Arnold

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.

Steps to create a new Arnold native-first pipeline package from the template.

Reference contract for the canonical Arnold native-first pipeline template scaffold.

Planning Pipeline — Skill Reference

Deliberation Pipeline

Three-round adversarial critique of epic drafts (high / mid / low abstraction) with revision after each round. Produces a chain-ready revised epic.

Walk a directory tree and audit whether each folder's children belong at the right level of abstraction. Produces a structured JSON audit plus a nested Markdown annotated tree.

Fan out DeepSeek Pro critics and a Kimi editor to iteratively simplify a piece of writing.

Arnold pipeline that classifies a user query, optionally researches via Hivemind/Banodoco, optionally edits a ComfyUI workflow, and always emits a final reply.

Three-round adversarial critique of epic drafts (high / mid / low abstraction) with revision after each round. Produces a chain-ready revised epic.

Keep a long-running autonomous process moving to completion by setting up a RECURRING REMINDER that, on every fire, checks status, unblocks whatever is stuck, pushes the work forward, and re-arms itself — until the whole thing is done. The canonical target is a `megaplan chain`/epic, but it works for any unattended run (a build, a deploy, a batch job). Use when the user says "babysit", "keep it moving", "push it forward", "unblock the run", "don't stop until it's done", "check on it every hour", or "set up a babysit loop".

Methodology for running multi-profile LLM bake-offs via megaplan and presenting fair, blind-assessed comparisons. Cost/quality discipline, prompt hygiene, pre-merge gates, and reporting patterns. Use when the user says "bakeoff", "bake off", "megaplan bakeoff", or asks to compare profile mixes head-to-head.

Run megaplan plans and chains inside a provider-managed container (today, Railway) with a persistent workspace volume. Use when the run needs to outlast a local terminal session, span multiple repos, or share a long-lived dev box across concurrent chains. Covers `cloud.yaml` fields, `extra_repos[]` + `chain_session` multi-tenancy, the operator loop, and the gotchas that wedge fresh runs.

Run an epic — a chain of sprint-sized megaplans driven sequentially via `megaplan chain`. Use when the work is bigger than ~2 weeks and needs to be decomposed into multiple plans with state, ordering, and failure semantics handled by the harness.

Observe an in-flight megaplan — introspect state, trace events, diagnose blockages, detect drift. Companion to megaplan-prep. Use during and after a run, not before.

Set up a megaplan run before invoking it — size the work, write the brief, score overall plan difficulty, and choose robustness/depth. Consult before every `python -m arnold.pipelines.megaplan init`.

AI agent harness for coordinating Claude and GPT to make and execute extremely robust plans.

File and manage megaplan tickets — short, repo-scoped notes on problems or observations that get folded into epics and auto-addressed when the resolving epic completes.