{"id":51845042,"url":"https://github.com/davdittrich/planning-with-beads","last_synced_at":"2026-07-23T11:01:16.256Z","repository":{"id":353798627,"uuid":"1220957383","full_name":"davdittrich/planning-with-beads","owner":"davdittrich","description":"Persistent task \u0026 knowledge management for AI agents via Beads system. Based on Manus context engineering principles.","archived":false,"fork":false,"pushed_at":"2026-05-30T22:48:05.000Z","size":55,"stargazers_count":0,"open_issues_count":0,"forks_count":0,"subscribers_count":0,"default_branch":"master","last_synced_at":"2026-05-31T00:19:15.649Z","etag":null,"topics":["agent-skills","ai-agents","beads","claude-extension","context-engineering","manus","persistent-memory","planning","productivity","skill-md","task-management"],"latest_commit_sha":null,"homepage":null,"language":"Shell","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":null,"status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/davdittrich.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":null,"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":null,"dco":null,"cla":null}},"created_at":"2026-04-25T15:07:23.000Z","updated_at":"2026-05-30T22:48:09.000Z","dependencies_parsed_at":null,"dependency_job_id":null,"html_url":"https://github.com/davdittrich/planning-with-beads","commit_stats":null,"previous_names":["davdittrich/planning-with-beads"],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/davdittrich/planning-with-beads","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/davdittrich%2Fplanning-with-beads","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/davdittrich%2Fplanning-with-beads/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/davdittrich%2Fplanning-with-beads/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/davdittrich%2Fplanning-with-beads/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/davdittrich","download_url":"https://codeload.github.com/davdittrich/planning-with-beads/tar.gz/refs/heads/master","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/davdittrich%2Fplanning-with-beads/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":286080680,"owners_count":35800203,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2026-07-20T02:08:10.276Z","status":"online","status_checked_at":"2026-07-23T02:00:06.683Z","response_time":57,"last_error":null,"robots_txt_status":"success","robots_txt_updated_at":"2025-07-24T06:49:26.215Z","robots_txt_url":"https://github.com/robots.txt","online":true,"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":["agent-skills","ai-agents","beads","claude-extension","context-engineering","manus","persistent-memory","planning","productivity","skill-md","task-management"],"created_at":"2026-07-23T11:01:15.442Z","updated_at":"2026-07-23T11:01:16.250Z","avatar_url":"https://github.com/davdittrich.png","language":"Shell","funding_links":[],"categories":[],"sub_categories":[],"readme":"# Planning with Beads\n\nA persistent task and knowledge management skill for AI agents, based on Manus context engineering principles and powered by the **Beads (`bd`)** system.\n\n## Overview\n\nPlanning with Beads replaces volatile file-based planning with a structured, graph-based issue tracker. It ensures that your AI agent maintains a consistent goal, tracks every discovery, and never repeats failed attempts—even across multiple sessions or after context window resets.\n\n## Key Features\n\n- **Hermetic Ticket Architecture**: Enforces execution-ready tickets with explicit scope, input/output schemas, and execution guards.\n- **Persistent Memory**: Uses Beads to store tasks, findings, and decisions on disk.\n- **Context Engineering**: Implements Manus principles like \"Attention Manipulation via Recitation\" using `bd prime`.\n- **Atomic Workflows**: Enforces one ticket per atomic task and immediate bug tracking.\n- **Fail Pattern Prevention**: Includes explicit rules to prevent repetitive mistakes.\n- **2-Action Rule**: Ensures every discovery is captured before it's lost from the agent's memory.\n- **Automation Scripts**: Helper scripts for session initialization and completion verification.\n\n## Getting Started\n\n1. **Initialize Session**:\n   The fastest way to start is using the initialization script:\n   ```bash\n   ./scripts/init-session.sh \"Your Project Goal\"\n   ```\n   This initializes Beads and scaffolds an Epic with default phases (Discovery, Planning, Implementation, Verification).\n\n2. **Claim and Prime**:\n   Find an unblocked task and load context:\n   ```bash\n   bd ready\n   bd update \u003ctask_id\u003e --claim\n   bd prime\n   ```\n\n3. **Verify Completion**:\n   When finished with a session or an Epic:\n   ```bash\n   ./scripts/check-complete.sh\n   ```\n\n## Manus Principles Integration\n\nThis skill is designed around the 6 Manus Principles for high-performance AI agents:\n1. KV-Cache Optimization\n2. Masking vs. Removal\n3. Filesystem as External Memory\n4. Attention Manipulation via Recitation\n5. Persistence of \"Wrong Turns\"\n6. Anti-Few-Shotting Resilience\n\n## Documentation\n\n- [SKILL.md](SKILL.md): Core rules and command reference.\n- [reference.md](reference.md): Deep dive into Manus principles with Beads.\n- [examples.md](examples.md): Practical workflow examples.\n\n## License\n\nMIT\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fdavdittrich%2Fplanning-with-beads","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fdavdittrich%2Fplanning-with-beads","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fdavdittrich%2Fplanning-with-beads/lists"}