{"id":45677552,"url":"https://github.com/juan294/cc-rpi","last_synced_at":"2026-05-02T07:05:15.411Z","repository":{"id":339721375,"uuid":"1162865792","full_name":"juan294/cc-rpi","owner":"juan294","description":"Blueprint repository for Claude Code projects — RPI methodology, known agent error patterns, operational rules, and project templates","archived":false,"fork":false,"pushed_at":"2026-03-26T07:16:41.000Z","size":548,"stargazers_count":3,"open_issues_count":0,"forks_count":1,"subscribers_count":0,"default_branch":"main","last_synced_at":"2026-03-26T11:52:08.410Z","etag":null,"topics":["ai-agents","best-practices","claude-code","developer-tools","error-patterns","llm","methodology","prompt-engineering"],"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/juan294.png","metadata":{"files":{"readme":"README.md","changelog":"CHANGELOG.md","contributing":"CONTRIBUTING.md","funding":null,"license":"LICENSE","code_of_conduct":"CODE_OF_CONDUCT.md","threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":"SECURITY.md","support":null,"governance":null,"roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null,"zenodo":null,"notice":null,"maintainers":null,"copyright":null,"agents":null,"dco":null,"cla":null},"funding":{"github":["juan294"]}},"created_at":"2026-02-20T19:45:52.000Z","updated_at":"2026-03-26T07:16:44.000Z","dependencies_parsed_at":"2026-03-14T10:02:25.120Z","dependency_job_id":null,"html_url":"https://github.com/juan294/cc-rpi","commit_stats":null,"previous_names":["juan294/cc-rpi"],"tags_count":20,"template":false,"template_full_name":null,"purl":"pkg:github/juan294/cc-rpi","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/juan294%2Fcc-rpi","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/juan294%2Fcc-rpi/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/juan294%2Fcc-rpi/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/juan294%2Fcc-rpi/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/juan294","download_url":"https://codeload.github.com/juan294/cc-rpi/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/juan294%2Fcc-rpi/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":286080680,"owners_count":31312744,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2026-04-02T12:59:32.332Z","status":"ssl_error","status_checked_at":"2026-04-02T12:54:48.875Z","response_time":89,"last_error":"SSL_connect returned=1 errno=0 peeraddr=140.82.121.5:443 state=error: 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":["ai-agents","best-practices","claude-code","developer-tools","error-patterns","llm","methodology","prompt-engineering"],"created_at":"2026-02-24T13:07:24.949Z","updated_at":"2026-05-02T07:05:15.392Z","avatar_url":"https://github.com/juan294.png","language":"Shell","funding_links":["https://github.com/sponsors/juan294"],"categories":[],"sub_categories":[],"readme":"# cc-rpi — Claude Code Reference \u0026 Project Intelligence\n\n[![CI](https://github.com/juan294/cc-rpi/actions/workflows/validate.yml/badge.svg)](https://github.com/juan294/cc-rpi/actions/workflows/validate.yml)\n[![Version: v1.18.0](https://img.shields.io/badge/Version-v1.18.0-orange.svg)](https://github.com/juan294/cc-rpi/releases/tag/v1.18.0)\n[![License: MIT](https://img.shields.io/badge/License-MIT-blue.svg)](LICENSE)\n[![Status: Active](https://img.shields.io/badge/Status-Active-brightgreen.svg)]()\n[![Claude Code](https://img.shields.io/badge/Built%20for-Claude%20Code-blueviolet.svg)](https://docs.anthropic.com/en/docs/claude-code)\n\n![Chapa Badge](https://chapa.thecreativetoken.com/u/juan294/badge.svg)\n\nA blueprint repository for setting up and running projects with [Claude Code](https://docs.anthropic.com/en/docs/claude-code), with a Codex compatibility layer via `AGENTS.md`. Contains the RPI (Research-Plan-Implement) methodology, a catalog of known agent errors, and operational rules learned from hundreds of real sessions.\n\n---\n\n## Requirements\n\n- [Claude Code](https://docs.anthropic.com/en/docs/claude-code) CLI installed and configured\n- Git\n\n## Quick Start\n\nClone the repository:\n\n```bash\ngit clone https://github.com/juan294/cc-rpi.git\n```\n\nThen tell Claude Code in your target project:\n\n\u003e Go read the cc-rpi repository and set up this project following all the best practices. Read the quick reference and methodology first, use the error-patterns skill or full error catalog only if needed, then configure CLAUDE.md, AGENTS.md, and slash commands for this project.\n\nBootstrapped and adopted projects now also get an `AGENTS.md`\ncompatibility layer so the same methodology can be operated from Codex /\nGPT-5.x without changing the workflow.\n\nIf you also use Codex, the blueprint ships a Codex-only\n`codex-simplify` skill at `cc-rpi/.codex/skills/codex-simplify/`.\nCopy it into `~/.codex/skills/codex-simplify/` if you want a reusable\nequivalent of Claude Code's native `/simplify` without creating a\nproject skill named `simplify`.\n\n## Harness Scope\n\n**Principle: one harness per blueprint.** cc-rpi is authored for Claude\nCode and maintained for a single author syncing 15+ downstream\nprojects. Every additional harness is ongoing sync surface --\nparallel command trees, parallel wrappers, extra work in `/update` on\nevery blueprint bump -- so by default new harness support lives\noutside this repo.\n\n**Codex is the one exception.