{"id":48019794,"url":"https://github.com/pr0ck0/ai-config","last_synced_at":"2026-04-14T22:00:19.298Z","repository":{"id":349017883,"uuid":"1200735437","full_name":"PR0CK0/ai-config","owner":"PR0CK0","description":"Agent config for ontology-driven LLM development. One source, minimal surface, secure by default.","archived":false,"fork":false,"pushed_at":"2026-04-03T19:41:29.000Z","size":40,"stargazers_count":1,"open_issues_count":0,"forks_count":0,"subscribers_count":0,"default_branch":"main","last_synced_at":"2026-04-04T13:51:02.264Z","etag":null,"topics":["agents","agents-md","ai-config","claude-code","codex","cursor","developer-tools","gemini","knowledge-graph","llm","ontology","openai","owl","rdf","secure-by-default","sparql","tdd"],"latest_commit_sha":null,"homepage":null,"language":"Shell","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"mit","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/PR0CK0.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":"LICENSE","code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null,"governance":null,"roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null,"zenodo":null,"notice":null,"maintainers":null,"copyright":null,"agents":"AGENTS.md","dco":null,"cla":null}},"created_at":"2026-04-03T19:09:01.000Z","updated_at":"2026-04-03T20:16:15.000Z","dependencies_parsed_at":null,"dependency_job_id":null,"html_url":"https://github.com/PR0CK0/ai-config","commit_stats":null,"previous_names":["pr0ck0/ai-config"],"tags_count":1,"template":false,"template_full_name":null,"purl":"pkg:github/PR0CK0/ai-config","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/PR0CK0%2Fai-config","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/PR0CK0%2Fai-config/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/PR0CK0%2Fai-config/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/PR0CK0%2Fai-config/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/PR0CK0","download_url":"https://codeload.github.com/PR0CK0/ai-config/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/PR0CK0%2Fai-config/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":286080680,"owners_count":31817128,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2026-04-14T18:05:02.291Z","status":"ssl_error","status_checked_at":"2026-04-14T18:05:01.765Z","response_time":153,"last_error":"SSL_read: unexpected eof while reading","robots_txt_status":"success","robots_txt_updated_at":"2025-07-24T06:49:26.215Z","robots_txt_url":"https://github.com/robots.txt","online":false,"can_crawl_api":true,"host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"keywords":["agents","agents-md","ai-config","claude-code","codex","cursor","developer-tools","gemini","knowledge-graph","llm","ontology","openai","owl","rdf","secure-by-default","sparql","tdd"],"created_at":"2026-04-04T13:46:13.517Z","updated_at":"2026-04-14T22:00:19.227Z","avatar_url":"https://github.com/PR0CK0.png","language":"Shell","funding_links":[],"categories":[],"sub_categories":[],"readme":"# ai-config\n\n\u003e Agent config for ontology-driven LLM development. One source, minimal surface, secure by default.\n\n[![License: MIT](https://img.shields.io/badge/License-MIT-yellow.svg)](LICENSE)\n[![Claude Code](https://img.shields.io/badge/Claude%20Code-compatible-blue?logo=anthropic)](https://claude.ai/code)\n[![Cursor](https://img.shields.io/badge/Cursor-compatible-purple)](https://cursor.sh)\n[![Gemini CLI](https://img.shields.io/badge/Gemini%20CLI-compatible-4285F4?logo=google)](https://github.com/google-gemini/gemini-cli)\n[![Codex CLI](https://img.shields.io/badge/Codex%20CLI-compatible-black?logo=openai)](https://github.com/openai/codex)\n\nOne file. One source. No drift.\n\n---\n\n## Philosophy\n\nRules here are **organizational scar tissue** — grown from real incidents, not upfront design. A rule gets added the second a mistake repeats. Nothing is added speculatively.\n\n- **One source.** Edit `AGENTS.md` only. `build.sh` generates all tool-specific aliases.\n- **Minimal surface.