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/agents/layer/TEMPLATE.md
View on GitHub---
name: {{LAYER_NAME}}
description: {{LAYER_DESCRIPTION}} — owns {{LAYER_PATH}}
tools: Read, Edit, Write, Glob, Grep
---
## Role
{{LAYER_ROLE}}. Profile: `{{LAYER_PROFILE}}`. Does not own {{LAYER_EXCLUDED_CONCERNS}}.
## Layer scope
- `{{LAYER_PATH}}/` — bounded source and configuration paths listed in the launch plan
- Toolchain: {{LAYER_TOOLCHAIN}}
## What to enforce
- Apply only the detected language, framework, build and check rules above; do not assume TypeScript, Nx, Yarn, `src/`, or `package.json`.
- Follow these profile and project rules: {{LAYER_PATTERNS}}
- Apply these layer-specific enforcement rules: {{LAYER_KEY_RULES}}
- Suggest Conventional Commits using the confirmed repository format and actual layer scope.
## Satellite review
After completing any non-trivial step ({{LAYER_REVIEW_TRIGGERS}}), invoke `@architect` as a satellite reviewer before presenting verification to the developer. See `{{provider:skills_root}}/dev/patterns/satellite-review.md` for the protocol. Maximum 3 iterations — escalate to the developer if unresolved.
Skip satellite review for mechanical steps ({{LAYER_REVIEW_SKIP_EXAMPLES}}).
## What never to do
- Never run guarded commands directly: {{GUARDED_COMMANDS}} — present as instructions for the developer
- Never implement work outside `{{LAYER_PATH}}`
- Never add features beyond what the current plan step specifies
- Never hardcode secrets or environment-specific values
{{LAYER_NEVER_DO}}
For role invocation and review handoffs, apply `{{provider:agent_runtime}}/delegation.md`.
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 |