Skip to content

richfrem/agent-plugins-skills / plugins/agent-exploration-cycle/.apm/skills/running-exploration-cycle

running-exploration-cycle

Verified

Runs the business exploration cycle end to end: starts or resumes a session (intake interview, session brief), enforces the Discovery Plan HARD-GATE, routes the four phases (Discovery Plan, Visual Blueprinting, Prototype, Handoff) to the sibling skills and keeps session state. Use when the user says "let's explore this idea", "I have an idea I want to explore", "help me plan this out", "start discovery", "resume my exploration", "where did we leave off", or starts any conversation about a need, problem or idea before building. Not for hardening an existing prototype (use reengineering-vibe-code) or for engineering build work.

FileKindSize
SKILL.mdskill md4.6 KB
assets/exploration-dashboard.mdmarkdown1.8 KB
evals/evals.jsonconfig6.0 KB
references/acceptance-criteria.mdmarkdown2.2 KB
references/architecture.mdmarkdown6.3 KB
references/design-rationale.mdmarkdown6.3 KB
references/discovery-planning-agent.mdmarkdown4.7 KB
references/discovery-planning-tracks.mdmarkdown5.9 KB
references/discovery-planning.mdmarkdown2.4 KB
references/dispatch-strategies.mdmarkdown5.7 KB
references/domain-patterns-exploration-session.mdmarkdown3.3 KB
references/domain-patterns.mdmarkdown1.7 KB
references/environment-check.mdmarkdown1.7 KB
references/exploration-cycle-orchestrator-agent.mdmarkdown16.7 KB
references/exploration-optimizer.mdmarkdown8.9 KB
references/exploration-orchestrator-guide.mdmarkdown3.7 KB
references/exploration-session-brief.mdmarkdown2.1 KB
references/exploration-workflow.mdmarkdown2.4 KB
references/hard-gate-enforcement.mdmarkdown3.3 KB
references/high-level-process.mmdother885 B
references/intake-agent.mdmarkdown12.0 KB
references/orchestrator-loop.mmdother1.3 KB
references/post-run-survey.mdmarkdown1.7 KB
references/problem-framing-agent.mdmarkdown2.7 KB
references/process-definition.mdmarkdown3.7 KB
references/process-overview.mmdother3.7 KB
references/session-setup.mmdother1.3 KB
references/state-and-gates.mmdother1.0 KB
references/using-exploration-cycle.mdmarkdown2.3 KB
requirements-dev.inother69 B
requirements.inother60 B
scripts/check_gaps.pyscript2.5 KB
scripts/dispatch.pyexecutablescript23.6 KB
scripts/exploration_session.pyexecutablescript15.9 KB
scripts/sandbox_runner.pyscript8.7 KB
scripts/smoke_test.pyscript5.1 KB
scripts/state_engine.pyscript21.9 KB
scripts/test_dispatch_authorization_gate.pyscript4.0 KB
scripts/test_dispatch_security.pyscript10.0 KB
scripts/test_exploration_integration.pyscript14.7 KB
scripts/test_integration.pyscript4.4 KB
scripts/test_path_traversal.pyscript1.8 KB
scripts/test_phase_premium_counter.pyscript2.0 KB
scripts/test_sandbox_runner.pyscript5.6 KB
scripts/test_session_start_hook.pyscript2.4 KB
scripts/test_state_engine.pyscript13.5 KB
scripts/test_validate_phase_gate.pyscript12.7 KB
scripts/validate_phase_gate.pyexecutablescript8.7 KB
---
name: running-exploration-cycle
plugin: agent-exploration-cycle
description: >
  Runs the business exploration cycle end to end: starts or resumes a session (intake interview,
  session brief), enforces the Discovery Plan HARD-GATE, routes the four phases (Discovery Plan,
  Visual Blueprinting, Prototype, Handoff) to the sibling skills and keeps session state. Use when
  the user says "let's explore this idea", "I have an idea I want to explore", "help me plan this
  out", "start discovery", "resume my exploration", "where did we leave off", or starts any
  conversation about a need, problem or idea before building. Not for hardening an existing
  prototype (use reengineering-vibe-code) or for engineering build work.
allowed-tools: Bash, Read, Write, AskUserQuestion
---

# Running the Exploration Cycle

Front door and conductor of the exploration plugin. Process: [process-overview.mmd](references/process-overview.mmd) and [process-definition.md](references/process-definition.md).

