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/war/references/02-implementation.md
View on GitHub# Implementation audit
This reference audits the **implementation** ({{CODE_SCAN_TARGET}}) against the Target Architecture. It delegates research to `@architect` (read-only), presents findings in the console for review, then saves a dated snapshot.
The subject is code and infrastructure — not design artifacts. For design artifact review, the WAF assessment runs inside the `{{provider:invoke:design}}` lifecycle itself (`patterns/waf-review.md`, applied from Solution's gate step) rather than as a standalone command. For version-level design review across all stories, use `{{provider:invoke:war}} design [VERSION]`.
> ⚠️ Follow every step in order. Do not skip, summarize, or improvise. If you are unsure, ask before deviating.
## Step 1 — Determine scope
Apply `{{provider:skills_root}}/war/patterns/scope-resolution.md` (fill the placeholder as "Code").
## Step 2 — Read Target Architecture
Read the following docs for the target version. Do not ask the developer — read them directly:
- `System Overview.md`
- `Non-Functional Concerns/Requirements.md`
- `System Sizing.md`
- All files in `Containers/`
- All files in `Non-Functional Concerns/`
Extract per container:
- Stated responsibilities and boundaries
- Integration points (inputs/outputs)
- Technology choices
- Non-functional expectations (latency, availability, security posture)
Do not summarise to the developer. Proceed to Step 3.
## Step 3 — Delegate code audit to @architect
Invoke `@architect` with the following research prompt (do not deviate from this pattern):
> "Read {{CODE_SCAN_TARGET}}. For each {{BUILD_UNIT_LABEL}}, identify:
>
> 1. What the app does (inferred from code and config)
> 2. What it connects to (dependencies, external calls, env vars)
> 3. Any patterns that appear to violate or diverge from the following architecture intent:
>
> <paste the relevant architecture context extracted in Step 2>
>
> Return your findings as a structured list. Do not write files. Do not make changes."
`@architect` returns findings as text. Do not let it write files autonomously.
## Step 4 — Assess each pillar
Using the architecture docs (Step 2) and the architect's findings (Step 3), assess each pillar in scope.
### Pillar definitions
{{WAF_PILLARS_TABLE}}
### RAG rating
| Rating | Meaning |
| -------- | ------------------------------------------------------------------- |
| 🟢 Green | Implementation matches architecture intent — no material gaps |
| 🟡 Amber | Partially implemented — gaps exist but risk is bounded or mitigated |
| 🔴 Red | Not implemented or diverges materially from architecture intent |
### Output per pillar
```
### <Pillar name> — <RAG emoji + colour>
**Strengths**
- What the implementation gets right
**Gaps**
- Specific gaps, referencing the app/file/config where the divergence was found
**Recommendations**
- P1: address before production
- P2: address in next iteration
- P3: backlog
```
## Step 5 — Present, then save
Apply `{{provider:skills_root}}/war/patterns/present-and-save.md` (fill the placeholders as "" / "implementation"), using `{{provider:skills_root}}/war/templates/implementation-report.md` as the file structure. Replace all `{{VERSION}}`, `{{YYYY-MM-DD}}`, and `{{all pillars | <pillar name>}}` placeholders with actual values, and fill in all audit content.
## Step 6 — Confirm and close
After saving:
> "Audit saved to `docs/Target Architecture (HLD)/WAR/{VERSION}/{date}-implementation-audit.md`.
>
> To re-run after implementation changes: `{{provider:invoke:war}} implementation`
> To scope to one pillar: `{{provider:invoke:war}} implementation {pillar}` (e.g. `{{provider:invoke:war}} implementation Security`)
> To review design artifacts for this version: `{{provider:invoke:war}} design {VERSION}`"
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 |