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

references/exploration-orchestrator-guide.md

View on GitHub
# Exploration Workflow Orchestration Guide

Comprehensive reference guide for the Business Exploration Loop orchestrator (`exploration-workflow`).

## Contents

- [Session Types & Phase Activation](#session-types--phase-activation)
- [Pre-Flight & Dispatch Setup](#pre-flight--dispatch-setup)
- [Bootstrap Protocol & Dashboard Schema](#bootstrap-protocol--dashboard-schema)
- [State Reading & Resume Protocol](#state-reading--resume-protocol)
- [Phase Routing & Hard-Gate Enforcement](#phase-routing--hard-gate-enforcement)
- [Task Ledger & Isolation](#task-ledger--isolation)
- [Gotchas & Failure Modes](#gotchas--failure-modes)

---

## Session Types & Phase Activation

| Type | Intent | Active Phases |
|------|--------|---------------|
| **Greenfield** | Building new app/system from scratch | All 4 phases |
| **Brownfield** | Adding feature or legacy analysis | Phase 1 required; Phase 3 modifies codebase |
| **Analysis/Docs** | Non-software deliverables (BRD, process map, policy) | Phases 1 & 4 required; Phase 3 skipped |
| **Spike** | Timeboxed proof-of-concept / tech validation | Phase 1 required; iterations flexible |

---

## Pre-Flight & Dispatch Setup

Select the worker dispatch model:
1. A `cli-agent` backend (copilot, agy, claude, codex or local), when an external CLI is installed and authorized
2. `claude-subagents` (in-session sub-agents)
3. `direct` (main context execution)

See [dispatch-strategies.md](dispatch-strategies.md); model and runtime choices belong to the `cli-agent` skill.

---

## Bootstrap Protocol & Dashboard Schema

Initialize `exploration/exploration-dashboard.md`:

```markdown
# Exploration Session Dashboard
**Status:** In Progress
**Session Type:** [Greenfield / Brownfield / Analysis / Spike]
**Active Phase:** Phase 1 — Discovery Planning
**Dispatch Strategy:** [Selected strategy]

## Phases
- [ ] Phase 1: Discovery Planning (`discovery-planning`)
- [ ] Phase 2: Behavioral Capture (`visual-companion` / `vibe-behavioral-test-capture`)
- [ ] Phase 3: Prototyping (`subagent-driven-prototyping` / `prototype-builder`)
- [ ] Phase 4: Handoff Package (`exploration-handoff`)

## Session Artifacts
- Brief: `exploration/session-brief.md`
- Discovery Plan: `exploration/discovery-plans/`
- Captures: `exploration/captures/`
- Prototypes: `exploration/prototype/`
- Handoff: `exploration/handoffs/`
```

---

## State Reading & Resume Protocol

When user asks to resume or check status:
1. Read `exploration/exploration-dashboard.md`.
2. Inspect last completed phase from HANDOFF_BLOCKs.
3. Present plain-language status recap to SME before proceeding.

---

## Phase Routing & Hard-Gate Enforcement

At each phase gate:
- **Phase 1 -> 2**: Requires explicit approval of Discovery Plan.
- **Phase 2 -> 3**: Requires the SME's confirmation of the layout direction (`captures/layout-direction.md` or `document-structure.md`); user stories and behavioral notes are checked in the Phase 1 capture loop and at Gate 3.
- **Phase 3 -> 4**: Requires verified prototype artifacts.
- **Phase 4 Completion**: Requires finalized handoff package and TierGate risk determination.

---

## Task Ledger & Isolation

- Maintain a living task ledger throughout the session.
- Break Phase 3 implementation into manageable slices, each with a validation check.
- Isolate prototyping in a dedicated workspace using the `os-control-worktree` skill (rules in the Phase 3 reference of `building-interactive-prototypes`).

---

## Gotchas & Failure Modes

- **Silent Skip**: Never skip Phase 1 gate even if user insists "just build it".
- **Dashboard Synchronization**: Always update `**Status:**` and active phase checkboxes upon phase completion.
- **Analysis/Docs Phase 3**: Phase 3 must remain skipped (`- [~]`) for non-software sessions.
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: 471kUpdated 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