rpi▌
boshu2/agentops · updated May 7, 2026
MDX-style export adds YAML metadata + attribution linking explainx.ai and this canonical listing URL.
Quick Ref: One command, full lifecycle. /discovery → /crank → /validation. Thin wrapper that delegates to phase orchestrators.
- ›YOU MUST EXECUTE THIS WORKFLOW. Do not just describe it.
- ›THREE-PHASE RULE + FULLY AUTONOMOUS. Read references/autonomous-execution.md — it defines the mandatory 3-phase lifecycle, autonomous execution rules, anti-patterns, and phase completion logging. Unless --interactive is set, RPI runs hands-free. Do NOT stop after Phase 2. Do NOT ask the user anything between phases
/rpi — Full RPI Lifecycle Orchestrator
Quick Ref: One command, full lifecycle.
/discovery→/crank→/validation. Thin wrapper that delegates to phase orchestrators. YOU MUST EXECUTE THIS WORKFLOW. Do not just describe it. THREE-PHASE RULE + FULLY AUTONOMOUS. Readreferences/autonomous-execution.md— it defines the mandatory 3-phase lifecycle, autonomous execution rules, anti-patterns, and phase completion logging. Unless--interactiveis set, RPI runs hands-free. Do NOT stop after Phase 2. Do NOT ask the user anything between phases.
Quick Start
Run /rpi "<goal>" for the full lifecycle. For resume, loop, fast-path, and deep examples, read references/examples.md.
Lifecycle Ownership
Phase orchestrators own all sub-skill sequencing, retry gates, and phase budgets. /discovery handles brainstorm → design (when PRODUCT.md exists) → search → research → plan → pre-mortem and writes the execution packet; /crank owns wave-based implementation and implementation retries; /validation owns vibe → post-mortem → retro → forge and validation retries. /rpi stays thin: it owns setup, complexity classification, phase routing, the implementation gate, the validation-fail-to-crank loop, and the final report.
Execution Steps
Step 0: Setup + Classify
mkdir -p .agents/rpi
Determine starting phase:
- default:
discovery --from=implementation(aliases:crank) → skip to Phase 2--from=validation(aliases:vibe,post-mortem) → skip to Phase 3- aliases
research,plan,pre-mortem,brainstormmap todiscovery - If input is a bead ID and
--fromis not set, resolve it before routing:bd show <id>saysissue_type=epic→ Phase 2 using that epic ID- child issue with
parent→ Phase 2 using the parent epic ID
- If beads are absent or the input is plain goal text:
- preserve the goal as the lifecycle objective
- use
.agents/rpi/execution-packet.jsonas the phase-2 handoff when discovery does not yield an epic - default to Phase 1 unless the user explicitly set
--from
- Do not infer epic scope from
ag-*alone. Classify complexity:
| Level | Criteria | Behavior |
|---|---|---|
fast |
Goal <=30 chars, no complex/scope keywords | Full 3-phase. Gates use --quick throughout. |
standard |
Goal 31-120 chars, or 1 scope keyword | Full 3-phase. Gates use --quick. |
full |
Complex-operation keyword, 2+ scope keywords, or >120 chars | Full 3-phase. Gates use full council. |
Complex-operation keywords: refactor, migrate, migration, rewrite, redesign, rearchitect, overhaul, restructure, reorganize, decouple, deprecate, split, extract module, port
Scope keywords: all, entire, across, everywhere, every file, every module, system-wide, global, throughout, codebase
Overrides: --deep forces full. --fast-path forces fast.
Log:
RPI mode: rpi-phased (complexity: <level>)
Initialize state:
rpi_state = {
goal: "<goal string>",
epic_id: null,
phase: "<discovery|implementation|validation>",
complexity: "<fast|standard|full>",
test_first: <true by default; false only when --no-test-first>,
cycle: 1,
max_cycles: <3 when --loop; overridden by --max-cycles>,
verdicts: {}
}
Phase 1: Discovery
Delegate to /discovery:
Skill(skill="discovery", args="<goal> [--interactive] --complexity=<level>")
After /discovery completes:
- Check completion marker:
<promise>DONE</promise>or<promise>BLOCKED</promise> - If BLOCKED: stop. Discovery handles its own retries (max 3 pre-mortem attempts). Manual intervention needed.