## Contents

- [Constraints](#constraints) • [Quick start](#quick-start) • [Workflow](#workflow) • [Verification](#verification) • [References](#references)

## Constraints

- **HARD-GATE**: no capture, prototype or handoff work until the SME has approved the Discovery Plan (`PLAN_STATUS: APPROVED` or `## SME Approval`); a DRAFT never counts. Use the redirect in [hard-gate-enforcement.md](references/hard-gate-enforcement.md) verbatim, offer no workaround.
- **State**: the SQLite state engine is authoritative; `exploration/exploration-dashboard.md` is a read-only projection. Never rely on conversation memory for a gate. If you were dispatched as a subagent, skip this skill.
- **One question at a time**, in the SME's business language (no git, branch or subagent jargon).
- **Routing**: an existing working prototype goes to `reengineering-vibe-code`; technical codebase discovery goes to `handing-off-to-engineering`.
- **Models**: never name models or prices here; choose runtime and model through the `cli-agent` skill.

## Quick start

Run from this skill's folder, with `CLAUDE_PROJECT_DIR` set to the project:

```bash
python3 scripts/state_engine.py status
python3 scripts/validate_phase_gate.py 1
python3 scripts/check_gaps.py --files exploration/captures/brd-draft.md --threshold 3
```

## Workflow

1. **Resume check**: run `status`; an in-progress session continues at its active phase ([using-exploration-cycle.md](references/using-exploration-cycle.md)).
2. **Phase 0 Intake**: interview, classify, write `exploration/session-brief.md` ([intake](references/intake-agent.md), [brief](references/exploration-session-brief.md)); pick session type and dispatch ([session-setup.mmd](references/session-setup.mmd), [dispatch](references/dispatch-strategies.md)).
3. **Phase 1 Discovery Plan**: [discovery-planning.md](references/discovery-planning.md) and [tracks](references/discovery-planning-tracks.md); then the capture loop in `capturing-business-requirements`.
4. **Phases 2 and 3**: hand to `building-interactive-prototypes`. **Phase 4**: hand to `handing-off-to-engineering`.
5. Each phase ends at its gate ([state-and-gates.mmd](references/state-and-gates.mmd)); wait for the SME, then run the validator for that phase.

## Verification

```bash
python3 scripts/validate_phase_gate.py <phase>   # 1 to 4
python3 -m pytest scripts -q
```

Acceptance criteria: [acceptance-criteria.md](references/acceptance-criteria.md).

## References

- Process: [process-definition.md](references/process-definition.md) • [orchestrator-loop.mmd](references/orchestrator-loop.mmd) • [high-level-process.mmd](references/high-level-process.mmd) • [design-rationale.md](references/design-rationale.md) (read to know why the loop halts where it does)
- Entry and state: [exploration-workflow.md](references/exploration-workflow.md) • [exploration-orchestrator-guide.md](references/exploration-orchestrator-guide.md) • [environment-check.md](references/environment-check.md)
- Phase 0 and 1: [problem-framing-agent.md](references/problem-framing-agent.md) • [discovery-planning-agent.md](references/discovery-planning-agent.md) • [exploration-cycle-orchestrator-agent.md](references/exploration-cycle-orchestrator-agent.md) (CLI-dispatch director)
- Seed template: [exploration-dashboard.md](assets/exploration-dashboard.md)
- Quality: [architecture.md](references/architecture.md) (artifact markers) • [post-run-survey.md](references/post-run-survey.md) • [domain-patterns.md](references/domain-patterns.md) and [exploration-session patterns](references/domain-patterns-exploration-session.md) (known failures and escapes) • [exploration-optimizer.md](references/exploration-optimizer.md) (retired loop, use `os-lab`)
reverse-engineer-anythingmorluto/reaReverse engineer native, managed, Electron/JavaScript, packaged, firmware, and browser targets with REA, and build agent environments (AgentEnv bundles) of web applications from a live instance or a capture, and of Linux desktop apps with a task from a request. Use shipped-artifact or requested runtime evidence to explain features, compare versions, decompile code, or guide a reconstruction. Skip REA for ordinary source-repository architecture analysis.Stars: 472kUpdated Claude CodeCodexVerifiedInstall
diagnosing-superpowersobra/superpowersUse when a superpowers session went wrong and your human partner wants to know why — repeated work, ignored plans, stumbles, poor results, a skill that didn't fire, "it took too long", "why is it so expensive", "what is it doing" — or wants to build a bug report for the superpowers maintainers, for the current session or a past one identified by id or path, on any harness.Stars: 322kUpdated Claude CodeCodexVerifiedInstall
dispatching-parallel-agentsobra/superpowersUse when facing 2+ independent tasks that can be worked on without shared state or sequential dependenciesStars: 322kUpdated Claude CodeCodexVerifiedInstall
executing-plansobra/superpowersUse when executing an implementation plan in the current session as the implementer yourself — your human partner chose inline execution, or no subagent tool is availableStars: 322kUpdated Claude CodeCodexVerifiedInstall