiki/GitHub’s public code repositories can help users understand open-source project source codes, and users can also ask questions directly about the code docs.
tianqi
A weather-lookup workflow for Chinese locations, covering forecasts, hourly conditions, weather warnings, and daily-life indexes.
cto-advisor
Records technical decisions that serve a business outcome: constraints, architecture options, build-or-buy tradeoffs, and a justified skill selection. Use when the CEO asks "which architecture fits", "should we build or buy", "which skill should this department use", or "review our technical plan".
compliance-check
Compliance pre-flight for a feature, campaign, or initiative — maps the data and activity involved, checks applicable regimes (privacy/GDPR-style, consumer protection, marketing rules, sector-specific), lists required approvals and notices, builds a gap list with remediation owners, and ends in a go/no-go…
plan-payroll
Plans payroll cash: true loaded cost per hire (gross plus employer taxes, benefits, tools), a payroll calendar with cutoffs and cash-out dates, a scenario table for new hire vs raise vs contractor-vs-employee, and a payroll-to-revenue check against rough industry bands. Use when the user asks "can I afford to hire"…