- If DONE: read
.agents/rpi/execution-packet.json(or the matching run archive whenrun_idis known), preserve the execution-packet objective spine, and extractepic_idonly when it exists - Store
rpi_state.epic_idwhen present andrpi_state.verdicts.pre_mortem - Log:
PHASE 1 COMPLETE ✓ (discovery) — proceeding to Phase 2
Phase 2: Implementation
If the execution packet has epic_id:
Skill(skill="crank", args="<epic-id> [--test-first] [--no-test-first]")
Otherwise:
Skill(skill="crank", args=".agents/rpi/execution-packet.json [--test-first] [--no-test-first]")
Implementation gate (max 3 attempts):
<promise>DONE</promise>: proceed to validation<promise>BLOCKED</promise>: retry with block context (max 2 retries)- Re-invoke
/crankon the same lifecycle objective + block reason - If still BLOCKED after 3 total: stop, manual intervention needed
- Re-invoke
<promise>PARTIAL</promise>: retry remaining (max 2 retries)- Re-invoke
/crankon the same epic or execution packet (picks up remaining work) - If still PARTIAL after 3 total: stop, manual intervention needed
- Re-invoke
Record:
ao ratchet record implement 2>/dev/null || true
Log: PHASE 2 COMPLETE ✓ (implementation) — proceeding to Phase 3
DO NOT STOP HERE. Do not ask the user to commit. Do not summarize and wait. Proceed IMMEDIATELY to Phase 3. Implementation without validation is incomplete work — the flywheel does not turn, learnings are not captured, and quality is unverified.
Phase 3: Validation
MANDATORY for all complexity levels. /validation is the Phase 3 orchestrator — it wraps /vibe + /post-mortem + /retro + /forge. Do NOT call /vibe directly from /rpi — call /validation which handles the full sequence. fast complexity uses inline --quick gates inside /validation; it does not skip closeout.
If the execution packet has epic_id:
Skill(skill="validation", args="<epic-id> --complexity=<level> [--strict-surfaces if --quality]")
Otherwise:
Skill(skill="validation", args="--complexity=<level> [--strict-surfaces if --quality]")
Validation-to-crank loop (max 3 total attempts):
<promise>DONE</promise>: finish RPI<promise>FAIL</promise>: vibe found defects- Extract findings from validation output
- Re-invoke
/crankon the same epic or execution packet + findings context (preserve--test-first/--no-test-firstfrom original invocation) - Re-invoke
/validation - If still FAIL after 3 total: stop, manual intervention needed
Record:
ao ratchet record vibe 2>/dev/null || true
Log: PHASE 3 COMPLETE ✓ (validation) — RPI DONE
Step Final: Report + Loop
Report: Summarize all phase verdicts and epic status.
Optional loop (--loop): If validation verdict is FAIL and cycle < max_cycles:
- Extract 3 concrete fixes from the post-mortem report
- Increment
rpi_state.cycle - Re-invoke
/rpifrom discovery with a tightened goal - PASS/WARN stops the loop
Optional spawn-next (--spawn-next): After PASS/WARN finish:
- Read
.agents/rpi/next-work.jsonlfor harvested follow-up items - Report with suggested next
/rpicommand - Do NOT auto-invoke
Read references/report-template.md for full output format.
Read references/error-handling.md for failure semantics.
Flags
| Flag | Default | Description |
|---|---|---|
--from=<phase> |
discovery |
Start from discovery, implementation, or validation |
--interactive |
off | Human gates in discovery |
--auto |
on | Fully autonomous (no human gates). Inverse of --interactive. Passed through to /discovery and /plan. |
--loop |
off | Post-mortem FAIL triggers new cycle |
--max-cycles=<n> |
3 |
Max cycles when --loop enabled (default 3) |
--spawn-next |
off | Surface follow-up work after completion |
--test-first |
on | Strict-quality (passed to /crank) |
--no-test-first |
off | Opt out of strict-quality |
--fast-path |
auto | Force fast complexity (uses quick inline gates, still runs full lifecycle) |
--deep |
auto | Force full complexity |
--quality |
off | Pass --strict-surfaces to /validation, making all 4 surface failures blocking |
--dry-run |
off | Report without mutating queue |
--no-budget |
off | Disable phase time budgets (passed to phase skills) |
Phase Data Contracts
All transitions use filesystem artifacts (no in-memory coupling). The execution packet (.agents/rpi/execution-packet.json as the latest alias, plus .agents/rpi/runs/<run-id>/execution-packet.json as the per-run archive) carries the repo execution profile via contract_surfaces, plus done_criteria and queue claim/finalize metadata between phases. For detailed schemas, read references/phase-data-contracts.md.
