philosopher-OKF
llms.txt99 starsChanged 37 days agoMITView on GitHub
A skill for AI agents that turns any topic into one self-contained, white, research-paper-style HTML study page: CSS-drawn diagrams, a concept map, and references that always resolve. The knowledge lives in an Open Knowledge Format (OKF) bundle: plain Markdown, one file per concern, loaded only when the run's depth needs it. Start at okf/index.md, fetch okf/core/workflow.md next, follow its 8 steps and lazy load table, and fetch only what the depth asks for. Per-run token budgets: brief ~12k, standard ~25k,…
In this repositoryOne other file it gives its agents.
- philosopherSkill
The file
We split this llms.txt into the rules it gives an agent
1 rule. About 0 are common, 1 is distinctive, and 0 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈1
Distinctive · estimate
This author's own choices. Worth a look.
0
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 5
Start at okf/index.md, fetch okf/core/workflow.md next, follow its 8 steps and lazy load
≈ “Common” is an estimate: at least 1 in 5 of the 3,592 llms.txt files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
# Philosopher (phil-OKF) > A skill for AI agents that turns any topic into one self-contained, white, research-paper-style HTML study page: CSS-drawn diagrams, a concept map, and references that always resolve. The knowledge lives in an Open Knowledge Format (OKF) bundle: plain Markdown, one file per concern, loaded only when the run's depth needs it. Start at [okf/index.md](https://raw.githubusercontent.com/frypan05/philosopher-OKF/main/okf/index.md), fetch [okf/core/workflow.md](https://raw.githubusercontent.com/frypan05/philosopher-OKF/main/okf/core/workflow.md) next, follow its 8 steps and lazy load table, and fetch only what the depth asks for. Per-run token budgets: brief ~12k, standard ~25k, deep ~45k. ## Entry points - [SKILL.md](https://raw.githubusercontent.com/frypan05/philosopher-OKF/main/SKILL.md): entry point for skill-aware agents (Claude Code, Cursor, Codex); route the question, then follow the bundle - [okf/index.md](https://raw.githubusercontent.com/frypan05/philosopher-OKF/main/okf/index.md): bundle root; lists every core file and all 12 domains without requiring them to be read - [okf/core/workflow.md](https://raw.githubusercontent.com/frypan05/philosopher-OKF/main/okf/core/workflow.md): the 8 steps, the lazy load table, research caps, and the output rules - [okf/core/classifier.md](https://raw.githubusercontent.com/frypan05/philosopher-OKF/main/okf/core/classifier.md): routes a question to one of 12 domains by keyword and intent - [philosopher.md](https://raw.githubusercontent.com/frypan05/philosopher-OKF/main/philosopher.md): single-file build of the whole skill for chat apps that cannot fetch several files; regenerated from okf/ on every push, never edited by hand ## Core files - [okf/core/page-template.md](https://raw.githubusercontent.com/frypan05/philosopher-OKF/main/okf/core/page-template.md): base CSS and HTML skeleton every output uses; Optional CSS is the last section, read only if a planned component needs it - [okf/core/source-policy.md](https://raw.githubusercontent.com/frypan05/philosopher-OKF/main/okf/core/source-policy.md): allowed sources, citation format, and the never-fabricate-a-source rule - [okf/core/audience-depth.md](https://raw.githubusercontent.com/frypan05/philosopher-OKF/main/okf/core/audience-depth.md): reading levels, brief/standard/deep depth rules, and the word and reference budgets - [okf/core/knowledge-graph.md](https://raw.githubusercontent.com/frypan05/philosopher-OKF/main/okf/core/knowledge-graph.md): concept-map method used by deep runs - [okf/core/writing-rules.md](https://raw.githubusercontent.com/frypan05/philosopher-OKF/main/okf/core/writing-rules.md): prose rules and self-check, read at every depth - [okf/core/writing-detection.md](https://raw.githubusercontent.com/frypan05/philosopher-OKF/main/okf/core/writing-detection.md): word lists, heading anti-patterns, and structural thresholds, read at deep depth - [okf/core/output-contract.md](https://raw.githubusercontent.com/frypan05/philosopher-OKF/main/okf/core/output-contract.md): pointer stub; its rules live in workflow.md ## Domains - [okf/domains/index.md](https://raw.githubusercontent.com/frypan05/philosopher-OKF/main/okf/domains/index.md): the 12 study domains (technology and engineering, medical and health, natural sciences, mathematics, finance, economics, business, law, humanities, social sciences, research papers, general); each domain file opens with a Quick card, the only part read at brief depth ## Docs and examples - [README.md](https://raw.githubusercontent.com/frypan05/philosopher-OKF/main/README.md): install and usage matrix (folder, URL, text prompt, MCP) plus validation and extension steps - [examples/sample-flamingo-reading-guide.html](https://raw.githubusercontent.com/frypan05/philosopher-OKF/main/examples/sample-flamingo-reading-guide.html): a finished page, in full HTML source - [Repository](https://github.com/frypan05/philosopher-OKF): clone, browse the rendered files, and raise issues ## Optional - [scripts/validate.sh](https://raw.githubusercontent.com/frypan05/philosopher-OKF/main/scripts/validate.sh): OKF conformance and link check; run with `bash scripts/validate.sh okf` - [okf/log.md](https://raw.githubusercontent.com/frypan05/philosopher-OKF/main/okf/log.md): dated change history of the bundle
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.