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/skills/dev/templates/plan.md
View on GitHub---
name: Dev Plan Template
description: Template for 1-plan.md — the immutable implementation plan created by {{provider:invoke:dev}} plan. Strict structure; the intent it implements lives in 0-intent.md and is linked, not repeated.
type: reference
---
# <TICKET>: <Short Title> — Plan
| Field | Value |
| ------- | ------------------------------ |
| Ticket | {{PROJECT_KEY}}-XX |
| Intent | [0-intent.md](0-intent.md) |
| Branch | `feat/{{PROJECT_KEY}}-XX-slug` |
| Created | YYYY-MM-DD |
<!--
Do not repeat the problem, outcome, scope or constraints here. They live in
0-intent.md (see interfaces/intent.md). This document answers one question: how.
-->
## Solution
<One short paragraph: the approach and why it fits the intent and the architecture.
Name the HLD container(s) touched and anything reused.>
```mermaid
%% Required when the plan changes how things are wired together (network topology,
%% service-to-service routing, container boundaries, data flow) or when "what talks
%% to what" is not obvious from the step list. Show the TARGET state, coloured per
%% Documentation/01 Principles.md. Delete this block when a diagram adds nothing.
flowchart LR
A["Component A"]:::changed --> B["Component B"]:::existing
classDef changed fill:#176B54,stroke:#104D3C,color:#fff
classDef existing fill:#2C3E50,stroke:#1A252F,color:#fff
```
<!--
Optional: decisions taken while planning, one line each (choice, reason). Approved
deviations from the HLD are RF rows in 2-report.md, referenced here by ID, never a
second table.
-->
## Acceptance Criteria
<!--
Sprint contract — agreed before implementation starts. Derived from the intent's
outcome and boundaries plus tracker ACs. Each item must be checkable by the Test
stage with a command, curl, log output or a UI action. Do not change after approval.
-->
- [ ] `<AC-1>` — <what to observe and where>
- [ ] `<AC-2>` — <what to observe and where>
## Dependencies
<!--
Optional — omit this section if there are none.
Tickets, PRs or external preconditions that must be resolved before this plan runs.
-->
- {{PROJECT_KEY}}-XX must be merged first
## Steps
<!-- Step 1 writes the tests by default when the project has a test setup for the
touched layers: one case per testable acceptance criterion, in the existing framework.
Skipping it needs a stated reason (no setup for this layer, config/infra change proven
by a live check, one-line fix covered by an existing case). Keep the heading below and
replace the body, or replace it with "Step 1 — Tests: skipped because <reason>".
-->
### Step 1 — Tests: <what the cases cover>
**Changes:**
- `<project test location>` — new cases for `<AC-1>`, `<AC-2>`; type: `<unit / integration / e2e / ...>`, framework: `<existing one>`
**Verification:**
> Run: `<test command>`
> Expected: suite runs; new cases fail for the expected reason (`<assertion>`), nothing else breaks
### Step N — <Layer>: <What>
**Changes:**
- `<test location>` — only if this step needs cases Step 1 could not write yet
- `path/to/file.ts` — what changes and why
**Verification:**
> Run: `<command>`
> Expected: `<what to see>` — including relevant tests passing, where applicable
>
> Or: open `<URL>` and confirm `<what>`
Run required verification before dependent steps; request human verification only when needed.
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 |