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 prisoners-dilemmagit 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/prisoners-dilemma)<a href="https://agentmods.dev/skills/deciqai/knowledge-skills/prisoners-dilemma"><img src="https://agentmods.dev/badge/skills/deciqai/knowledge-skills/prisoners-dilemma/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/prisoners-dilemma"><img src="https://agentmods.dev/badge/skills/deciqai/knowledge-skills/prisoners-dilemma.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 | $0.00147 | $0.02575 |
| Opus 5 | $0.00073 | $0.01288 |
| Sonnet 5 | $0.00029 | $0.00515 |
| Haiku 4.5 | $0.00015 | $0.00258 |
Grade A, and why
prisoners-dilemma 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 — 125 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Prisoner's Dilemma
Overview
Whatever the other party does, each player is individually better off defecting — so both defect, and both end up worse than mutual cooperation. This is the structural skeleton beneath price wars, arms races, overfishing, and ad spend spirals. The problem is never character; it is structure. Exhortations to cooperate fail. Change the matrix.
Composes with: second-order-thinking for matrix redesign · expected-value-and-kelly for probabilistic payoffs · repeated-games-reputation for the iterated-game case.
When to Use
- Two or more parties would each do better cooperating, but cooperation keeps failing to materialize
- Situation involves price competition, capacity races, advertising arms races, or commons-style resource depletion
- You are about to negotiate or enter a partnership and want to know whether the structure makes betrayal individually rational
- Someone asks directly about "prisoner's dilemma," "tragedy of the commons," "race to the bottom," or "Nash equilibrium"
- A present-day competitive sprint is in play — an AI capex / compute arms race, AI-safety release race, or AI-native land-grab where every player feels forced to move fast despite preferring collective restraint
When NOT to use: zero-sum games · pure coordination problems (Schelling) · long transparent repeated game with established reputations (use repeated-games-reputation) · low-stakes reversible decisions
Coaching Novices (Adaptive Front Door)
- Engine mode: user has a concrete case → run The Process directly.
- Coach mode: user is unfamiliar or has no concrete case → 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.
- One-line what-it-is (≤2 sentences): some situations look like "people being stubborn" but are actually a structural trap — given the rules, defecting is individually rational, and exhorting people to cooperate won't work; you have to change the structure.
- Check fit against When to Use / When NOT to use. If it's zero-sum or pure coordination, point elsewhere.
- Elicit their real situation. Get a concrete case (a partnership, a market, a negotiation). > [WAIT — do not advance until user responds]
- Run The Process one step at a time with their input — payoff matrix first, then dominant-strategy reasoning, then escape options. > [WAIT — do not advance until user responds]
- Close by naming the one escape mechanism that fits their situation — repetition, reputation, enforcement, or matrix-change — and why that one rather than the others. > [WAIT — do not advance until user responds]
What ships with it
4 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 · 125 lines · 147 tokens per session scan A 54f9df519031
prisoners-dilemma is a skill published in the GitHub repository deciqAI/knowledge-skills (10 stars, last pushed 10d ago), licensed MIT. It adds 147 tokens to every session and 2,575 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 2026-09-03.
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.
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"…
ui-ux-pro-max
Builds an end-to-end UI system for a product — design tokens (color scale, type scale, spacing, radii, shadows), a component inventory covering every interaction state, a layout grid, and WCAG contrast checks — emitted as CSS variables plus a component spec doc. Use when the user says "set up a design system", "create…