Menu
Steps to create a new Arnold native-first pipeline package from the template.
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 | new-arnold-pipeline |
| description | Steps to create a new Arnold native-first pipeline package from the template. |
arnold_pipelines/_template/ to arnold_pipelines/<your_pipeline>/.__init__.py: set name, description, capabilities, keep
driver=("native", "project+validate") and supported_modes=("native",),
and ensure build_pipeline() compiles the native program and returns a
projected Pipeline with a non-null native_program.pipelines.py: replace the skeleton @phase functions with real
logic. Use @pipeline, @phase, @decision, parallel,
compile_pipeline, and project_graph from arnold.pipeline.native.arnold pipelines check <your_pipeline> to validate the package
against the native-first authoring contract (metadata, driver, native
program, and graph projection).Pipeline carries a non-null native_program.The native_program compiled by build_pipeline() is a dispatch
substrate — it describes how the runtime executes the pipeline, but it
does not define the final visible compositional semantics. Panel
synthesis, join delegation, parallel merge strategy, subpipeline
ownership, and Capsule projection are deferred to later Megaplan layers.
Do not add _legacy.py, graph fallback builders, compatibility
namespaces, shim packages, or temporary wrapper modules. The template and
this workflow are native-first only. Generated manifests and catalogs are
outputs of the authoring path, not editable source.