Complexity-Scaled Council Gates
Pre-mortem
complexity == "low"orcomplexity == "fast": inline review, no spawning (--quick)complexity == "medium"orcomplexity == "standard": inline fast default (--quick)complexity == "high"orcomplexity == "full": full council, 2-judge minimum; retry gate max 3 total attempts
Final Vibe
complexity == "low"orcomplexity == "fast": inline review, no spawning (--quick)complexity == "medium"orcomplexity == "standard": inline fast default (--quick)complexity == "high"orcomplexity == "full": full council, 2-judge minimum; retry gate max 3 total attempts
Post-mortem (STEP 2)
complexity == "low"orcomplexity == "fast": inline review, no spawning (--quick)complexity == "medium"orcomplexity == "standard": inline fast default (--quick)complexity == "high"orcomplexity == "full": full council, 2-judge minimum; retry gate max 3 total attempts
Examples
Read references/examples.md for full lifecycle, resume, and interactive examples. --fast-path still runs validation; it only forces the fast/inline gate profile.
Troubleshooting
Read references/troubleshooting.md for common problems and solutions.
Runtime Compatibility
RPI runs in three runtime modes. All must produce identical phase artifacts.
| Concern | gc (default) | Hook-capable (Claude Code) | Hook-less (Codex) |
|---|---|---|---|
| Session start | gc controller starts session | session-start.sh hook fires automatically |
ao codex start called explicitly |
| Session stop | gc controller stops session | session-end.sh hook fires automatically |
ao codex stop called explicitly |
| Phase execution | gcExecutor via gc sessions |
streamExecutor via Claude CLI |
directExecutor via Codex CLI |
| Event capture | gc event bus (ao:phase, ao:gate, ao:failure, ao:metric) |
local events.jsonl (legacy) | local events.jsonl (legacy) |
| Phase state | .agents/rpi/phased-state.json |
.agents/rpi/phased-state.json |
.agents/rpi/phased-state.json |
| Phase numbering | 1 = discovery, 2 = implementation, 3 = validation | Same | Same |
| Ratchet checkpoints | ao ratchet check |
ao ratchet check |
ao ratchet check |
| Agent health | gc status --json |
manual / tmux inspection | manual |
gc is the default when available. ao rpi auto-selects gcExecutor when gc binary is on PATH, version >= 0.13.0, and city.toml exists. Falls back to streamExecutor otherwise. Use --runtime stream or --runtime tmux to force legacy executors.
Minimal contract across all modes: phase state is always written to .agents/rpi/phased-state.json; phase numbering stays 1=discovery, 2=implementation, 3=validation; ao ratchet check reads that shared state unchanged; the close-loop flywheel still runs at stop time.
Reference Documents
- references/complexity-scaling.md
- references/context-windowing.md
- references/gate-retry-logic.md
- references/gate4-loop-and-spawn.md
- references/phase-budgets.md
- references/phase-data-contracts.md
- references/report-template.md
- references/error-handling.md
- references/examples.md
- references/autonomous-execution.md
- references/troubleshooting.md
How to use rpi on Cursor
AI-first code editor with Composer
Prerequisites
Before installing skills in Cursor, ensure your development environment meets these requirements:
- ›Cursor installed and configured on your development machine
- ›Node.js version 16.0+ with npm package manager (verify with
node --version) - ›Active project directory or workspace where you want to add rpi
Execute installation command
Execute the skills CLI command in your project's root directory to begin installation:
The skills CLI fetches rpi from GitHub repository boshu2/agentops and configures it for Cursor.
Select Cursor when prompted
The CLI will show a list of available agents. Use arrow keys to navigate and space to select Cursor:
Verify installation
Confirm successful installation by checking the skill directory location:
Reload or restart Cursor to activate rpi. Access the skill through slash commands (e.g., /rpi) or your agent's skill management interface.
Security & Verification Notice
We perform automated surface-level scans (Gen AI Scanner, Socket, Snyk) during installation. These checks detect common vulnerabilities but do not guarantee complete security. Always review skill source code and verify the publisher's reputation before production use.
Skills execute code in your development environment. Always verify the publisher's identity, review recent commits, and test in isolated environments before production deployment.
List & Monetize Your Skill
Submit your Claude Code skill and start earning
Use Cases▌
User Story & Requirements Generation
Create detailed user stories, acceptance criteria, and feature specs
Example
Generate user stories for 'password reset feature' with acceptance criteria, edge cases, and test scenarios
Reduce spec writing time by 50%, ensure comprehensive coverage
Competitive Analysis
Research competitors, compare features, identify gaps
Example
Analyze 5 competitor products, create feature comparison matrix, suggest differentiation opportunities
Complete competitive research in 2 hours instead of 2 days
Roadmap Prioritization
Evaluate features using frameworks (RICE, ICE, Kano) and create prioritized backlogs
Example
Score 20 feature ideas using RICE framework, generate prioritized roadmap with rationale
Make data-driven prioritization decisions faster
Stakeholder Communication
Draft PRDs, status updates, and stakeholder presentations
Example
Create executive summary of Q3 roadmap, monthly progress report, feature launch announcement
Save 3-5 hours/week on communication overhead
Implementation Guide▌
Prerequisites
- ›Claude Desktop or compatible AI client
- ›Access to product documentation and roadmap tools (Jira, Notion, etc.)
