DataArt/artisyn-implementation-harness / skills/implementation-harness
implementation-harness
FlaggedInstall the portable AI-dev harness, rebuild its operational graph standalone, harvest project skill improvements into its canonical templates, package direct canonical edits into a portable bundle, or apply canonical updates to an existing project. Use /implementation-harness launch, /implementation-harness reindex-graph, or /implementation-harness patch harvest|prepare|apply.
canonical/adaptors/copilot/delegation.md
View on GitHub# Delegation in Copilot
Installed specialists live in `.github/agents/<name>.agent.md`. Use an exposed,
authorized delegation tool (normally `task`) with the installed agent's identity
and the tool's actual schema. The host selects the session agent; mentioning a role
or writing `@name` is not proof a subagent was invoked.
Do not start a separate host process to simulate an unavailable delegation tool.
Where the host supports them, generated specialists use `include-custom-instructions: true`
so delegated work receives the repository conventions, and `strict-tools-list: true`
with an explicit tool list. Verify each key for the host. Tool availability does not
grant execution approval or filesystem scope.
Give each worker explicit inputs, disjoint output paths, scope and evidence. The
orchestrator owns shared reports and verifies returned files. Never enable fleet
mode, auto-delegation or extra permissions merely to satisfy an instruction.
For docs-writer authoring only, if delegation is unavailable or prohibited, apply
the installed role inline and record the fallback. This is not independent review.
If independent review is unavailable, report it as pending for human review or
an explicitly authorized exception at the workflow's existing gate.
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| reverse-engineer-anythingmorluto/reaReverse engineer native, managed, Electron/JavaScript, packaged, firmware, and browser targets with REA, and build agent environments (AgentEnv bundles) of web applications from a live instance or a capture, and of Linux desktop apps with a task from a request. Use shipped-artifact or requested runtime evidence to explain features, compare versions, decompile code, or guide a reconstruction. Skip REA for ordinary source-repository architecture analysis. | Stars: 471k | Updated | Claude CodeCodex | Verified | Install |
| diagnosing-superpowersobra/superpowersUse when a superpowers session went wrong and your human partner wants to know why — repeated work, ignored plans, stumbles, poor results, a skill that didn't fire, "it took too long", "why is it so expensive", "what is it doing" — or wants to build a bug report for the superpowers maintainers, for the current session or a past one identified by id or path, on any harness. | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| dispatching-parallel-agentsobra/superpowersUse when facing 2+ independent tasks that can be worked on without shared state or sequential dependencies | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| executing-plansobra/superpowersUse when executing an implementation plan in the current session as the implementer yourself — your human partner chose inline execution, or no subagent tool is available | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |