levi-qiao

quest-executor

Execute, resume, or verify an already compiled octopus quest whose objective contains the exact marker `octopus.quest-executor/v1`. Drive that single goal to reproducibly verified completion using its acceptance criteria, run controls, red lines, and owner boundary. Do not use to choose an arm, interview the user, generate or revise a prompt, or run an existing `.octopus/...` loop-graph node.

quest

Author one compiled quest objective for a goal-capable host. Use when the user asks to interview, generate, revise, or deliver a single self-contained octopus quest for Grok `/goal` or a Codex task. This is an authoring skill only. Do not use to execute or resume an objective marked `octopus.quest-executor/v1`; use `quest-executor` for that. Use `loop-graph` authoring for gated milestones, split executor/supervisor runs, or loop-only hosts.

graphkit

Run a long-horizon coding task as a small graph of agent nodes instead of one drifting loop. Generates an executor node (works against a single-source-of-truth ledger) and a clean-context supervisor node that audits from outside the executor's context — re-verifying claimed-done work, checkpoint-committing what passes, and correcting drift through a one-way directives file. Use for multi-round tasks where an agent tends to scope-creep, fake "done", or quietly lower the bar. Nodes share no context, so the executor runs on a cheap/fast model while a strong model supervises.

loop-graph

Author and optionally direct-launch one durable loop-graph run as executor, ledger, directives, and supervisor artifacts under a dated `.longgraph` directory, then present copy-ready host prompts. Use for multi-round work with gated milestones, independent audit, cross-host execution, or durable state. Detect Codex or Claude Code from context and create both same-host runtime nodes when the owner chooses direct launch. Existing runtime nodes are self-contained. A sibling preset (for example /loop-converge) may bind a pack and then follow this skill.

58 Updated 3 weeks ago

loop-graph

Author and optionally direct-launch one durable loop-graph run as executor, ledger, directives, and supervisor artifacts under a dated `.octopus` directory, then present copy-ready host prompts. Use for multi-round work with gated milestones, independent audit, cross-host execution, or durable state. Detect Codex or Claude Code from context and create both same-host runtime nodes when the owner chooses direct launch. Existing runtime nodes are self-contained.

41 Updated 1 months ago

longgraph

Author and optionally direct-launch one durable loop-graph run for long-horizon agent work. Use when the user invokes /longgraph, asks to design or start a multi-round run, needs durable state, gated milestones, owner decision boundaries, cross-host continuity, or independent audit. Detect Codex or Claude Code from context instead of asking. For unused/duplicate/slim loops, use /loop-converge. For a self-contained task, recommend the host's ordinary task or goal directly. Do not execute or resume existing runtime node files from this authoring skill.

loop-converge

Author and optionally direct-launch a two-node loop-graph run whose North Star is code convergence — delete unused code, merge duplicates, reuse, slim. Use when the user invokes /loop-converge, or asks to loop on dead code, duplication, unused exports, DRY cleanup, or merging twin implementations. Starts the owner interview (scope / authority / launch) immediately; supervisor is required. Not for adding features or a one-shot tidy. Do not execute or resume existing runtime node files from this authoring skill.

octopus

Author and optionally direct-launch one durable loop-graph run for long-horizon agent work. Use when the user invokes /octopus, asks to design or start a multi-round run, needs durable state, gated milestones, owner decision boundaries, cross-host continuity, or independent audit. Detect Codex or Claude Code from context instead of asking. For a self-contained task, recommend the host's ordinary task or goal directly. Do not execute or resume existing runtime node files from this authoring skill.