** Short rules shape judgment. Long rules get ignored — and the middle ones get ignored most. Research shows LLMs reliably attend to the beginning and end of long contexts, with significant degradation in between ([Liu et al., 2023 — \"Lost in the Middle\"](https://arxiv.org/abs/2307.03172)). Keep `AGENTS.md` short and front-load what matters.\n- **Ontology-grounded.** Models, schemas, and knowledge graphs are first-class.\n- **TDD.** Every function ships with a test. Red → green → refactor, always.\n- **Secure.** No hardcoded paths, tokens, or secrets. Ever.\n\n---\n\n## Structure\n\n```\nai-config/\n├── AGENTS.md              ← single source of truth — edit this only\n├── build.sh               ← generates all tool folders + wires git hooks\n├── claude/\n│   ├── CLAUDE.md          ← generated\n│   ├── settings.json      ← model, hooks, statusline config\n│   ├── agents/            ← 8 specialist sub-agents\n│   ├── hooks/             ← session management, context injection, statusline\n│   └── commands/          ← /-check, /-ship, /-review, /-discover, /-session, /-sync\n├── cursor/\n│   ├── user-rules.md      ← generated — paste into Settings → Rules for AI\n│   └── rules/\n│       └── global.mdc     ← generated — drop into .cursor/rules/ per project\n├── gemini/\n│   └── GEMINI.md          ← generated\n└── codex/\n    └── AGENTS.md          ← generated\n```\n\nEach tool folder is built exhaustively. You only need the generated config file for your tool — the rest (agents, hooks, commands) is Claude Code-specific.\n\n---\n\n## Install\n\n**1. Clone and build:**\n```bash\ngit clone https://github.com/PR0CK0/ai-config.git ~/ai-config\ncd ~/ai-config\n./build.sh        # generates all tool folders + wires pre-push hook\n```\n\n**2. Claude Code — rules only (drop-in):**\n```bash\ncp ~/ai-config/claude/CLAUDE.md ~/.claude/CLAUDE.md\n```\n\n**Claude Code — full setup (agents, hooks, slash commands, statusline):**\n```bash\ncp ~/ai-config/claude/CLAUDE.md ~/.claude/CLAUDE.md\ncp ~/ai-config/claude/settings.json ~/.claude/settings.json\ncp -r ~/ai-config/claude/agents ~/.claude/agents\ncp -r ~/ai-config/claude/hooks ~/.claude/hooks\ncp -r ~/ai-config/claude/commands ~/.claude/commands\nchmod +x ~/.claude/hooks/statusline.sh\n```\n\n**3. Cursor — global rules:**\nPaste `cursor/user-rules.md` content into Cursor → Settings → Rules for AI.\n\n**Cursor — per-project:**\n```bash\nmkdir -p .cursor/rules \u0026\u0026 cp ~/ai-config/cursor/rules/global.mdc .cursor/rules/\n```\n\n**4. Gemini CLI:**\n```bash\nmkdir -p ~/.gemini \u0026\u0026 cp ~/ai-config/gemini/GEMINI.md ~/.gemini/GEMINI.md\n```\n\n**5. Codex CLI:**\n```bash\ncp ~/ai-config/codex/AGENTS.md ~/AGENTS.md   # global\n# or copy to project root for per-project\n```\n\n**Per-project pointer (any tool):**\n```bash\necho \"READ ~/ai-config/AGENTS.md BEFORE ANYTHING\" \u003e AGENTS.md\n```\n\n**Symlinks instead of copies:**\n```bash\n./build.sh --symlink\n```\n\n\u003e `build.sh` wires `.githooks/pre-push` automatically — if `AGENTS.md` changes, the hook rebuilds all aliases and blocks the push until generated files are committed.\n\n---\n\n## Inspiration\n\n| Source | What it contributed |\n|--------|---------------------|\n| [steipete/agent-scripts](https://github.com/steipete/agent-scripts) | Git safety rules, atomic commit discipline, the pointer pattern |\n| [steipete — Just Talk To It](https://steipete.me/posts/just-talk-to-it) | \"Organizational scar tissue\" philosophy; blast-radius thinking |\n| [forrestchang/andrej-karpathy-skills](https://github.com/forrestchang/andrej-karpathy-skills) | Think Before Coding, Simplicity First, Surgical Changes, Goal-Driven Execution |\n| Home-grown | Ontologist + modeler agents, session hooks, slash commands, statusline |\n\n---\n\n## License\n\nMIT\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fpr0ck0%2Fai-config","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fpr0ck0%2Fai-config","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fpr0ck0%2Fai-config/lists"}