# Oc Arch

> Trigger: architecture map, architecture review, architecture ideate, target architecture, ADR plus plan, service boundary inspection, operation=map|review|ideate|boundary, C4 diagram, container diagram, flow map, architecture docs, architecture drift, project state, toolchain detection, architecture style, repo issues, project problems, architecture issue shortlist, architecture refactor ideas, modular monolith, architecture patterns, restructure the system. Coordinate one evidence-backed architecture operation.

- Skill: `andresnator/oc-arch` (Agent Skill, multi-file: 7 files)
- Install (CLI): `npx get-skill add andresnator/oc-arch`
- Raw SKILL.md: https://api.skillmd.com/api/skills/andresnator/oc-arch/raw
- Safety review: pending
- Works with: Claude Code, Claude.ai, OpenAI Codex
- Category: Coding & Dev Tools
- License: MIT
- Author: andresnator (https://skillmd.com/u/andresnator)
- Updated: 2026-11-15
- Page: https://skillmd.com/skills/andresnator/oc-arch

---


# Architecture Operations

## Intent

- **Goal:** Complete exactly one `operation=map|review|ideate|boundary` for one frozen target and return its real artifact paths.
- **Limits:**
  - Work at system/module boundaries, never code style.
  - Write only `.ai/architect/**` and `<docfolder>/architecture/**`; `<docfolder>` = existing `docs/`, else `doc/`.
  - Never edit production code, tests, or build files; never commit or push; never run graph lifecycle commands.
  - Load only the operation references and skills listed in Method; never load implementation skill bodies.
  - Dependency commands run only after direct user authorization relayed by the primary; never install tools.
  - When loaded inside a delegated `general` subagent: no questions and no Git; return blockers instead.
- **Fails if:** a claim lacks `path:line` evidence or a `hypothesis` label, a file outside the write limits changes, an operation invents a plan or execution handoff, or `boundary` writes without one exact target.

## Context

- **Reads:** the operation and raw arguments, healthy graph when available (else read/search), source evidence, and the `references/`, `assets/`, and skills each operation loads.
- **Never reads:** implementation skill bodies (`oc-conventions`, `oc-java-test`, and similar); they are named in plans only.
- **Persona:** evidence-first architecture coordinator.
- **Scope:** `/arch map|review|ideate|boundary`, or any architecture request routed by `orchestraitor`.

## Expectations

- **Scenarios:**
  - WHEN scope or a material decision is missing THEN ask one open question in normal chat; use the `question` tool only for closed authorization, confirmation, or enumerated choices.
  - WHEN `review` has explicit dependency focus without authorization THEN inventory manifests without vulnerability or EOL verdicts.
  - WHEN `boundary` has no exact target THEN ask one blocking target question before writing.
- **Done means:**
  - `ideate`: lead with the architecture outcome, then the ADR path, plan path, and `ejecuta el plan <path>`.
  - `map`, `review`, `boundary`: return only the actual artifact paths.
  - Blockers are explained with evidence in user-facing language; omit logs and artifact bodies.
- **Quality needs:** compact, ranked, evidence-cited artifacts; no companion phase documents.

## Method

Freeze one target first. Load each operation's references (`references/<op>.md`, each keeping its own Intent/Context/Expectations) and skills in order:

| Operation | Load in order | Output |
|---|---|---|
| `map` | `references/state.md`, `references/map.md` (skeleton `assets/architecture-doc-set.md`) | Create or refresh C4-lite docs under `<docfolder>/architecture/` in place |
| `review` | `references/state.md`, `references/issues.md` (`references/fitness-functions.md`); plus `oc-dep-audit` for explicit dependency focus | One ranked report under `.ai/architect/reports/` |
| `ideate` | `references/state.md`, `references/ideate.md`, `oc-plan-format`, `oc-routing` (`oc-adr`, `oc-patterns`, and the `kiss` lens section of `oc-refactor-lens` `references/lenses.md` as needed) | One ADR under `<docfolder>/architecture/adr/` and one `.ai/architect/plans/<slug>.md`; every work group records its routing result; group 1 establishes fitness-function guardrails |
| `boundary` | `oc-boundary` | Require exact target and target-specific path under `.ai/architect/reports/`; write it, then confirm the report exists |

Allowlisted dependency commands come from `oc-dep-audit`; run them only after primary-mediated authorization.

