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/docs/Engineering Guide/Lifecycles/04 Architecture Lifecycle.md
View on GitHub# Architecture Lifecycle — Audit Commands
_Periodic health checks that surface gaps between design, implementation, and documentation._
---
## Intent
The architecture lifecycle runs outside individual tickets. Its job is to keep the team's view of the system accurate: Is the Target Architecture sound? Is the codebase aligned with it? Are the gaps documented?
The output is a dated snapshot that becomes the project's health record over time.
---
## When to use it
| Command | When |
| ------------------------------------ | -------------------------------------------------------------------------- |
| `{{SKILL_PREFIX}}where-we-are` | After a sprint; before a planning session; when "where are we?" is unclear |
| `{{SKILL_PREFIX}}war design` | After major HLD updates; before a design gate for a large feature |
| `{{SKILL_PREFIX}}war implementation` | Quarterly; before a major release; when architectural drift is suspected |
---
## Commands
| Command | What it does | Output |
| ---------------------------------------------- | --------------------------------------------------------------------------------- | ------------------------------------------------------------------------------------------ |
| `{{SKILL_PREFIX}}where-we-are [VERSION]` | Delivery gap report: designed vs implemented vs documented, per container | `docs/System Architecture (LLD)/where-we-are/<YYYY-MM-DD>-gap-report.md` |
| `{{SKILL_PREFIX}}war design [VERSION]` | WAF assessment of the Target Architecture documents — is the design itself sound? | `docs/Target Architecture (HLD)/WAR/<active version>/<YYYY-MM-DD>-design-audit.md` |
| `{{SKILL_PREFIX}}war implementation [VERSION]` | WAF code audit — does the implementation match the Target Architecture? | `docs/Target Architecture (HLD)/WAR/<active version>/<YYYY-MM-DD>-implementation-audit.md` |
---
## Invariants
**`{{SKILL_PREFIX}}where-we-are`:**
- Read `docs/Target Architecture (HLD)/README.md` first to find the active version. Do not hardcode a version name.
- Assess three dimensions per container: Designed (exists in HLD), Implemented (code exists), Documented (LLD folder populated). All three checked independently.
- Do not judge LLD quality — only presence. A folder with one file counts as "present".
- Delegate the code scan to the Architect agent — do not scan inline.
- Present the full gap matrix before asking to save. Never auto-save.
**`{{SKILL_PREFIX}}war design`:**
- Assess HLD documents only — not the codebase.
- All WAF pillars must be addressed. Present findings before saving.
- Save to `WAR/<active version>/` — create the folder if it does not exist. Never overwrite a previous report.
**`{{SKILL_PREFIX}}war implementation`:**
- Delegate code scan to the Architect agent.
- All WAF pillars must be addressed. Flag any implementation patterns that deviate from HLD without a recorded justification.
- Present findings before saving. Save to `WAR/<active version>/` — create the folder if it does not exist. Never overwrite a previous report.
---
## The audit loop
```
{{SKILL_PREFIX}}where-we-are → gap tickets → {{SKILL_PREFIX}}dev (fill gaps) → {{SKILL_PREFIX}}war implementation → verify alignment
```
Gap tickets produced by audit commands feed back into the Dev lifecycle as regular tickets.
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 |