Receber por email
← Voltar para o catálogo

rpi

Run discovery, crank, validation.

393estrelas
Atualizado há 4 meses

Ver no GitHub ↗ Licença: NOASSERTION

Como adicionar

/plugin marketplace add boshu2/agentops

O comando exato pode variar conforme o repositório. Confira o README no GitHub.

Para o autor da skill

Cole no README do seu repo

Mostra que sua skill está catalogada na Skillteca, gera backlink e tráfego rastreável.

[![Skillteca](https://www.skillteca.com.br/api/badge/rpi/svg)](https://www.skillteca.com.br/skills/rpi)

Skills relacionadas

Ver todas de Desenvolvimento →

Alerta por categoria

Receba novas skills de Desenvolvimento toda segunda

1 email curto, só com as skills novas de Desenvolvimento. 4 minutos de leitura, sem spam, cancela com 1 clique.

Você confirma o email no primeiro envio. Sem spam. Cancela com 1 clique.

Ler descrição completa

/rpi - Full Lifecycle Orchestrator

Quick ref: /discovery -> /crank -> /validation, then report.

Execute this workflow. Do not only describe it. RPI is autonomous unless --interactive is set. The user touchpoint is after validation, or after a real blocked state exhausts retries. Read [references/autonomous-execution.md](references/autonomous-execution.md) when you need the full autonomy contract.

When an external executor fails but the code surface may still be valid, read [references/codex-executor.md](references/codex-executor.md) and recover through Codex direct checks before declaring a source-level regression.

Loop position

/rpi is the orchestrator across every move of the [operating loop](../../docs/architecture/operating-loop.md): BDD intent → vertical slices → conflict-free wave → bead acceptance → evidence + learning capture. It delegates each move to the skill that owns it (/discovery, /plan, /crank, /validation, /forge//retro), and enforces three loop-level invariants:

  • No move-skipping. Strict delegation is on by default; phases never compress, and validation cannot be skipped. The lifecycle objective is preserved across the whole loop.
  • The first failing test is the bead's contract. With --test-first on (the default), /crank is invoked with the TDD-per-slice discipline; --no-test-first is an explicit opt-out, not a fast path.
  • Acceptance examples close the bead, not activity. Validation FAIL re-cranks on the same objective up to 3 attempts; DONE requires the acceptance roll-up in the [slice-validation template](../../docs/templates/slice-validation.md) to be fully green.
  • Ports stay visible. Preserve the

[Intent-to-Loop Hexagon](../../docs/architecture/intent-to-loop-hexagon.md) boundary as the objective crosses shape_intent, persist_intent, plan_slices, execute_wave, validate_acceptance, and record_evidence.

  • Context density survives phase boundaries. Apply the [Context Density Rule](../domain/references/context-density-rule.md) to every phase handoff and final report: keep intent, boundary, evidence, decision, constraint, and next action; omit or link anything else.

Core Contract

RPI delegates via Skill(skill="discovery", ...), Skill(skill="crank", ...), and Skill(skill="validation", ...) as separate tool invocations. Keep strict delegation on by default; do not compress phases, replace phase skills with direct agent spawns, or skip validation. Read [../shared/references/strict-delegation-contract.md](../shared/references/strict-delegation-contract.md) for the full anti-compression contract. See [references/isolation-contract.md](references/isolation-contract.md) for the four-lever model, phase-isolated skill transport, and the compression patterns scripts/check-skill-isolation.sh flags. See [references/best-practices.md](references/best-practices.md) for the principle and anti-pattern citation table.

When the runtime supports phase isolation, keep /rpi visible in the main session and run each phase contract through isolated transport: phase skill name in, bounded handoff artifact in, phase artifact/verdict/next action out. The transport may be a daemon job, process runner, or subagent wrapper, but it must execute the declared phase skill contract rather than doing phase work directly.

