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-constructive-dissentgit 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-constructive-dissent)<a href="https://agentmods.dev/skills/jeffreytse/grimoire-core/apply-constructive-dissent"><img src="https://agentmods.dev/badge/skills/jeffreytse/grimoire-core/apply-constructive-dissent.svg" alt="Measured on agentmods" 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 | $0.00046 | $0.01758 |
| Opus 5 | $0.00023 | $0.00879 |
| Sonnet 5 | $0.00009 | $0.00352 |
| Haiku 4.5 | $0.00005 | $0.00176 |
Grade A, and why
apply-constructive-dissent 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 5d 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 — 69 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Apply Constructive Dissent
Build the conditions where genuine disagreement surfaces and synthesizes into better decisions — rather than suppressing to a false consensus that looks like harmony but is information loss.
Why This Is Best Practice
Yan Ying (晏婴, 578–500 BC) articulated this to Duke Jing of Qi in 左传 昭公二十年: "和与同异乎...君所谓可而有否焉，臣献其否以成其可" — harmony and sameness are different. When the ruler approves, the minister should name what is wrong with the approval in order to make it truly good. A minister who only agrees with the ruler is adding water to water — producing same-ness, not harmony. The minister who names the defect achieves 和 (genuine synthesis); the one who only agrees achieves 同 (false consensus).
This principle has been independently validated as one of the most impactful organizational design findings of the modern era:
Adopted by: Google (Project Aristotle finding applied to all teams globally), Amazon (Leadership Principle: "Have Backbone; Disagree and Commit"), Bridgewater Associates (radical transparency and believability-weighted decision-making), Intel (Andy Grove's constructive confrontation doctrine).
Impact: Google Project Aristotle (2015) found psychological safety — the belief that speaking up won't result in punishment — was the #1 predictor of team effectiveness across 180+ teams, stronger than individual talent, technical skill, or team composition. Edmondson (Harvard Business School) has replicated this across healthcare, financial services, manufacturing, and technology over 20+ years. Teams with genuine psychological safety outperform on learning speed, error detection, and adaptive performance.
Why best: False consensus (同) is not neutral — it actively suppresses information. When team members do not raise doubts, concerns, or contrary evidence, those doubts exist but are invisible to the decision. The decision proceeds without the information that would have changed it. 和 (constructive dissent) makes that information visible before commitment, not after failure.
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.
- 5d ago First seen · 69 lines · 46 tokens per session scan A c36e3fdad481
apply-constructive-dissent is a skill published in the GitHub repository jeffreytse/grimoire-core (4 stars, last pushed 19d ago), licensed MIT. It adds 46 tokens to every session and 1,758 once invoked, about $0.0002 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
semantic-model-disambiguation
Analyze Power BI semantic models for column-level overlaps that confuse Copilot and Fabric data agents. Detect ambiguity, review with domain expert, apply fixes via MCP.
infrastructure-as-code
Domain: DevOps & Cloud Engineering.
prompt-2-data
Generate comprehensive synthetic relational data for any specified subject with multiple normalized CSV files maintaining referential integrity.
academic-paper-drafting
End-to-end academic paper drafting for CHI, HBR, journals, and conferences with venue-specific templates, drafting workflows, and revision strategies.
research-first-development
Build knowledge bases that build software — research before code, teach before execute.
agent-governance
Patterns for adding safety, trust, and policy enforcement to AI agent systems -- control which tools agents can call, what content they process, and maintain accountability through audit trails.