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-concept-mappinggit 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-concept-mapping)<a href="https://agentmods.dev/skills/product-on-purpose/thinking-framework-skills/think-concept-mapping"><img src="https://agentmods.dev/badge/skills/product-on-purpose/thinking-framework-skills/think-concept-mapping/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-concept-mapping"><img src="https://agentmods.dev/badge/skills/product-on-purpose/thinking-framework-skills/think-concept-mapping.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 | $0.00092 | $0.01482 |
| Opus 5 | $0.00046 | $0.00741 |
| Sonnet 5 | $0.00018 | $0.00296 |
| Haiku 4.5 | $0.00009 | $0.00148 |
Grade A, and why
think-concept-mapping 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 — 65 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Concept Mapping
When a domain is described in prose or sketched as a diagram, the relationships between its concepts stay vague: a line is drawn between two boxes, or two ideas are called "related", and how they actually relate is never specified. Concept mapping refuses the unlabeled link. It builds a non-hierarchical semantic network in which every connection is a directed, labeled linking phrase, so each node-link-node triple reads as an explicit proposition ("free tier - increases - signup volume"), and clusters are joined by cross-links that connect concepts across different parts of the map. The load-bearing move is forcing every relationship to be named, which externalizes how the domain interrelates and makes gaps, missing links, and false propositions visible. The output is a concept map plus a list of surfaced gaps. It externalizes and inspects how concepts relate; it does not claim to improve learning, retention, or decisions.
When to Use
- A domain has many interrelated concepts and the goal is to make how they relate explicit and inspectable.
- You suspect hidden gaps or misconceptions in how a space is understood and want them surfaced as checkable propositions.
- Integration across sub-areas matters, so the cross-links between clusters carry the value (for example linking a pricing concept to a support-cost concept).
When NOT to Use
- To evaluate whether one argument or recommendation is sound - use argument-mapping. Both produce "maps" and this is the easiest confusion: argument mapping has a claim, reasons, co-premises, and objections and judges soundness; a concept map is a network of propositions and judges nothing.
- To decompose one big question top-down into MECE parts - use issue-tree. A concept map is a non-hierarchical network, not a decomposition tree, and does not aim for mutual exclusivity.
- To cluster many raw notes bottom-up with no named relationships - use affinity-mapping (the KJ method). Affinity mapping groups items into themes and deliberately does not name the relationship between them; if you only need themes, not propositions, use it.
- To move a problem down fixed event / pattern / structure / mental-model levels - use iceberg-model. The iceberg has prescribed causal levels; a concept map has none.
- If you drop the labeled-link / proposition constraint, you are doing free-association mind-mapping with unlabeled branches (the Buzan method), which this library excludes (X-tier; Farrand 2002). The named-relationship discipline is the skill; without it this collapses into the excluded method.
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.
- 9d ago First seen · 65 lines · 92 tokens per session scan A 9b9b81b9cee5
think-concept-mapping is a skill published in the GitHub repository product-on-purpose/thinking-framework-skills (15 stars, last pushed 23d ago), licensed Apache-2.0. It adds 92 tokens to every session and 1,482 once invoked, about $0.0005 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
Vibe Coding Mastery
The complete operating system for building software with AI. From first prompt to production deployment — prompting frameworks, architecture patterns, testing strategies, debugging playbooks, and production graduation checklists. Works with Claude Code, Cursor, Windsurf, Copilot, and any AI coding tool.
ai-shifu-course-creator
Convert raw course material into optimized, runnable MarkdownFlow teaching scripts and deploy them as live courses through a five-phase pipeline covering segmentation, orchestration, generation, optimization, and deployment.
ai-learning-planner-cn
An AI learning planner that creates personalised study paths, tracks progress, recommends resources, answers questions, and produces learning reports. It can also support group learning.
add-educational-comments
Add educational comments to the file specified, or prompt asking for file to comment if one is not provided.
common-sense-index-investing-bogle
Apply John Bogle index investing rules for low-cost funds, asset allocation, fees, taxes, ETFs, advisers, and buy-hold discipline.
openlibrary
Query the Open Library catalog from the terminal: search books and authors, look up works, editions, and ISBNs, enumerate every edition of a work, read community ratings, and resolve cover-image URLs. Fully keyless public API. Includes the OL…M/W/A key-graph reference, ISBN 302-redirect resolution, search query…