en un clic
planning
Planning Pipeline — Skill Reference
Installer avec Codex ou Claude Copiez ce prompt, collez-le dans Codex, Claude ou un autre assistant, puis laissez-le vérifier la page du skill et l'installer pour vous.
Menu
Planning Pipeline — Skill Reference
Installer avec Codex ou Claude Copiez ce prompt, collez-le dans Codex, Claude ou un autre assistant, puis laissez-le vérifier la page du skill et l'installer pour vous.
Basé sur la classification professionnelle SOC
Run the canonical Megaplan planning pipeline from its Arnold plugin home.
Launch one durable, mutation-authorized meta-fixer to repair a failed automated fixer and its missed backstop, retrigger ordinary repair, and prove the identified epic or session advances. Use when a watchdog, repair loop, meta-repair loop, or progress auditor ran or should have run but the real chain stayed stuck, repeated stale evidence, claimed false success, or failed to self-correct. Invoke with `--target "EPIC_OR_SESSION_TEXT"`.
Launch an external model as a subagent for a second opinion, adversarial review, or delegated work. Default pathway is an agentic DeepSeek / Kimi / Zhipu GLM hermes subagent (file/web/terminal tools, one process or fanned out N-wide); also Codex (GPT-5.5) and Claude via the Agent tool. Use for independent root-cause analysis, cross-checking your reasoning, judge/jury panels, or handing implementation to a different model.
Scaffold a new Arnold native-first pipeline package from the _template skeleton.
Adversarial review of prose drafts by N reviewers, then revise. Not for code.
Survey every place loose work hides in a git repo — starting with the current checkout's own uncommitted/untracked/unpushed work, then local branches, all worktrees (`.megaplan-worktrees`, `.megaplan/bakeoffs/*`, agent-tool worktrees), stashes, detached HEADs, interrupted rebases/merges, submodules, remote branches on origin and other remotes, fork PR refs, sibling repo variants, other clones of this repo elsewhere on disk, the megaplan-cloud machine (Hetzner box) and every workspace on it, and GitHub Codespaces — classify each as land-on-main / delete / parked with reasoning, and act only on explicit per-item approval. Use when the user says "clean up loose branches", "prune branches", "what branches can I delete", "clean up worktrees", "review my stashes", "what's lying around in this repo", or asks for branch / worktree / stash housekeeping.
| name | planning |
| description | Planning Pipeline — Skill Reference |
The megaplan pipeline (packaged at arnold_pipelines/megaplan/) is the built-in megaplan plan-production substrate.
Its canonical registry identity is megaplan with the legacy alias planning → megaplan.
It orchestrates the full prepare → plan → critique/gate/revise loop →
finalize → execute → review lifecycle.
The gate stage emits a PipelineVerdict whose recommendation field is one
of the following GateRecommendation literals:
| Verdict | Meaning |
|---|---|
proceed | Gate approved the plan; advance to finalize (and optionally execute). |
iterate | Gate rejected the plan; re-enter the critique → revise loop. |
tiebreaker | Evaluators are split; hand off to the tiebreaker stage for adjudication. |
escalate | Quality ceiling reached at current tier; escalate to a higher-complexity model. |
Robustness controls the depth of the critique/gate loop and the number of
evaluators engaged. Canonical names (accepted by --robustness / config):
| Level | Alias(es) | Behaviour |
|---|---|---|
bare | tiny | Single-pass, no gate loop. Fastest; for quick drafts. |
light | — | One critique + revise round, minimal gate criteria. |
full | standard | Standard gate loop (default). Balanced quality/cost. |
thorough | robust | Extended gate loop, stricter criteria, more evaluators. |
extreme | superrobust | Maximum depth, all evaluators enabled. |
The default robustness when no --robustness flag is supplied is full.
prep → plan → critique ──→ gate ──proceed──→ finalize [→ execute → review]
↑ │
└──iterate────┘
│
└──tiebreaker──→ [adjudication] → finalize
Driver substrate: subprocess_isolated (execute/review) + graph+loop-node
(critique→gate→revise subloop).
arnold_api_version: 1.0
capabilities: plan, execute, review