odin-run

Plugin odin-run from marketplace odin-marketplace in OutlineDriven/odin-claude-plugin. Commands read from the repo's manifest — 1 month ago.

Skills (46)

• append-run-log

  Use when a completed agent run must be recorded as durable, queryable evidence. Not for remote, credential, publish, deploy, or irreversible changes.

• artifact-arena

  Use when asked to run /artifact-arena to generate and judge competing artifact implementations. Not for remote, credential, publish, deploy, or irreversible changes.

• audit-loop-scaffold

  Use when loop scaffold files have drifted from their provenance-pinned templates. Not for remote, credential, publish, deploy, or irreversible changes.

• autopilot

  Use when a human has an approved delivery plan and wants the full chain run under phase gates. Not for planning, open-ended debugging, or single-step execution: use work directly.

• cloud-task-orchestrator

  Use when a human explicitly runs /cloud-task-orchestrator for a large task across cloud agents to drain a verified task graph. Not for local subagent coordination: use orchestration-patterns.

• corroborate-by-independent-reruns

  Use when a candidate patch or answer needs independent corroboration before it is trusted. Not for multi-stance investigation: use council.

• cross-run-playbook

  Use when a long agentic project needs each cycle to end in a learning memo and a keep/iterate/restart decision. Not for single-pass builds.

• cybernetic-loop

  Use when the caller supplies a falsifiable out-of-happy-path invariant and a finite budget. Restores via bounded patches or reverts. Not for normal feature delivery or universal retries.

• cycle-memo

  Use when a build, QA pass, demo, user complaint, or abandoned attempt leaves the next pass needing lessons rather than code. Not for changelog extraction. Not for session handoff: use handoff.

• diagnose-loop-health

  Use when a configured loop misbehaves, produces unexpected results, or its setup soundness is questioned. Not for tasks that require source or remote-system changes, not for loop design.

• diagnose-wave-stall

  Use when a dispatched agent wave has stopped progressing: a result that never arrives or one that exists but stays unconsumed, and the blocking node must be named. Not for a configured loop misbehaving: use diagnose-loop-health. Clearing actions are recorded, never executed. Re-dispatch follows only

• diamond-task

  Use when one issue or PR is too large for a worker and partitions into disjoint write sets. Not for independent parallel tasks: use parallel-launch. No remote or irreversible changes.

• do-it-now

  Use when the user says do it now, ship it now, no phases, or finish it now, or would defer work to phases, rollouts, follow-up PRs, or TODOs. Not for remote, credential, publish, deploy, or irreversible changes.

• duet

  Use when the user invokes /duet, says pair on this, or faces aesthetic, architectural, or irreversible decisions. Not for one-shot fork resolution: use decide.

• feedback-sweep

  Use when asked to /feedback-sweep [setup|reconfigure] [mode:non-interactive]. Not for pattern discovery: use feedback-pattern-sweep.

• figure-it-out

  Use when non-trivial work should run a matched playbook to verified real-surface completion, or a bespoke workflow when none fits. Not for remote, credential, publish, deploy, or irreversible changes.

• gate-file-completion

  Use when a task needs gate-file proof before a done claim. Also fires on "gate-file-completion", "unlazy", "depth tree", "gates", or "do not stop until it is done".

• gate-proposed-change

  Use when asked to evaluate a proposed commit, merge, or auto-merge against a gate config. Not for landing PRs: use gate-and-merge. Read-only.

• goal-prompt-drafting

  Use when asked to draft copy-ready /goal objectives for long-running agents. Not for source or remote-system changes.

• guardrail-carve-run

  Use when guardrail-adjacent material (stealth, scraping, privacy, IP, policy, security) or mixed reversible/irreversible, sensitive work, or the user says "autobahn this". Not for carved risky work.

• implement-spec

  Use when a ticket DAG from a complete specification needs parallel execution into a green draft PR. Not for a settled ticket with no spec: use work. Not for ticket decomposition: use to-tickets.

• llm-self-loop

  Use when a button click, dashboard check, or human verdict sits inside an iteration loop and needs an autonomous gate. Not for remote, credential, publish, deploy, or irreversible changes.

