Launchpad
End-to-end orchestrator that chains SPARC or wave-planner (Stage 1), plan-review (Stage 2), linear (Stage 3), and hive-workers-skill (Stage 4) into a single interruptible workflow.
Stage 1 routing (ADR-109):
- Infra changes (Docker, CI, entrypoints, hooks, dev tooling) → SPARC researcher + architect →
docs/internal/implementation/{slug}.md
- Feature work (application code, new endpoints, UI) → wave-planner → hive-mind YAML configs
Execution
When triggered, immediately:
- Read
./agent-prompt.md
- Spawn a single Task with
subagent_type: "general-purpose" passing the agent-prompt content as the prompt
- Include in the prompt: the user's request (issue IDs, project name, or description), current working directory, and any flags (
--from, --skip-review, --fresh, --infra, --feature)
- Wait for the agent to complete
- Present the agent's summary to the user
Do NOT execute the workflow in this session. The subagent handles all stage sequencing, gate prompts, resume detection, and skill dispatching.
Execution Context Requirements
This skill spawns a general-purpose subagent that coordinates stages via nested Task dispatches.
Foreground execution required: Yes. Interactive stage gates use AskUserQuestion which auto-denies in background mode.
Dispatcher tools (frontmatter): Read, Task, AskUserQuestion
Subagent tools: Read, Write, Edit, Bash, Grep, Glob, Task, AskUserQuestion, TodoWrite
Reference: Subagent Tool Permissions
Sub-Documentation
| Document |
Contents |
| agent-prompt.md |
Full coordinator logic: input parsing, Stage 0 infra detection, stage routing, resume detection, error handling |
Related Skills
Infra Trigger Criteria (ADR-109)
Stage 1a (SPARC) is selected when scope includes any of:
docker-entrypoint.sh, Dockerfile, docker-compose.yml.github/workflows/*.yml.husky/*, pre-commit, pre-push hook scriptsscripts/ files called by Docker/CI/hookspackage.json scripts block changes- Dev tooling config:
.eslintrc, vitest.config.ts, turbo.json
Stage 1b (wave-planner) for everything else. Mixed scope → use Stage 1a.
Override with flags: --infra forces Stage 1a, --feature forces Stage 1b.
Changelog
v1.2.1 (2026-03-09)
- Section 2: Dual-path hive execution skill detection — check both
hive-workers-skill and hive-mind-execution at user-level and project-level paths
- Section 7: Use resolved
HWS_PATH instead of hardcoded path for hive execution skill
v1.2.0 (2026-02-19)
- Section 2: Add MISSING/OK skill classification with explicit consent gate for optional skills
- Section 7: Replace silent Stage 4 fallback with explicit AskUserQuestion consent gate
v1.1.0 (2026-02-18)
- Add Stage 0 infra detection routing (ADR-109)
- Add
sparc-methodology to composes as Stage 1a for infra changes
- Add
--infra / --feature override flags
- Update description and Related Skills table
v1.0.0
- Initial release: 4-stage pipeline (Plan, Review, Issues, Execute)
- Interruptible stage gates with standardized 5-option prompts
- Resume detection via multi-signal artifact checks
- Skill existence checks with graceful fallbacks
1---2name: launchpad3description: End-to-end planning and execution orchestrator. Chains SPARC or wave-planner (Stage 1), plan-review, linear, and hive-workers-skill into a single workflow. Automatically routes infra changes through SPARC research instead of wave-planner. Use when starting a new initiative, executing a set of Linear issues, or running plan-to-deployment.4---56# Launchpad78End-to-end orchestrator that chains SPARC or wave-planner (Stage 1), plan-review (Stage 2), linear (Stage 3), and hive-workers-skill (Stage 4) into a single interruptible workflow.910**Stage 1 routing (ADR-109)**:11- **Infra changes** (Docker, CI, entrypoints, hooks, dev tooling) → SPARC researcher + architect → `docs/internal/implementation/{slug}.md`12- **Feature work** (application code, new endpoints, UI) → wave-planner → hive-mind YAML configs1314## Execution1516When triggered, **immediately**:17181. Read `./agent-prompt.md`192. Spawn a single Task with `subagent_type: "general-purpose"` passing the agent-prompt content as the prompt203. Include in the prompt: the user's request (issue IDs, project name, or description), current working directory, and any flags (`--from`, `--skip-review`, `--fresh`, `--infra`, `--feature`)214. Wait for the agent to complete225. Present the agent's summary to the user2324Do NOT execute the workflow in this session. The subagent handles all stage sequencing, gate prompts, resume detection, and skill dispatching.2526## Execution Context Requirements2728This skill spawns a general-purpose subagent that coordinates stages via nested Task dispatches.2930**Foreground execution required**: Yes. Interactive stage gates use AskUserQuestion which auto-denies in background mode.3132**Dispatcher tools** (frontmatter): Read, Task, AskUserQuestion33**Subagent tools**: Read, Write, Edit, Bash, Grep, Glob, Task, AskUserQuestion, TodoWrite3435**Reference**: [Subagent Tool Permissions](https://code.claude.com/docs/en/sub-agents)3637## Sub-Documentation3839| Document | Contents |40|----------|----------|41| [agent-prompt.md](agent-prompt.md) | Full coordinator logic: input parsing, Stage 0 infra detection, stage routing, resume detection, error handling |4243## Related Skills4445| Skill | Role |46|-------|------|47| [sparc-methodology](../sparc-methodology/SKILL.md) | Stage 1a (infra): SPARC researcher + architect → implementation plan |48| [wave-planner](../wave-planner/SKILL.md) | Stage 1b (feature): Generate wave plan + hive configs |49| [plan-review-skill](../plan-review-skill/SKILL.md) | Stage 2: VP review of plan (both paths) |50| [linear](../linear/SKILL.md) | Stage 3: Create Linear project + issues |51| [hive-workers-skill](../hive-workers-skill/SKILL.md) | Stage 4: Execute waves via ruflo swarm |5253## Infra Trigger Criteria (ADR-109)5455Stage 1a (SPARC) is selected when scope includes any of:56- `docker-entrypoint.sh`, `Dockerfile`, `docker-compose.yml`57- `.github/workflows/*.yml`58- `.husky/*`, `pre-commit`, `pre-push` hook scripts59- `scripts/` files called by Docker/CI/hooks60- `package.json` `scripts` block changes61- Dev tooling config: `.eslintrc`, `vitest.config.ts`, `turbo.json`6263Stage 1b (wave-planner) for everything else. Mixed scope → use Stage 1a.6465Override with flags: `--infra` forces Stage 1a, `--feature` forces Stage 1b.6667## Changelog6869### v1.2.1 (2026-03-09)70- Section 2: Dual-path hive execution skill detection — check both `hive-workers-skill` and `hive-mind-execution` at user-level and project-level paths71- Section 7: Use resolved `HWS_PATH` instead of hardcoded path for hive execution skill7273### v1.2.0 (2026-02-19)74- Section 2: Add MISSING/OK skill classification with explicit consent gate for optional skills75- Section 7: Replace silent Stage 4 fallback with explicit AskUserQuestion consent gate7677### v1.1.0 (2026-02-18)78- Add Stage 0 infra detection routing (ADR-109)79- Add `sparc-methodology` to `composes` as Stage 1a for infra changes80- Add `--infra` / `--feature` override flags81- Update description and Related Skills table8283### v1.0.084- Initial release: 4-stage pipeline (Plan, Review, Issues, Execute)85- Interruptible stage gates with standardized 5-option prompts86- Resume detection via multi-signal artifact checks87- Skill existence checks with graceful fallbacks
smith-horn