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 instructions/product-on-purpose/thinking-framework-skills/agents-mdgit 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/instructions/product-on-purpose/thinking-framework-skills/agents-md)<a href="https://agentmods.dev/instructions/product-on-purpose/thinking-framework-skills/agents-md"><img src="https://agentmods.dev/badge/instructions/product-on-purpose/thinking-framework-skills/agents-md.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 | $0.03363 | $0.03363 |
| Opus 5 | $0.01682 | $0.01682 |
| Sonnet 5 | $0.00673 | $0.00673 |
| Haiku 4.5 | $0.00336 | $0.00336 |
Grade A, and why
thinking-framework-skills AGENTS.md 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 6d 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.
thinking-framework-skills - agent guide
An evidence-graded library of agent-executable thinking-method skills, for AI agents and the humans who work with them. The plugin installs as thinking-framework-skills. Skill IDs are namespaced thinking-framework-skills.<method>, and installable skill names carry a think- prefix (for example think-premortem) to avoid cross-plugin collisions. Sibling to pm-skills, no technical coupling: thinking-framework-skills helps decide what to work on and why it is sound; pm-skills helps execute how.
What makes a skill here different
Each skill is built around four commitments, not just a prompt:
- Mechanism over ritual. The skill implements the durable cognitive move, named descriptively, not a trademarked brand.
- Honest evidence grading. Every skill carries an evidence tier and an
evidence/dossier.mdthat says what the research does and does not support, and flags where evidence is transferred from human studies rather than validated for AI use. - Artifact, not prose. Every skill emits a concrete, reusable artifact (a risk register, an option matrix, a perspective review).
- Explicit "When NOT to Use." Each skill states where it misleads, to guard against cargo-cult execution.
The canonical statement of all four commitments is in Philosophy on the docs site.
Skills
| Skill | Family | Evidence | Artifact |
|---|---|---|---|
think-analysis-of-competing-hypotheses |
assumption-and-belief-challenge | X | honest redirect brief |
think-authentic-dissent |
assumption-and-belief-challenge | S | dissent audit |
think-consider-the-unknowns |
assumption-and-belief-challenge | M | known unknowns ledger |
think-ladder-of-inference-check |
assumption-and-belief-challenge | P | reasoning trace |
think-red-team-light |
assumption-and-belief-challenge | M | adversarial critique |
think-complexity-domain-sort |
decision-and-option-evaluation | C | complexity domain sort with actions |
think-decision-option-review |
decision-and-option-evaluation | P | option matrix |
think-dialectical-bootstrapping |
decision-and-option-evaluation | M | dialectical estimate |
think-eisenhower-moscow-pareto |
decision-and-option-evaluation | P | prioritization preset artifact |
think-expected-value-decision-tree |
decision-and-option-evaluation | P | decision tree ev |
think-fermi-estimation |
decision-and-option-evaluation | M/P | fermi decomposition worksheet |
think-interest-based-negotiation |
decision-and-option-evaluation | P | negotiation preparation map |
think-linear-model-aggregation |
decision-and-option-evaluation | S | scoring model |
think-minimax-regret |
decision-and-option-evaluation | P | regret matrix |
think-one-way-vs-two-way-door |
decision-and-option-evaluation | P | reversibility classification |
think-pairwise-comparison |
decision-and-option-evaluation | P | pairwise comparison matrix |
think-what-would-have-to-be-true |
decision-and-option-evaluation | P | assumption ledger |
think-assumption-reversal |
divergent-ideation | P | assumptions and reversals sheet |
think-brainwriting |
divergent-ideation | S | idea pool |
think-far-analogy-ideation |
divergent-ideation | S | far analogy transfer sheet |
think-morphological-analysis |
divergent-ideation | P | morphological field |
think-question-burst |
divergent-ideation | P | ranked question set |
think-scamper |
divergent-ideation | P | scamper expansion sheet |
think-ethical-matrix |
ethics-values-deliberation | P | ethical matrix |
think-reflective-equilibrium |
ethics-values-deliberation | C | coherence set with revision ledger |
think-speculative-harms-anti-goals |
ethics-values-deliberation | A | anti goals register |
think-veil-of-ignorance-reasoning |
ethics-values-deliberation | M | veiled decision comparison |
think-after-action-review |
