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 jeffreytse/grimoire-core --skill apply-non-consensus-category-convictiongit clone --depth 1 https://github.com/jeffreytse/grimoire-coreWrote 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/jeffreytse/grimoire-core/apply-non-consensus-category-conviction)<a href="https://agentmods.dev/skills/jeffreytse/grimoire-core/apply-non-consensus-category-conviction"><img src="https://agentmods.dev/badge/skills/jeffreytse/grimoire-core/apply-non-consensus-category-conviction/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/jeffreytse/grimoire-core/apply-non-consensus-category-conviction"><img src="https://agentmods.dev/badge/skills/jeffreytse/grimoire-core/apply-non-consensus-category-conviction.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00061 | $0.01692 |
| Opus 5 | $0.00030 | $0.00846 |
| Sonnet 5 | $0.00012 | $0.00338 |
| Haiku 4.5 | $0.00006 | $0.00169 |
Grade A, and why
apply-non-consensus-category-conviction 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 8d 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 — 68 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Apply Non-Consensus Category Conviction
Bet on an unproven category or business model that the prevailing market consensus actively doubts or dismisses, when independently-formed conviction — grounded in deep prior understanding, not contrarianism for its own sake — supports it, since the earliest, highest-impact opportunities in venture investing are frequently ones the mainstream view has already dismissed.
Why This Is Best Practice
Adopted by: Liu Qin (刘芹) and Wuyuan Capital's (五源资本) early investment in Xiaomi is documented in Chinese and English technology press accounts as a genuinely non-consensus bet at the time — made against prevailing industry skepticism that a new entrant, led by a founder without an established track record in that specific hardware category, could meaningfully compete against entrenched incumbents. The investment is now widely cited in venture capital case studies specifically as an example of conviction formed independently of, and against, the prevailing consensus view at the time of investment.
Impact: Because a genuinely unproven category or company has no established market price or track record to validate a thesis against, the entire basis for the investment must come from independently-formed conviction rather than external confirmation — by the time consensus catches up and confirms the thesis, much of the opportunity's earliest, most attractive risk-adjusted return has typically already been captured by earlier, non-consensus investors. The documented Xiaomi case is specifically cited as an example where the return to being early and non-consensus, rather than waiting for confirming signals, was substantial.
Why best: Waiting for market consensus to validate a category before investing forfeits the specific return premium available to genuinely early, non-consensus conviction — by definition, once consensus has formed, the highest-conviction, lowest-priced entry point has typically already passed. The willingness to act on independently-formed conviction ahead of consensus, when that conviction is genuinely well-grounded (see apply-deep-industry-immersion-research) rather than merely contrarian for its own sake, is what allows an investor to capture this early-stage opportunity.
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.
- 8d ago First seen · 68 lines · 61 tokens per session scan A 9c5eaaa8d131
apply-non-consensus-category-conviction is a skill published in the GitHub repository jeffreytse/grimoire-core (4 stars, last pushed 23d ago), licensed MIT. It adds 61 tokens to every session and 1,692 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 2026-09-03.
Other skills, from other repositories
azure-cost-management-api
In PowerShell, inline JSON for Cost Management API causes "Unsupported Media Type" errors.
stock-analysis-lead
Orchestrate a US-stock investment analysis — classify sector archetype, fetch SEC filings, dispatch a tiered fan-out of six vertical equity-research agents (business model, earnings quality, balance sheet, management, industry, peer comparison) over a validated JSON findings contract, then synthesize a buy/hold/sell…
stock-earnings-quality-review
Review a US-listed company's earnings quality, cash-flow integrity, and operating leverage for an equity-research workup. Covers operating cash flow vs net income drift, free cash flow trajectory, capex character (maintenance vs expansion), equity issuance / shareholder-return yield, revenue-quality signals…
stock-industry-review
Review a US-listed company's industry position and competitive moat for an equity-research workup. Covers Porter Five Forces scan, market-share trend (absolute and relative to industry growth), TAM size and trajectory, unit economics where disclosed (LTV/CAC, unit gross margin), moat classification (network / brand /…
stock-management-review
Review a US-listed company's management quality and capital-allocation track record for an equity-research workup. Covers 5-year capital-allocation history (buybacks vs dividends vs M&A vs capex vs debt), buyback timing, M&A return-on-investment, guidance-vs-actuals track record, comp-structure alignment, insider…
stock-peer-comparison-review
Independently benchmark a US-listed target equity against 2-4 closest peers on a fixed 12-item ratio panel — growth rates, profitability, capital intensity, balance sheet leverage, capital returns, and valuation multiples. Provides cross-validation for moat and market-share claims made by the business and industry…