- ›Understanding of product management frameworks (RICE, Jobs-to-be-Done, etc.)
- ›Stakeholder contact information and communication channels
Time Estimate
30-60 minutes to see productivity improvements
Installation Steps
- 1.Install product management skill
- 2.Start with user story generation for known feature
- 3.Progress to competitive analysis: research 2-3 competitors
- 4.Use for roadmap prioritization: apply RICE/ICE scoring
- 5.Draft stakeholder communications and refine based on feedback
- 6.Build template library for recurring PM tasks
- 7.Share effective prompts with product team
Common Pitfalls
- ⚠Not validating competitive research—verify facts before sharing
- ⚠Accepting user stories without involving engineering team
- ⚠Over-relying on frameworks without qualitative judgment
- ⚠Not customizing outputs to company culture and communication style
- ⚠Skipping stakeholder validation of generated requirements
Best Practices▌
✓ Do
- +Validate research and competitive analysis with real data
- +Collaborate with engineering when generating technical requirements
- +Customize frameworks and templates to your company context
- +Use skill for first drafts, refine with stakeholder input
- +Document successful prompt patterns for PM tasks
- +Combine AI efficiency with human judgment and intuition
✗ Don't
- −Don't publish competitive analysis without fact-checking
- −Don't finalize user stories without engineering review
- −Don't make prioritization decisions solely on AI scoring
- −Don't skip customer validation of generated requirements
- −Don't ignore company-specific context and culture
💡 Pro Tips
- ★Provide context: company goals, constraints, customer feedback
- ★Ask for alternatives: 'Show 3 ways to prioritize this roadmap'
- ★Request stakeholder-specific formatting: 'Executive summary vs. engineering spec'
- ★Use skill for 70% generation + 30% customization to company needs
When to Use This▌
✓ Use When
Use for user story writing, competitive research, roadmap prioritization, stakeholder communication, and PRD drafting. Best for reducing repetitive documentation and research work.
✗ Avoid When
Avoid for strategic product vision (requires deep customer empathy), pricing decisions (needs market and financial expertise), or when face-to-face customer discovery is more valuable than speed.
Learning Path▌
- 1Basic: user stories, feature specs, status updates
- 2Intermediate: competitive analysis, prioritization frameworks, PRDs
- 3Advanced: product strategy, go-to-market planning, OKR setting
- 4Expert: product vision, market positioning, business model innovation
Discussion
Product Hunt–style comments (not star reviews)- No comments yet — start the thread.
Ratings
4.5★★★★★42 reviews- ★★★★★Yash Thakker· Dec 16, 2024
rpi reduced setup friction for our internal harness; good balance of opinion and flexibility.
- ★★★★★James Dixit· Dec 16, 2024
rpi fits our agent workflows well — practical, well scoped, and easy to wire into existing repos.
- ★★★★★Nikhil Singh· Dec 4, 2024
Registry listing for rpi matched our evaluation — installs cleanly and behaves as described in the markdown.
- ★★★★★Hana Li· Dec 4, 2024
Solid pick for teams standardizing on skills: rpi is focused, and the summary matches what you get after install.
- ★★★★★Kwame Singh· Nov 23, 2024
Useful defaults in rpi — fewer surprises than typical one-off scripts, and it plays nicely with `npx skills` flows.
- ★★★★★Ira Ghosh· Nov 23, 2024
We added rpi from the explainx registry; install was straightforward and the SKILL.md answered most questions upfront.
- ★★★★★Hana Verma· Nov 15, 2024
Keeps context tight: rpi is the kind of skill you can hand to a new teammate without a long onboarding doc.
- ★★★★★Dhruvi Jain· Nov 7, 2024
I recommend rpi for anyone iterating fast on agent tooling; clear intent and a small, reviewable surface area.
- ★★★★★Oshnikdeep· Oct 26, 2024
Useful defaults in rpi — fewer surprises than typical one-off scripts, and it plays nicely with `npx skills` flows.
- ★★★★★Aanya Ramirez· Oct 14, 2024
I recommend rpi for anyone iterating fast on agent tooling; clear intent and a small, reviewable surface area.
showing 1-10 of 42