oh-my-githubcopilot 2.0.0-alpha.1cd01f4 → 2.0.0-alpha.2aedbd0

package/AGENTS.md

@@ -176,5 +176,29 @@ Before starting work on an issue:
 
 <!-- v3-ai-sdlc-init:start -->
 ## AI SDLC v3
-This repo follows the v3 AI-SDLC layout. See `.ai/matrix.json`, `.memory/human-override/`, and `docs/architecture/adr/`. Modules at `r3dlex/skills/ai-sdlc-init/modules/`.
+
+This repo follows the v3 AI-SDLC layout (`topology_type: standalone`, depth 0). It is the single source of truth for the agent operating contract; `CLAUDE.md` and `GEMINI.md` are thin pointers to this file (ADR-0007).
+
+### Workflow
+
+- Workflow doc: [`.ai/workflows/repo-workflow.md`](.ai/workflows/repo-workflow.md)
+- Workflow manifest: [`.ai/workflows/repo-workflow.json`](.ai/workflows/repo-workflow.json)
+- Handoff index: [`.ai/handoff/init-ai-repo-handoff.md`](.ai/handoff/init-ai-repo-handoff.md)
+
+Continue through the mandatory phases and record status in `.ai/phases/<phase>/status.json`. See `.ai/matrix.json`, `.memory/human-override/`, and `docs/architecture/adr/`. Modules at `r3dlex/skills/init-ai-repo/modules/`.
+
+### Harness Map
+
+The six context types this harness assembles, and where each lives (ADR-0008):
+
+| Context type | Canonical source | Static or dynamic |
+| --- | --- | --- |
+| `Instructions` | `AGENTS.md`, `.ai/system-prompts/`, `.ai/rules/` | Static |
+| `Knowledge` | `docs/architecture/`, `docs/specifications/`, `docs/learning/` | Static |
+| `Memory` | `.memory/human-override/`, `.memory/self-learned/` | Dynamic |
+| `Examples` | `.ai/evals/<set>/`, `docs/learning/concept-maps/` | Static |
+| `Tools` | `.ai/skills/`, `.ai/mcp/registry.json` | Dynamic |
+| `Guardrails` | `.ai/rules/security.md`, `.ai/rules/technical-bounds.md`, `.ai/policies/` | Static |
+
+**Static-vs-dynamic boundary.** Static context is fixed at the start of a task and is reviewed and versioned in-repo; dynamic context is assembled per-run (memory written by local agents, tool/MCP results resolved at call time). This boundary is a reviewed, versioned decision (ADR-0008); moving a context type across it requires an ADR update.
 <!-- v3-ai-sdlc-init:end -->

package/CHANGELOG.md

@@ -2,7 +2,7 @@
 
 All notable changes to oh-my-githubcopilot are documented here.
 
-## [2.0.0] — 2026-06-13
+## [v2.0.0] — 2026-06-13
 
 ### Breaking Changes
 - **Agent parity (23→19):** Six agents removed, merged, or renamed:

package/README.md

@@ -141,5 +141,5 @@ If omp saves you time, consider [sponsoring the project](https://github.com/spon
 
 <!-- v3-ai-sdlc-init:start -->
 ## AI SDLC v3
-This repo follows the v3 AI-SDLC layout. See `.ai/matrix.json`, `.memory/human-override/`, and `docs/architecture/adr/`. Modules at `r3dlex/skills/ai-sdlc-init/modules/`.
+This repo follows the v3 AI-SDLC layout (`topology_type: standalone`, depth 0). `AGENTS.md` is the single source of truth; `CLAUDE.md` and `GEMINI.md` are thin pointers (ADR-0007). Workflow: [`.ai/workflows/repo-workflow.md`](.ai/workflows/repo-workflow.md) and [`.ai/workflows/repo-workflow.json`](.ai/workflows/repo-workflow.json). See `.ai/matrix.json`, `.memory/human-override/`, and `docs/architecture/adr/`. Modules at `r3dlex/skills/init-ai-repo/modules/`.
 <!-- v3-ai-sdlc-init:end -->

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "oh-my-githubcopilot",
-  "version": "2.0.0-alpha.1cd01f4",
+  "version": "2.0.0-alpha.2aedbd0",
   "description": "Multi-agent orchestration for GitHub Copilot CLI. 19 agents, 59 skills, parallel execution, HUD, PSM, SWE-bench.",
   "author": {
     "name": "r3dlex"