{"id":49035583,"url":"https://github.com/dollardill/beads-superpowers","last_synced_at":"2026-04-25T08:01:37.757Z","repository":{"id":349504986,"uuid":"1202538987","full_name":"DollarDill/beads-superpowers","owner":"DollarDill","description":"Claude Code plugin merging Superpowers skills with Beads issue tracking. 15 mandatory skills + persistent task memory for AI coding agents.","archived":false,"fork":false,"pushed_at":"2026-04-19T09:30:29.000Z","size":569,"stargazers_count":4,"open_issues_count":2,"forks_count":0,"subscribers_count":1,"default_branch":"main","last_synced_at":"2026-04-19T11:34:28.891Z","etag":null,"topics":["ai-agents","beads","claude-code","claude-code-plugin","developer-tools","issue-tracker","superpowers","tdd"],"latest_commit_sha":null,"homepage":"https://github.com/DollarDill/beads-superpowers#readme","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/DollarDill.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":"AGENTS.md","dco":null,"cla":null}},"created_at":"2026-04-06T06:02:42.000Z","updated_at":"2026-04-19T09:30:09.000Z","dependencies_parsed_at":null,"dependency_job_id":null,"html_url":"https://github.com/DollarDill/beads-superpowers","commit_stats":null,"previous_names":["dollardill/beads-superpowers"],"tags_count":5,"template":false,"template_full_name":null,"purl":"pkg:github/DollarDill/beads-superpowers","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/DollarDill%2Fbeads-superpowers","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/DollarDill%2Fbeads-superpowers/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/DollarDill%2Fbeads-superpowers/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/DollarDill%2Fbeads-superpowers/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/DollarDill","download_url":"https://codeload.github.com/DollarDill/beads-superpowers/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/DollarDill%2Fbeads-superpowers/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":286080680,"owners_count":32254714,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2026-04-25T04:23:17.126Z","status":"ssl_error","status_checked_at":"2026-04-25T04:21:53.360Z","response_time":59,"last_error":"SSL_connect returned=1 errno=0 peeraddr=140.82.121.6:443 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","beads","claude-code","claude-code-plugin","developer-tools","issue-tracker","superpowers","tdd"],"created_at":"2026-04-19T11:01:57.476Z","updated_at":"2026-04-25T08:01:37.750Z","avatar_url":"https://github.com/DollarDill.png","language":"Shell","funding_links":[],"categories":[],"sub_categories":[],"readme":"\u003cp align=\"center\"\u003e\n  \u003cimg src=\"assets/banner.svg\" alt=\"beads-superpowers — Process discipline and persistent memory for AI coding agents\" width=\"100%\" /\u003e\n\u003c/p\u003e\n\n\u003cp align=\"center\"\u003e\n  \u003cem\u003eProcess discipline and persistent memory for AI coding agents.\u003c/em\u003e\n\u003c/p\u003e\n\n\u003cp align=\"center\"\u003e\n  \u003ca href=\"LICENSE\"\u003e\u003cimg alt=\"License: MIT\" src=\"https://img.shields.io/badge/license-MIT-blue.svg\"\u003e\u003c/a\u003e\n  \u003ca href=\".claude-plugin/plugin.json\"\u003e\u003cimg alt=\"Plugin version\" src=\"https://img.shields.io/badge/plugin-v0.4.1-4f46e5.svg\"\u003e\u003c/a\u003e\n  \u003ca href=\"https://github.com/DollarDill/beads-superpowers/actions/workflows/release.yml\"\u003e\u003cimg alt=\"Release\" src=\"https://github.com/DollarDill/beads-superpowers/actions/workflows/release.yml/badge.svg\"\u003e\u003c/a\u003e\n  \u003ca href=\"https://github.com/DollarDill/beads-superpowers/stargazers\"\u003e\u003cimg alt=\"GitHub stars\" src=\"https://img.shields.io/github/stars/DollarDill/beads-superpowers?style=social\"\u003e\u003c/a\u003e\n\u003c/p\u003e\n\n---\n\n## Try it in 60 seconds\n\n### Option A: Claude Code Marketplace (recommended)\n\n```bash\nclaude plugin marketplace add DollarDill/beads-superpowers\nclaude plugin install beads-superpowers@beads-superpowers-marketplace\n```\n\n### Option B: npx (via Vercel Skills CLI)\n\n```bash\nnpx skills add DollarDill/beads-superpowers --all -y -g\n```\n\nAfter installing, tell Claude: **\"Run the setup skill\"** — this configures the SessionStart hook that makes skills activate automatically.\n\n### Option C: curl (one command, no dependencies)\n\n```bash\ncurl -fsSL https://raw.githubusercontent.com/DollarDill/beads-superpowers/main/install.sh | bash\n```\n\nInstalls 20 skills to `~/.claude/skills/` and configures the SessionStart hook automatically. Supports `--yes` (CI mode), `--version X.Y.Z`, `--dry-run`, and `--uninstall`. See [install.sh](install.sh) for details.\n\n### Then, in any project\n\n```bash\ncd your-project\nbd init\n```\n\nIn Claude Code, run `/skills` to verify — you should see 20 skills available.