orchestrating
/orchestrating
Use when two or more independent lanes can run in parallel, an output-only lane protects lead context from raw payload, or a handoff or durable run needs coordination.
- Author
- lawzava ↗
- Repository
- megapowers ↗
- Licence
- MIT
- Last repository change
- 25.10.2026
Assessment and security
- Files in this package
- 4
- Scripts
- 1
- HTML comments
- 0
- URLs in SKILL.md
- 0
No signals detected. Repository changed on 25.10.2026, without references to retired models or APIs.
MIT, open: use and modify while retaining author attribution.
- 1 scripts in this package. Review them before installing, as Claude may execute them.
Scripts: scripts/lanes.go
What it does and when to use it
Use when two or more independent lanes can run in parallel, an output-only lane protects lead context from raw payload, or a handoff or durable run needs coordination.
Original author description
Use when two or more independent lanes can run in parallel, an output-only lane protects lead context from raw payload, or a handoff or durable run needs coordination.
How it works
SKILL.md has no level-two headings · 46 lines, 339 words
SKILL.md preview
--- name: orchestrating description: Use when two or more independent lanes can run in parallel, an output-only lane protects lead context from raw payload, or a handoff or durable run needs coordination. when_to_use: "Trigger phrases: run these in parallel, fan out, spawn agents, split the work, delegate lanes, review while I build, several independent files or services to inspect at once." metadata: short-description: Parallel lanes, output-only lanes, and delegation coordination --- # Orchestrating Honor explicit delegation requests. Otherwise, delegate only when coordination value exceeds its overhead. Keep a no-op, one bounded task, or sequential dependency path inline. Scan dependencies, boundaries, ownership, and oracle before dispatch. Native agents are the default for matching lanes. Use one to three direct children with fresh, bounded context. For independent lanes whose results cannot reshape one another, issue spawn calls consecutively without intervening waits, continue independent lead work, and join every returned identity until completion, failure, or confirmed cancellation. For a plan with recorded prerequisites, start each task once its prerequisites have passed their oracle and its ownership is disjoint from running lanes; do not wait for a whole wave. Before dispatch, read [native dispatch and lane lifecycle](references/native-dispatch.md) and use only the active harness's call shape. One bounded output-only lane may use one fresh-context child returning `verdict`, `evidence`, `uncertainty`, and `next`. Keep bulky raw payloads in an artifact. Run verbose checks through the [run receipt tool](../verify-and-finish/references/run-receipt.md) and report command, exit status, result counts, and log path. Preflight tools, authentication, permissions, and write authority. Brief the outcome, disjoint ownership, constraints, oracle, prohibited scope, return condition, nested-delegation limit, and an advisory time budget; keep a hard timeout where needed. Shared guidance has one writer; shared writes and Git stay lead-owned. Honor an operator-selected route before native ranking. Otherwise, when `~/.config/megapowers/agent-capabilities.md` ([template](assets/agent-capabilities.md)) exists, read it once per session for eligible bindings; without it, use native defaults. Apart from a bound independent reviewer, the registry cannot authorize access, disclosure, permissions, writes, or effects. Before review dispatch, set its scope and correction-round budget. A spent budget leaves unresolved findings open; it never converts them into approval. Give related failures to one lane so it sees their shared cause. Join all identities before synthesis; a missing or silent result is a gap, never a pass. Treat each report as a claim and check its evidence before using it: re-run load-bearing claims yourself and sample the rest. Ordinary handoffs use inline inspection plus `verify-and-finish`; only an approved goal surviving interruption uses `autonomous-run`.
Files in this package (4)
- SKILL.md 3 KB
- assets/agent-capabilities.md 3 KB
- references/native-dispatch.md 4 KB
- scripts/lanes.go 15 KB
Versions
| Repository | Score | Licence |
|---|---|---|
| This page · lawzava/megapowers | 81 | MIT |
| zircote-plugins/claude-team-orchestration | 100 | MIT |
Database snapshot: 13.11.2026 · package version 4ea5b0a813af (SHA-256 digest of the entire package)
Downloads in the last 30 days: 0 · ranking
Report a problem with this skill: harmful content, incorrect descriptions or an author’s removal request.
Similar skills
- 90lanes
Set up and run lanes, one long-lived Claude Code session and one state file per kind of work. Use when the user wants to set up lanes in a project, add or rename a lane, start or resume a lane session ("lane: <slug>"), clear a lane in place, or asks why a new session was stopped by the lane guard. - 100run-parallel
[Orbit 2.4.4 Implementation] Independent tasks with parallel agents after an independence check. Use when: «параллельно», «одновременно несколько», «разгони задачи», «несколько агентов сразу»; parallel agents, run in parallel. - 100parallel-lanes
Split browser work across parallel lanes. Use when a task touches several independent sites or several independent records, when the user asks to run things in parallel, or when a sequential browser plan would take more than a few minutes. - 100team-orchestrator
Use when orchestrating Agent Teams for parallel development - team composition, task distribution, dependency management, and result aggregation. Triggers on /orchestrate, multi-agent coordination, parallel team work, task delegation to teammates. - 82parallel
Run independent tasks at once in subagents, race attempts at one task, or cover many parts of one job. Use it only when the user asks for parallel work. Use it when the user asks to run two or more independent tasks or failures in parallel. Use it also to race or compare several… - 100orchestrating-parallel-research
Use when running many independent tasks in parallel across isolated agent workspaces — fanning out research experiments (remote GPU, ablations, innovation points) or feature work — and you act as the coordinator deciding how to split, isolate, dispatch, and report.