** `AGENTS.md` is a widely adopted\ncross-agent markdown convention that Codex reads natively, so the\ncompatibility layer is a single file and a handful of translations,\nnot a parallel command tree. The ongoing cost is low enough to carry\nupstream without dragging on `/update` across every project.\n\nOther harnesses (OpenCode, GitHub Copilot, etc.) are better served by\nsibling projects or community-maintained overlays. [copilot-rpi][] is\nmaintained as a separate repository rather than layered on top of\ncc-rpi for exactly this reason. For an ad-hoc harness such as\nOpenCode, the recommended path is a small overlay repo with a\ngenerator script that derives the harness-specific command directory\nfrom `.claude/commands/`, a long-lived downstream fork, or a minimal\n`AGENTS.md` + harness config file with no command wrappers at all.\n\n[copilot-rpi]: https://github.com/juan294/copilot-rpi\n\n## Guide\n\nNew here? Read **[GUIDE.md](GUIDE.md)** — a human-readable walkthrough of the philosophy, the workflow, and every command. It covers everything you need to know without diving into every file. Also works great as source material for NotebookLM podcasts or articles.\n\n## What's Inside\n\n### Methodology (`methodology/`)\n\nThe full Research-Plan-Implement pattern adapted for Claude Code, based on HumanLayer's opencode-rpi and ACE-FCA framework. Organized by topic (10 files, in reading order):\n\n- **Philosophy** — Core tenets, error amplification principle, mental alignment\n- **Context Engineering** — The foundational discipline: compaction, context quality, settings \u0026 permissions\n- **Four Phases** — Research, Plan, Implement, Validate with detailed processes\n- **Agent Design** — Documentarian rule, tool restrictions, subagent catalog, Anthropic-native commands (`/simplify`, `/batch`), agent teams, autonomy principles\n- **Pseudocode Notation** — Compact notation for writing implementation plans\n- **Testing** — Automated-first verification hierarchy, TDD protocol\n- **Push Accountability** — Post-push CI ownership, background polling, fix-and-repush cycle\n- **CI \u0026 Guardrails** — Pre-commit hooks, CI workflows, development guardrails, enforcement stack\n- **Scheduled Agents** — Recurring quality agents on cron/launchd, shared context system\n- **Error \u0026 Success Logging** — Framework for systematic improvement\n\n### Known Error Patterns (`patterns/`)\n\nA catalog of recurring Claude Code agent errors documented from real sessions. Each entry includes the symptom, root cause, correct approach, and what to avoid:\n\n- Shell behavior (parallel calls, cwd resets, tilde paths)\n- Git operations (worktrees, pre-commit hooks, push rejections)\n- GitHub CLI (`gh` field names, CI status checking)\n- Node.js/TypeScript (ESM shebangs, Buffer vs string)\n- CI \u0026 workflow (push-and-forget, skipping TDD, suggesting manual steps)\n\n### Examples (`examples/`)\n\nSample documents illustrating the methodology in practice — a research document, implementation plan with phase files, error/success log entries, and additional pseudocode notation examples. Use these as reference when producing your own RPI artifacts.\n\n### Templates (`templates/`)\n\nReady-to-use starting points for new projects:\n\n- **CLAUDE.md template** — Slim project configuration (~70 lines) with universal instructions\n- **AGENTS.md template** — Codex compatibility layer that teaches Codex how to interpret the cc-rpi `.claude/` layout\n- **Codex-only skills** — `.codex/skills/` holds personal Codex helpers\n  that intentionally stay outside `.claude/skills/`; currently includes\n  `codex-simplify`\n- **Rule templates** — `.claude/rules/` files with conditional loading (deployment, Supabase, testing) and universal rules (RPI details, push accountability)\n- **settings.json template** — `.claude/settings.json` with Agent Teams, hooks, and permissions\n- **Setup checklist** — Step-by-step guide including rules, skills, hooks, CI, and scheduled agents\n- **Slash commands** — `/bootstrap`, `/adopt`, `/update`, `/research`, `/plan`, `/implement`, `/validate`, `/describe-pr`, `/pre-launch`, `/remediate`, `/triage`, `/status`, `/fix-ci` — plus Anthropic-native `/simplify` and `/batch`\n- **Scheduled agent scripts** — Nightly blueprint sync and multi-project morning triage with launchd/cron templates\n\n## Adding New Patterns\n\nWhen you discover a new recurring error or best practice:\n\n1. Add it to `patterns/agent-errors.md` (detailed entry with symptom/root cause/solution)\n2. Add a one-liner to `patterns/quick-reference.md`\n3. Keep entries generic — no project-specific references\n\nSee [CONTRIBUTING.md](CONTRIBUTING.md) for full guidelines.\n\n## Community\n\n- [GitHub Discussions](https://github.com/juan294/cc-rpi/discussions) — Ask questions, share ideas, discuss the methodology\n- [Contributing Guide](CONTRIBUTING.md) — How to report patterns, propose improvements, submit PRs\n- [Code of Conduct](CODE_OF_CONDUCT.md) — Expected behavior for all participants\n\n## Credits\n\n- [HumanLayer](https://humanlayer.dev/) — ACE-FCA framework and opencode-rpi implementation\n- Adapted for Claude Code's native capabilities (CLAUDE.md, Task tool, slash commands)\n\n## License\n\n[MIT](LICENSE)\n\n## Changelog\n\nSee [CHANGELOG.md](CHANGELOG.md) for release history.\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fjuan294%2Fcc-rpi","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fjuan294%2Fcc-rpi","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fjuan294%2Fcc-rpi/lists"}