\n\n\u003cdetails\u003e\n\u003csummary\u003eIf you previously ran \u003ccode\u003ebd setup claude\u003c/code\u003e\u003c/summary\u003e\n\nThe plugin's SessionStart hook already runs `bd prime`. Remove the duplicate hooks:\n\n```bash\nbd setup claude --remove\n```\n\n\u003c/details\u003e\n\n## Why it exists\n\nAI coding agents have two recurring failure modes:\n\n1. **No process discipline.** They skip tests, rush to code, and claim work is done without verification.\n2. **No persistent memory.** Todo lists vanish when a session ends. The next session starts blind.\n\n**beads-superpowers** merges two upstream systems to solve both at once:\n\n- **[Superpowers](https://github.com/obra/superpowers)** by Jesse Vincent — 20 mandatory skills enforcing TDD, brainstorming, systematic debugging, and two-stage code review.\n- **[Beads](https://github.com/gastownhall/beads)** by Steve Yegge — a Dolt-backed issue tracker that survives across sessions, agents, and projects.\n\nThe result: skills that don't just tell agents *how* to work — they give agents a persistent ledger to track *what* they're working on.\n\n## How it works\n\n```text\nSession Start\n  │\n  ▼\nSessionStart hook fires automatically\n  ├── Injects using-superpowers skill (skill routing + beads awareness)\n  └── Runs bd prime (beads CLI context + persistent memories)\n  │\n  ▼\nAgent receives task from user\n  │\n  ▼\nSkill system activates\n  ├── brainstorming → design spec → user approval\n  ├── writing-plans → implementation plan → beads created for each task\n  ├── subagent-driven-development → execute tasks → two-stage review\n  │     └── Per task: bd create → bd update --claim → implement → bd close\n  └── finishing-a-development-branch → merge/PR → Land the Plane\n  │\n  ▼\nLand the Plane (mandatory session close)\n  ├── bd close \u003ccompleted-beads\u003e --reason \"description\"\n  ├── bd dolt push (sync beads to Dolt remote)\n  ├── git push (sync code to remote)\n  └── git status (verify clean state)\n```\n\nThe `using-superpowers` skill (loaded at every session start) enforces:\n\n\u003e **IF A SKILL APPLIES TO YOUR TASK, YOU DO NOT HAVE A CHOICE. YOU MUST USE IT.**\n\nSkills are not suggestions. They use bright-line rules, anti-rationalization tables, and empirically-tested enforcement language. See [`docs/METHODOLOGY.md`](docs/METHODOLOGY.md) for the research basis.\n\n## Skills reference\n\n| Skill | Category | When to use |\n|-------|----------|-------------|\n| **using-superpowers** | Meta | Every session start — routes to the right skill |\n| **brainstorming** | Design | Before any creative work — explores design before code |\n| **writing-plans** | Planning | After design approval — creates bite-sized task plans |\n| **subagent-driven-development** | Execution | Execute plans with fresh subagent per task + two-stage review |\n| **executing-plans** | Execution | Execute plans in a single session with checkpoints |\n| **test-driven-development** | Quality | Any feature or bugfix — RED-GREEN-REFACTOR cycle |\n| **systematic-debugging** | Quality | Any bug or test failure — 4-phase root cause analysis |\n| **verification-before-completion** | Quality | Before any \"done\" claim — evidence before assertions |\n| **requesting-code-review** | Review | After implementation — dispatches code reviewer |\n| **receiving-code-review** | Review | When receiving feedback — anti-sycophancy review reception |\n| **using-git-worktrees** | Infrastructure | Isolated development branches with safety checks |\n| **finishing-a-development-branch** | Infrastructure | Merge/PR decision tree + Land the Plane protocol |\n| **dispatching-parallel-agents** | Advanced | 2+ independent tasks without shared state |\n| **writing-skills** | Meta | Creating or modifying skills — TDD for process docs |\n| **document-release** | Quality | Post-ship documentation audit — syncs docs to match shipped code |\n| **project-init** | Infrastructure | Beads/Dolt DB setup, bootstrap, and recovery |\n| **stress-test** | Design | Adversarial interrogation of designs/plans with recommended answers |\n| **setup** | Infrastructure | Post-npx hook installation — configures SessionStart for skills auto-activation |\n| **auditing-upstream-drift** | Meta | Periodic audit for staleness vs upstream superpowers and beads |\n| **getting-up-to-speed** | Meta | Start of session or post-compaction — runs bd commands, deep-dives the codebase, produces a structured current-state summary |\n\n### Beads commands used in skills\n\n| Action | Command | Used in |\n|--------|---------|---------|\n| Create epic | `bd create \"Epic: name\" -t epic` | subagent-driven-dev, executing-plans |\n| Create task | `bd create \"Task: name\" -t task --parent \u003cepic\u003e` | subagent-driven-dev, executing-plans |\n| Claim work | `bd update \u003cid\u003e --claim` | executing-plans |\n| Complete work | `bd close \u003cid\u003e --reason \"description\"` | all execution skills |\n| Check remaining | `bd ready --parent \u003cepic\u003e` | subagent-driven-dev, executing-plans |\n| Add dependency | `bd dep add \u003cchild\u003e \u003cparent\u003e` | subagent-driven-dev, writing-plans |\n| Store learning | `bd remember \"insight\"` | any session |\n| Sync to remote | `bd dolt push` | finishing-a-development-branch |\n| Session context | `bd prime` | SessionStart hook (automatic) |\n\n## Architecture\n\n```mermaid\nflowchart TB\n    User[User prompt] --\u003e Orchestrator\n    subgraph Orchestrator [Main Agent — orchestrator-only beads]\n        SP[using-superpowers skill]\n        BD[bd prime — beads context]\n        SP --\u003e Routing{Route to skill}\n        BD --\u003e Routing\n    end\n    Routing --\u003e|design| Brainstorm[brainstorming]\n    Routing --\u003e|plan| WP[writing-plans]\n    Routing --\u003e|execute| SDD[subagent-driven-development]\n    Routing --\u003e|debug| Debug[systematic-debugging]\n    SDD --\u003e Sub1[Subagent 1: Task A]\n    SDD --\u003e Sub2[Subagent 2: Task B]\n    Sub1 --\u003e|results| Review[Two-stage review]\n    Sub2 --\u003e|results| Review\n    Review --\u003e Close[bd close + bd dolt push]\n    Close --\u003e Land[Land the Plane: git push]\n```\n\nThe orchestrator is the only agent that touches beads. Subagents focus on implementation and have no concurrent bead-conflict surface. The two-stage review catches both spec deviation (first-stage spec reviewer) and code-quality issues (second-stage code reviewer) before any task is marked complete.\n\n## Design decisions\n\n| Decision | Rationale |\n|----------|-----------|\n| **Orchestrator-only beads** | Only the main agent manages beads. Subagents focus on implementation — no concurrent bead conflicts. |\n| **Plugin subsumes bd hooks** | The plugin's SessionStart hook runs `bd prime` itself. No need for separate `bd setup claude` hooks. |\n| **TodoWrite fully replaced** | Every TodoWrite reference is replaced with `bd` commands. Zero active TodoWrite usage. |\n| **Land the Plane in finishing skill** | Session close protocol lives in the terminal skill, not a separate skill. Every pipeline path ends here. |\n| **Skills are Markdown, not code** | Pure documentation — no build step, no dependencies, works on any platform with a file system. |\n\n## Project structure\n\n```text\nbeads-superpowers/\n├── .claude-plugin/         Plugin manifests (auto-discovered by Claude Code)\n├── .github/                CI workflow, Dependabot, issue/PR templates\n├── assets/                 README banner SVG\n├── hooks/                  SessionStart hook (bash + Windows polyglot wrapper)\n├── skills/                 20 beads-native skills\n├── agents/                 code-reviewer agent\n├── commands/               Deprecated slash commands (will be removed in a future version)\n├── docs/                   METHODOLOGY, SETUP-GUIDE, testing, upstream-reference\n├── tests/                  Test infrastructure (5 suites)\n├── scripts/                bump-version.sh\n├── CHANGELOG.md\n├── CLAUDE.md               Plugin development instructions\n├── AGENTS.md               Agent instructions\n├── CONTRIBUTING.md         How to contribute\n├── SECURITY.md             Vulnerability reporting policy\n├── LICENSE                 MIT\n└── README.md               This file\n```\n\nFor a deeper directory listing, see [`docs/SETUP-GUIDE.md`](docs/SETUP-GUIDE.md).\n\n## Development\n\nWhen you edit skills in this repo, the installed plugin cache goes stale. The simplest fix is a one-time symlink:\n\n```bash\nrm -rf ~/.claude/plugins/cache/beads-superpowers-marketplace/beads-superpowers/0.4.1\nln -s ~/workplace/beads-superpowers \\\n  ~/.claude/plugins/cache/beads-superpowers-marketplace/beads-superpowers/0.4.1\n```\n\nVerify sync:\n\n```bash\ndiff -rq skills/ ~/.claude/plugins/cache/beads-superpowers-marketplace/beads-superpowers/0.4.1/skills/\n```\n\n\u003e `claude plugin update` exists but has a [cache invalidation bug](https://github.com/anthropics/claude-code/issues/14061). Use the symlink approach instead.\n\nFor the full contributor guide, see [`CONTRIBUTING.md`](CONTRIBUTING.md).\n\n## Attribution\n\n- **Superpowers skills** — [obra/superpowers](https://github.com/obra/superpowers) by Jesse Vincent (MIT License)\n- **Beads issue tracker** — [gastownhall/beads](https://github.com/gastownhall/beads) by Steve Yegge (MIT License)\n- **beads-superpowers integration** — Dillon Frawley\n\n## License\n\n[MIT](LICENSE)\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fdollardill%2Fbeads-superpowers","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fdollardill%2Fbeads-superpowers","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fdollardill%2Fbeads-superpowers/lists"}