create-agdf 0.1.4 → 0.1.6

package/README.md

@@ -18,14 +18,14 @@ Optional flags:
 ## Targets and existing AGENTS.md
 
 - `codex` writes a repository-local Codex marketplace under `.agents/plugins/` and a local AGDF plugin copy under `plugins/agdf/`
-- `copilot` writes `AGENTS.md`, visible repository skills under `.github/skills/`, and AGDF control templates under `.agdf/control/`
-- `both` writes the Codex project marketplace plus the Copilot-facing repository files
+- `copilot` writes `AGENTS.md`, Copilot custom instructions under `.github/`, visible repository skills under `.github/skills/`, and AGDF control templates under `.agdf/control/`
+- `both` writes the Codex repository-local marketplace plus the Copilot-facing repository files
 
-If the target repository already has an `AGENTS.md`, `create-agdf` preserves it and writes `AGENTS.agdf.md` instead of replacing your existing instructions. Merge the AGDF fragment into your current `AGENTS.md` when you want Copilot to load both instruction sets. Use `--force` only when you explicitly want to overwrite generated files.
+If the target repository already has an `AGENTS.md`, `create-agdf` preserves it and writes `AGENTS.agdf.md` instead of replacing your existing instructions. Merge the AGDF fragment into your current `AGENTS.md` when you want Copilot to load both instruction sets. The generated `.github/copilot-instructions.md` keeps Copilot pointed at `AGENTS.md`, `.github/skills/` and `.agdf/control/` without duplicating the full AGDF rule model. Use `--force` only when you explicitly want to overwrite generated files.
 
 Use the `codex` target when AGDF should be available only inside one repository instead of being installed as a personal/global Codex plugin.
 
-After `npm create agdf@latest codex`, restart Codex in that repository, open `/plugins`, select the project marketplace and install `agdf`.
+After `npm create agdf@latest codex`, restart Codex in that repository, open `/plugins`, select `This repository` and install `agdf`.
 
 ## Control scaffold
 
@@ -43,17 +43,28 @@ Copy or promote templates into live `.agdf/control/` files only when the target
 
 The repository-facing AGDF sources are maintained in:
 
-- `plugin/meta/agdf-copilot-agents.md`
+- `plugin/meta/agdf-agent-router.md`
+- `plugin/meta/agdf-plugin.definition.json`
 - `plugin/skills/`
 - `plugin/meta/agdf-runtime-contract.md`
 - `plugin/control/`
 
+Skill routing is rendered from `skillSet.slug`, `useFor`, `boundary` and the target surface `skillPrefix`; it is not maintained as separate Codex, Claude Code and Copilot routing tables.
+
 The published package assets are generated from these repository sources only at pack/publish time. The package does not keep a second manually maintained template tree.
 
 ```bash
 npm run sync-package-assets
 ```
 
+To verify the rendered routing locally, run:
+
+```bash
+npm run test:routing
+```
+
+The routing test installs `both` into a temporary target repository and checks that plugin routing stays unprefixed while Copilot routing receives the configured `agdf-` prefix.
+
 ## Publishing
 
 The repository publishes this package from `create-agdf/` via the GitHub Actions workflow `.github/workflows/publish-create-agdf.yml`.

