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 product-on-purpose/thinking-framework-skills --skill think-contradiction-resolutiongit clone --depth 1 https://github.com/product-on-purpose/thinking-framework-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/product-on-purpose/thinking-framework-skills/think-contradiction-resolution)<a href="https://agentmods.dev/skills/product-on-purpose/thinking-framework-skills/think-contradiction-resolution"><img src="https://agentmods.dev/badge/skills/product-on-purpose/thinking-framework-skills/think-contradiction-resolution/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/product-on-purpose/thinking-framework-skills/think-contradiction-resolution"><img src="https://agentmods.dev/badge/skills/product-on-purpose/thinking-framework-skills/think-contradiction-resolution.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 | $0.00144 | $0.01830 |
| Opus 5 | $0.00072 | $0.00915 |
| Sonnet 5 | $0.00029 | $0.00366 |
| Haiku 4.5 | $0.00014 | $0.00183 |
Grade A, and why
think-contradiction-resolution 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 11d 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 — 64 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Contradiction Resolution (Ideal Final Result)
Most problems arrive as a trade-off: to get more of A you must accept less of B (cheaper but flimsier, faster but riskier, generous but unprofitable). The reflex is to optimize - find the least-bad point on the curve. Contradiction resolution refuses that reflex first. It reframes the problem as a contradiction to be dissolved - a solution in which you stop trading A against B at all - and only settles for the compromise once a disciplined attempt to dissolve the trade-off has actually failed. The reframe is the durable move; it is the de-branded core of TRIZ (Genrich Altshuller, from 1946). The output is a contradiction-resolution worksheet, not a discussion.
When to Use
- A problem is stated as, or has quietly collapsed into, an "A vs B" trade-off, and nobody has tested whether the trade-off is actually necessary.
- The obvious answer is "pick a point on the curve," and a genuine win-win would be worth far more than the best compromise.
- A design, process, or product tension keeps forcing the same painful balance ("thorough vs fast", "generous vs profitable", "secure vs convenient").
- The opposing requirements look like they might hold at different times, places, scales, or under different conditions.
When NOT to Use
- The trade-off is genuinely fundamental. Some contradictions are imposed by physical law, conservation, regulation, or hard external limits and cannot be engineered away (you cannot separate "spend the money" from "keep the money"). Forcing the move there manufactures clever-sounding non-solutions and delays the real decision. When dissolution fails, the honest output is "this is a real trade-off" - route it to
think-decision-option-reviewto choose under it, or treat it as a standing polarity to manage. This is the central wall. - You need idea volume, not a frame. This skill is convergent on one tension and produces fewer ideas than open ideation. For breadth use
think-brainwritingorthink-far-analogy-ideation. - The tension is one you must manage, not eliminate. An unresolvable polarity (centralize vs decentralize, structure vs flexibility) is to be navigated over time, not dissolved - that is tension/polarity mapping, not this.
- No real opposition exists. If the problem is vague or under-specified rather than genuinely two-sided, this tool will invent a contradiction that is not there. Frame it first with
think-problem-restatement, then run this once a real trade-off is on the table.
What ships with it
5 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.
- 11d ago First seen · 64 lines · 144 tokens per session scan A 13c6ebfb0dc6
think-contradiction-resolution is a skill published in the GitHub repository product-on-purpose/thinking-framework-skills (15 stars, last pushed today), licensed Apache-2.0. It adds 144 tokens to every session and 1,830 once invoked, about $0.0007 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 skills, from other repositories
ops-demo
CocoOps demo mode activator — populates .cocoplus/ops/demo/ with realistic mock data and sets cocoplus.toml [demo] enabled = true. Invoked via $ops demo.
add-analytics
Add Google Analytics 4 tracking to any project. Detects framework, adds tracking code, sets up events, and configures privacy settings.
agent-teams-simplify-and-harden
Implementation + audit loop using parallel agent teams with structured simplify, harden, and document passes. Spawns implementation agents to do the work, then audit agents to find complexity, security gaps, and spec deviations, then loops until code compiles cleanly, all tests pass, and auditors find zero issues or…
acl-rule-analysis
Vendor-agnostic ACL and firewall rule analysis with shadowed rule detection, overly permissive rule identification, unused rule discovery, redundant rule flagging, and rule ordering optimization. Covers ACLs (Cisco/JunOS/EOS) and firewall policies (PAN-OS/FortiGate/CheckPoint).
agent-team-orchestration
Orchestrate multi-agent teams with defined roles, task lifecycles, handoff protocols, and review workflows. Use when: (1) Setting up a team of 2+ agents with different specializations, (2) Defining task routing and lifecycle (inbox → spec → build → review → done), (3) Creating handoff protocols between agents, (4)…
agent-bom-enforce
Enforce security policies on MCP tool calls and block dangerous operations at runtime. Use when: "block risky calls", "apply policy", "proxy", "runtime protection", "policy enforcement", "intercept MCP calls".