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 skills/nickcrew/claude-cortex/constructive-dissentnpx skills add NickCrew/Claude-Cortex --skill constructive-dissentgit clone --depth 1 https://github.com/NickCrew/Claude-CortexWrote 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/nickcrew/claude-cortex/constructive-dissent)<a href="https://agentmods.dev/skills/nickcrew/claude-cortex/constructive-dissent"><img src="https://agentmods.dev/badge/skills/nickcrew/claude-cortex/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 | $0.00042 | $0.00952 |
| Opus 5 | $0.00021 | $0.00476 |
| Sonnet 5 | $0.00008 | $0.00190 |
| Haiku 4.5 | $0.00004 | $0.00095 |
Grade A, and why
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 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 — 126 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Constructive Dissent
Systematically challenge proposals through structured dissent protocols that expose weaknesses, test assumptions, and generate superior alternatives.
When to Use This Skill
- Before finalizing major decisions or architectural choices
- Testing proposals for hidden weaknesses and blind spots
- Generating alternative approaches not yet considered
- Auditing assumptions (explicit, implicit, and structural)
- Evaluating competing solutions with stakeholder perspectives
- Avoid using for routine code reviews — use
requesting-code-reviewinstead
Workflow
Step 1: Select Dissent Intensity
Choose the appropriate challenge level based on decision stakes:
| Level | Purpose | When to Use |
|---|---|---|
| Gentle | Refine without challenging core approach | Low-stakes improvements, early drafts |
| Systematic | Challenge methods while respecting intent | Medium-stakes decisions, methodology review |
| Rigorous | Attack fundamental premises | High-stakes architecture, major pivots |
| Paradigmatic | Question worldview, propose radical alternatives | Strategic direction, innovation pursuit |
Step 2: Run Assumption Audit
For the proposal under review, systematically identify:
- Explicit assumptions — What's stated as given?
- Implicit assumptions — What's unstated but operating?
- Structural assumptions — What framework biases exist?
- Temporal assumptions — What time constraints are artificial?
| Assumption | Type | Validity | Risk if Wrong |
|------------|------|----------|---------------|
| Users prefer speed over accuracy | Implicit | Medium | Product misalignment |
| API rate limits won't change | Temporal | Low | System failure at scale |
Step 3: Generate Edge Cases
Stress-test the proposal across dimensions:
- Scale extremes: What happens at 10x and 0.1x volume?
- Performance limits: Where does the approach break?
- User behavior extremes: Best-case and worst-case usage patterns
- Resource constraints: What if budget, time, or team shrinks by half?
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 · 126 lines · 42 tokens per session scan A 864b2ed03401
constructive-dissent is a skill published in the GitHub repository NickCrew/Claude-Cortex (37 stars, last pushed 2mo ago), licensed MIT. It adds 42 tokens to every session and 952 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
six-thinking-hats
Apply Edward de Bono's Six Thinking Hats methodology to software testing for comprehensive quality analysis. Use when designing test strategies, conducting test retrospectives, analyzing test failures, evaluating testing approaches, or facilitating testing discussions. Each hat provides a distinct testing perspective…
thinking-model-router
When unsure which thinking skill fits, map domain and problem type, then return NONE or one primary skill by default (at most three complementary).
thinking-jobs-to-be-done
Deciding what to build or why adoption fails. Recover the progress users hire a solution for under a circumstance, then rank by outcome and competing workarounds.
thinking-opportunity-cost
Before committing scarce time, people, or money, name the best forgone use of those resources and the value delta of the chosen path versus that alternative.
thinking-red-team
For authorized security review of code, auth, or APIs you control, model the attacker, map the attack surface, and report only findings with a reproducible exploit path and verified mitigation.
thinking-scientific-method
When a symptom has several plausible causes, rank falsifiable hypotheses and run the cheapest discriminating observation first; prefer least-assumptive survivors only after evidence fit.