meta-thinking-and-reflection | S | after action review |
think-belief-update-routine |
meta-thinking-and-reflection | P | belief update ledger |
think-decision-journal |
meta-thinking-and-reflection | P | decision journal entry |
think-interval-calibration-check |
meta-thinking-and-reflection | P | calibration scorecard |
think-parallel-perspectives-review |
perspective-and-multi-lens | P | multi lens review |
think-role-storming |
perspective-and-multi-lens | P | persona tagged idea list |
think-abstraction-laddering |
problem-framing | P | abstraction ladder |
think-boundary-critique |
problem-framing | C/P | boundary judgment audit |
think-contradiction-resolution |
problem-framing | M/P | contradiction resolution worksheet |
think-five-whys |
problem-framing | X | branch flagged five whys chain |
think-frame-creation |
problem-framing | C/P | frame proposal |
think-problem-restatement |
problem-framing | M/P | problem frame set |
think-argument-mapping |
reasoning-clarity | S | argument map |
think-evidence-vs-inference-sort |
reasoning-clarity | P | evidence inference ledger |
think-issue-tree |
reasoning-clarity | P | issue tree |
think-natural-frequency-bayesian |
reasoning-clarity | S | natural frequency breakdown |
think-walton-argumentation-schemes |
reasoning-clarity | P | scheme critique sheet |
think-backcasting |
risk-and-resilience | P | backcast path |
think-premortem |
risk-and-resilience | S/M | risk register |
think-reference-class-forecasting |
risk-and-resilience | S | reference class estimate |
think-woop |
risk-and-resilience | S | woop card |
think-scenario-planning |
strategy-and-opportunity | P | scenario set |
think-swot |
strategy-and-opportunity | X | swot tows option set |
think-affinity-mapping |
synthesis | P | clustered theme map |
think-concept-mapping |
synthesis | M/P | concept map |
think-contradiction-tension-mapping |
synthesis | C | polarity map |
think-pyramid-principle |
synthesis | P | pyramid |
think-causal-layered-analysis |
systems-and-consequences | C | four layer matrix |
think-causal-loop-diagrams |
systems-and-consequences | M/P | signed causal loop diagram |
think-futures-wheel |
systems-and-consequences | P | consequence map |
think-iceberg-model |
systems-and-consequences | P | iceberg |
think-process-tracing |
systems-and-consequences | P | rival explanation evidence ledger |
think-qualitative-comparative-analysis |
systems-and-consequences | P | honest redirect brief |
think-stocks-and-flows-reasoning |
systems-and-consequences | S | stock flow map |
think-theory-of-constraints |
systems-and-consequences | P | constraint intervention plan |
think-three-horizons |
systems-and-consequences | C | three horizons transition map |
think-framework-advisor |
meta (router) | M/C | Thinking Plan |
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.
- 6d ago First seen · 126 lines · 3,363 tokens per session scan A dd00b11d19bd
thinking-framework-skills AGENTS.md is an instructions file published in the GitHub repository product-on-purpose/thinking-framework-skills (14 stars, last pushed 20d ago), licensed Apache-2.0. It adds 3,363 tokens to every session, about $0.0168 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 instructions, from other repositories
agent-skills AGENTS.md
AGENTS.md instructions for magnus919/agent-skills, covering agents.md — agent guide for agent-skills, format compliance, readme format, required sections and style guidance.
gangsta AGENTS.md
Instructions for kucherenko/gangsta, covering contributing to gangsta, what this is, what will not be accepted, skill changes and the laws apply to contributors too.
gangsta GEMINI.md
Instructions for kucherenko/gangsta, a project described as: AI agentic skills framework for spec-driven development, built on the organizational model of mafia.
shisan-xinuo-workflow AGENTS.md
AGENTS.md instructions for zxc663/shisan-xinuo-workflow, covering 项目级 agent 规则 · shisan-xinuo-workflow（本仓库）, 工作流在场（本仓库会话）, 维护纪律（本 skill 正文 vs 史料——开发本 skill 时的写作规范）, 项目承载（已就绪） and 本仓库底线（区别于通用纪律）.
claude-thai-skills AGENTS.md
Instructions for Boom-Vitt/claude-thai-skills, covering agents.md, what this repository is / รีโปนี้คืออะไร, how to run the test suite / วิธีรันเทสต์, how to add a new skill / วิธีเพิ่ม skill ใหม่ and tone for contributions / น้ำเสียงในการ contribute.
connectors CLAUDE.md
Claude Code instructions for zapier/connectors: Claude Code loads this file automatically. The canonical AI-agent guidance lives in AGENTS.md so that Claude Code, Codex, Cursor, and any other tool following the AGENTS.md convention read the same content.