rpi

Full RPI lifecycle orchestrator. Delegates to /discovery, /crank, /validation phase skills. One command, full lifecycle with complexity classification, --from routing, and optional loop. Triggers: "rpi", "full lifecycle", "research plan implement", "end to end".

Safety Notice

This listing is imported from skills.sh public index metadata. Review upstream SKILL.md and repository scripts before running.

Copy this and send it to your AI assistant to learn

Install skill "rpi" with this command: npx skills add boshu2/agentops/boshu2-agentops-rpi

/rpi — Full RPI Lifecycle Orchestrator

YOU MUST EXECUTE THIS WORKFLOW. Do not just describe it.

DAG — Execute This Sequentially

mkdir -p .agents/rpi
classify(goal) → complexity, start_phase

From --from or start_phase, enter the DAG at the matching step and run every step after it:

STEP 1  ──  if start_phase <= discovery:
              Skill(skill="discovery", args="<goal> [--interactive] --complexity=<level>")
              BLOCKED? → stop (manual intervention)
              DONE?    → read epic-id from .agents/rpi/execution-packet.json

STEP 2  ──  Skill(skill="crank", args="<epic-id> [--test-first] [--no-test-first]")
              BLOCKED/PARTIAL? → retry (max 3), then stop
              DONE? → ao ratchet record implement 2>/dev/null || true

STEP 3  ──  if complexity != fast:
              Skill(skill="validation", args="<epic-id> --complexity=<level>")
              FAIL? → re-crank + re-validate (max 3 total), then stop
              DONE? → ao ratchet record vibe 2>/dev/null || true

STEP 4  ──  report(verdicts)
              if --loop && FAIL && cycle < max_cycles: restart from STEP 1
              if --spawn-next: read .agents/rpi/next-work.jsonl, suggest next

That's it. Steps 1→2→3→4. No stopping between steps. No summarizing. No asking. Enter at --from, run to the end. The human's only touchpoint is after STEP 4.


Setup + Classify (STEP 0 detail)

Determine start_phase:

  • default: discovery
  • --from=implementation (aliases: crank) → STEP 2
  • --from=validation (aliases: vibe, post-mortem) → STEP 3
  • aliases research, plan, pre-mortem, brainstorm → STEP 1
  • Input looks like epic ID (ag-*) and no --from → STEP 2

Classify complexity:

LevelCriteriaBehavior
fastGoal <=30 chars, no complex/scope keywordsSTEP 3 skipped
standardGoal 31-120 chars, or 1 scope keywordFull DAG. Gates use --quick
fullComplex-operation keyword, 2+ scope keywords, or >120 charsFull DAG. 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: {}
}

Gate Logic Detail

STEP 1 gate (discovery):

  • <promise>DONE</promise>: extract epic-id from .agents/rpi/execution-packet.json, proceed to STEP 2
  • <promise>BLOCKED</promise>: stop — discovery handles its own retries (max 3 pre-mortem attempts)

STEP 2 gate (implementation, max 3 attempts):

  • <promise>DONE</promise>: proceed to STEP 3
  • <promise>BLOCKED</promise>: retry with block context (max 2 retries)
  • <promise>PARTIAL</promise>: retry remaining (max 2 retries)

STEP 3 gate (validation-to-crank loop, max 3 total):

  • <promise>DONE</promise>: proceed to STEP 4
  • <promise>FAIL</promise>: extract findings → re-invoke /crank with findings → re-invoke /validation

STEP 4 (report + optional loop):

  • Summarize all phase verdicts and epic status. See references/report-template.md.
  • --loop + FAIL + cycle < max_cycles: extract 3 fixes from post-mortem, increment cycle, restart from STEP 1
  • --spawn-next: read .agents/rpi/next-work.jsonl, suggest next /rpi command (do NOT auto-invoke)

Flags

FlagDefaultDescription
--from=<phase>discoveryEnter DAG at discovery, implementation, or validation
--interactiveoffHuman gates in discovery only
--autoonFully autonomous. Inverse of --interactive
--loopoffPost-mortem FAIL triggers new cycle
--max-cycles=<n>3Max cycles when --loop enabled
--spawn-nextoffSurface follow-up work after completion
--test-firstonStrict-quality (passed to /crank)
--no-test-firstoffOpt out of strict-quality
--fast-pathautoForce fast complexity (skip STEP 3)
--deepautoForce full complexity
--dry-runoffReport without mutating queue
--no-budgetoffDisable phase time budgets

Quick Start

/rpi "add user authentication"                        # full DAG
/rpi --interactive "add user authentication"          # human gates in discovery only
/rpi --from=implementation ag-23k                      # enter at STEP 2
/rpi --from=validation                                 # enter at STEP 3
/rpi --loop --max-cycles=3 "add auth"                 # iterate-on-fail loop
/rpi --deep "refactor payment module"                  # force full council
/rpi --fast-path "fix typo in readme"                  # skip STEP 3

Examples

Read references/examples.md for full lifecycle, resume, and interactive examples.

Complexity-Scaled Council Gates

Pre-mortem (STEP 5 in discovery)

complexity == "low": inline review, no spawning (--quick) | complexity == "medium": inline fast default (--quick) | complexity == "high": full council, 2-judge minimum. Retry gate: max 3 total attempts.

Final Vibe (STEP 1 in validation)

complexity == "low": inline review, no spawning (--quick) | complexity == "medium": inline fast default (--quick) | complexity == "high": full council, 2-judge minimum. Retry gate: max 3 total attempts.

Post-mortem (STEP 2 in validation)

complexity == "low": inline review, no spawning (--quick) | complexity == "medium": inline fast default (--quick) | complexity == "high": full council, 2-judge minimum. Retry gate: max 3 total attempts.

Phase Data Contracts

All transitions use filesystem artifacts (no in-memory coupling). The execution packet (.agents/rpi/execution-packet.json) carries contract_surfaces (repo execution profile), done_criteria, and queue claim/finalize metadata between phases. Sub-skills include /plan, /vibe, /post-mortem, and /pre-mortem. For detailed contract schemas, read references/phase-data-contracts.md.

Troubleshooting

ProblemSolution
Discovery blocksNarrow goal scope or use --interactive
Implementation loopsCheck bd children <epic> for blockers
Validation FAIL exhaustedFix findings, re-run --from=validation

Read references/troubleshooting.md for more.

See also: discovery, crank, validation

Reference Documents

Source Transparency

This detail page is rendered from real SKILL.md content. Trust labels are metadata-based hints, not a safety guarantee.

Related Skills

Related by shared tags or category signals.

Research

research

No summary provided by upstream source.

Repository SourceNeeds Review
260-boshu2
Research

knowledge

No summary provided by upstream source.

Repository SourceNeeds Review
166-boshu2
Research

pr-research

No summary provided by upstream source.

Repository SourceNeeds Review
150-boshu2
Automation

council

No summary provided by upstream source.

Repository SourceNeeds Review
1.5K-boshu2
rpi | V50.AI