• negotiate-run-budget

  Use when a high-priority run reaches at least 90% of its budget and requests an extension. Never self-grants. Not for low-priority runs: let those exhaust silently.

• new-space

  Use when a user starts a new work session and asks to split human decisions from agent execution. Not for remote, credential, publish, deploy, or irreversible changes.

• notion-writer

  Use when the user explicitly asks to create, update, query, or archive Notion pages, databases, or blocks. Not for bulk operations, recursive edits, or widening the workspace scope.

• orchestration-patterns

  Use when work decomposes across subagents or role panels and needs coupling-based orchestration. Not for cloud-agent task-graph orchestration: use cloud-task-orchestrator.

• parallel-launch

  Use when work splits into independent sub-tasks or cross-domain research. Not for durable scope ownership with per-scope review: use partition-scopes-to-subagents.

• partition-scopes-to-subagents

  Use when asked to partition non-overlapping scopes across subagents and drive each to completion. Not for concurrent independent sub-tasks: use parallel-launch.

• post-to-slack

  Use when the user explicitly asks to share a message on Slack through an incoming webhook. Not for posting without an explicit request or for retrying an ambiguous delivery.

• propose-external-change

  Use when asked to change state in an external system: propose the write locally and halt at the human gate without executing. Not for remote, credential, publish, deploy, or irreversible changes.

• respond-to-slack-thread

  Use when the user asks to reply to or follow up on a specific Slack thread. Not for top-level messages, deleting messages, or composing the reply text.

• saga

  Use when a user runs saga or asks to autonomously build a sizable feature. Not for executing a given plan: use subagent-driven.

• schedule-dependency-waves

  Use when work units carrying declared dependencies must be ordered into execution waves before any dispatch, including detecting a dependency cycle. Not for partitioning one issue into disjoint write sets: use diamond-task. Not for concerns with no dependencies: use parallel-launch.

• scheduler

  Use when asked to set, list, pause, update, or delete a reminder or local task that fires at a confirmed time or interval. Not for destructive, remote, credential, publish, or deploy operations.

• seed-casebook

  Use when a user opens a build cycle in a repo with an iteration convention and wants the casebook seeded with real content. Not for ongoing triage or multi-repo setup.

• show-me-your-work

  Use when the user invokes it to append a structured decision record to an append-only TSV log, ending with an Attention section for reviewers. Not for an ephemeral visual: use show-me.

• size-the-run

  Use when a run could be over- or under-powered, before dispatching a subagent, or the user asks how hard to think about a task. Recommends one tier and effort level. Not for executing the sized task.

• subagent-driven

  Use when a user says execute with subagents or hands over an ordered multi-task plan. Not for credential, paid, or deployment work, or any mutation outside the skill''s designated workspace.

• swarm

  Use when asked to run partitioned parallel coverage or races across isolated workers. Don''t use for remote, credential, publish, deploy, or irreversible changes.

• thin-repo-pulse

  Use when a scheduled or watcher tick fires and a lightweight pulse must capture current external state. Not for remote, credential, publish, deploy, or irreversible changes.

• watch-for-harness-mode

  Use when a proven watch pattern should become a reusable harness artifact with configurable inputs. Not for remote, credential, publish, deploy, or irreversible changes.

• watch-for-structured

  Use when the user wants to classify a surface state and page an on-call API when triggered. Not for read-only anomaly watching without paging: use watch-for.

• watch-for

  Use when monitoring a file, log, endpoint, or artifact for drift or errors, or polling a target until a predicate holds. Modes: watch (default), until. Not for source or remote-system changes.

• wizard

  Use when asked to generate a bash wizard for provisioning, credentials, dashboards, migrations, or cutovers a human performs. Not for remote, credential, publish, deploy, or irreversible changes.

• work

  Use when implementing from a plan, spec, clear build request, or settled ticket, orchestrated or standalone. Don''t use for open-ended debugging (figure-it-out), exploration, or read-only research.

• workflows-driven

  Use when work decomposes across subagents or phases: audits, migrations, research sweeps, or scale one context cannot hold. Not for remote, credential, publish, deploy, or irreversible changes.

Similar plugins