RPI owns one lifecycle objective across all phases. Preserve the discovered epic_id when present; otherwise preserve the original goal and execution packet objective. A child bead or one ready slice is context, not a replacement objective. <promise>PARTIAL</promise> from /crank means retry Phase 2 on the same objective.

Route And Classify

  1. Create .agents/rpi/.
  2. Resolve --from:
  3. default, research, plan, pre-mortem, brainstorm -> discovery
  4. implementation or crank -> implementation
  5. validation, vibe, or post-mortem -> validation
  6. If the input is a bead and --from is absent, resolve it with bd show:
  7. epic -> implementation with that epic
  8. child with parent -> implementation with the parent epic
  9. Classify complexity:
  10. fast: short/simple goal or --fast-path
  11. standard: medium goal or one scope keyword
  12. full: --deep, complex-operation keyword, 2+ scope keywords, or >120 chars
  13. Log RPI mode: rpi-phased (complexity: <level>).

Track state compactly:

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,
  verdicts: {}
}

Complex-operation keywords include refactor, migrate, rewrite, redesign, rearchitect, overhaul, decouple, deprecate, split, extract module, and port. Scope keywords include all, entire, across, everywhere, every file, system-wide, global, and codebase.

Phase DAG

Enter at the routed phase and run every phase after it.

  1. Discovery: invoke /discovery <goal> [--interactive] --complexity=<level>

directly or through phase-isolated skill transport. On DONE, read .agents/rpi/execution-packet.json or the run archive and preserve its objective spine. On BLOCKED, stop with the discovery verdict.

  1. Implementation: invoke /crank <epic-id> when the packet has epic_id;

otherwise invoke /crank .agents/rpi/execution-packet.json, directly or through phase-isolated skill transport. Pass --test-first or --no-test-first through. On DONE, record ao ratchet record implement 2>/dev/null || true and continue. On PARTIAL or BLOCKED, retry the same objective up to 3 total attempts.

  1. Validation: invoke /validation <epic-id> --complexity=<level> when an

epic exists; otherwise invoke /validation --complexity=<level>, directly or through phase-isolated skill transport. Add --strict-surfaces when --quality is set. On FAIL, extract findings, re-run /crank on the same objective, then re-run /validation, up to 3 total validation attempts. On DONE, record ao ratchet record vibe 2>/dev/null || true.

  1. Report: summarize phase verdicts and epic status using

[references/report-template.md](references/report-template.md). With --loop, restart from discovery on FAIL while cycle < max_cycles. With --spawn-next, read .agents/rpi/next-work.jsonl and suggest the next command without invoking it. Before emitting the report, apply the Context Density Rule: every line should carry intent, boundary, evidence, decision, constraint, or next action.

Phase Data Contract

The execution packet carries the repo execution profile through contract_surfaces, done_criteria, and queue claim/finalize metadata. Keep the latest alias at .agents/rpi/execution-packet.json and read [references/phase-data-contracts.md](references/phase-data-contracts.md) for schemas and archive paths.

Complexity-Scaled Gates

Pre-mortem

  • complexity == "low" or "fast": inline review, no spawning (--quick)
  • complexity == "medium" or "standard": inline fast default (--quick)
  • complexity == "high" or "full": full council, 2-judge minimum; max 3 total attempts

Final Vibe

  • complexity == "low" or "fast": inline review, no spawning (--quick)
  • complexity == "medium" or "standard": inline fast default (--quick)
  • complexity == "high" or "full": full council, 2-judge minimum; max 3 total attempts

Post-mortem (STEP 2)

  • complexity == "low" or "fast": inline review, no spawning (--quick)
  • complexity == "medium" or "standard": inline fast default (--quick)
  • complexity == "high" or "full": full council, 2-judge minimum; max 3 total attempts

Flags

| Flag | Default | Purpose | |------|---------|---------| | --from=<phase> | discovery | Start at discovery, implementation, or validation | | --discovery-artifact=<path> | unset |

Compartilhar X LinkedIn