package/bin/create-agdf.js

@@ -8,9 +8,13 @@ import process from "node:process";
 const __dirname = dirname(fileURLToPath(import.meta.url));
 const packageRoot = resolve(__dirname, "..");
 const generatedRoot = join(packageRoot, "generated");
+const pluginDefinitionPath = join(generatedRoot, "plugins", "agdf", "meta", "agdf-plugin.definition.json");
+const pluginDefinition = JSON.parse(readFileSync(pluginDefinitionPath, "utf8"));
 const pluginInstallCommand = "claude plugin add arndtgold/ai-native-governance-delivery-framework";
 const allowedTargets = new Set(["codex", "copilot", "both"]);
 const agdfFragmentPath = "AGENTS.agdf.md";
+const codexSkillNames = pluginDefinition.skillSet.map((skill) => `${pluginDefinition.codex.skillPrefix}${skill.slug}`);
+const copilotSkillNames = pluginDefinition.skillSet.map((skill) => `${pluginDefinition.copilot.skillPrefix}${skill.slug}`);
 const codexPluginFiles = [
   join(".agents", "plugins", "marketplace.json"),
   join("plugins", "agdf", ".codex-plugin", "plugin.json"),
@@ -20,15 +24,14 @@ const codexPluginFiles = [
   join("plugins", "agdf", "control", "templates", "SOT_REGISTRY.md"),
   join("plugins", "agdf", "control", "templates", "CONTEXT_GRAPH.md"),
   join("plugins", "agdf", "control", "templates", "AGENT_QUALITY_CONTRACTS.json"),
+  join("plugins", "agdf", "hooks", "hooks.json"),
+  join("plugins", "agdf", "hooks", "session-start.sh"),
+  join("plugins", "agdf", "meta", "agdf-agent-router.md"),
+  join("plugins", "agdf", "meta", "agdf-constitution.md"),
+  join("plugins", "agdf", "meta", "agdf-plugin.definition.json"),
   join("plugins", "agdf", "meta", "agdf-runtime-contract.md"),
-  join("plugins", "agdf", "skills", "agdf-gate-check", "SKILL.md"),
-  join("plugins", "agdf", "skills", "agdf-brownfield-analysis", "SKILL.md"),
-  join("plugins", "agdf", "skills", "agdf-task-plan-review", "SKILL.md"),
-  join("plugins", "agdf", "skills", "agdf-clean-implementation-review", "SKILL.md"),
-  join("plugins", "agdf", "skills", "agdf-code-review", "SKILL.md"),
-  join("plugins", "agdf", "skills", "agdf-qa-gate", "SKILL.md"),
-  join("plugins", "agdf", "skills", "agdf-release-or", "SKILL.md"),
-  join("plugins", "agdf", "skills", "agdf-delivery-closeout", "SKILL.md"),
+  join("plugins", "agdf", "meta", "agdf-tenets.md"),
+  ...codexSkillNames.map((skillName) => join("plugins", "agdf", "skills", skillName, "SKILL.md")),
 ];
 const controlFiles = [
   join(".agdf", "control", "README.md"),
@@ -38,17 +41,14 @@ const controlFiles = [
   join(".agdf", "control", "templates", "CONTEXT_GRAPH.md"),
   join(".agdf", "control", "templates", "AGENT_QUALITY_CONTRACTS.json"),
 ];
+const copilotInstructionFiles = [
+  join(".github", "copilot-instructions.md"),
+  join(".github", "instructions", "agdf-governance.instructions.md"),
+];
 const copilotSkillFiles = [
   join(".github", "skills", "README.md"),
-  join(".github", "skills", "agdf-runtime-contract.md"),
-  join(".github", "skills", "agdf-gate-check", "SKILL.md"),
-  join(".github", "skills", "agdf-brownfield-analysis", "SKILL.md"),
-  join(".github", "skills", "agdf-task-plan-review", "SKILL.md"),
-  join(".github", "skills", "agdf-clean-implementation-review", "SKILL.md"),
-  join(".github", "skills", "agdf-code-review", "SKILL.md"),
-  join(".github", "skills", "agdf-qa-gate", "SKILL.md"),
-  join(".github", "skills", "agdf-release-or", "SKILL.md"),
-  join(".github", "skills", "agdf-delivery-closeout", "SKILL.md"),
+  join(".github", "skills", pluginDefinition.copilot.runtimeContractFileName),
+  ...copilotSkillNames.map((skillName) => join(".github", "skills", skillName, "SKILL.md")),
 ];
 
 function printUsage() {
@@ -171,6 +171,13 @@ function generatedFilesForTarget(target, targetDir, force) {
       });
     }
 
+    for (const instructionPath of copilotInstructionFiles) {
+      files.push({
+        path: instructionPath,
+        content: loadAsset(instructionPath),
+      });
+    }
+
     for (const skillPath of copilotSkillFiles) {
       files.push({
         path: skillPath,
@@ -197,7 +204,7 @@ function printNextSteps(target, destination, files, wroteAgentsFragment) {
     console.log(`- Existing AGENTS.md detected. Merge ${agdfFragmentPath} into your current AGENTS.md before using Copilot with AGDF.`);
   }
   if (target === "codex" || target === "both") {
-    console.log("- Restart Codex in this repository, open /plugins, select the project marketplace and install agdf.");
+    console.log("- Restart Codex in this repository, open /plugins, select This repository and install agdf.");
     console.log("- Start a new Codex thread in this repository and ask: Run an AGDF gate check for this request.");
   }
   if (target === "both") {

package/generated/.agents/plugins/marketplace.json

@@ -1,5 +1,8 @@
 {
-  "name": "agdf-project",
+  "name": "agdf-repo",
+  "interface": {
+    "displayName": "This repository"
+  },
   "plugins": [
     {
       "name": "agdf",

package/generated/.github/copilot-instructions.md

@@ -0,0 +1,10 @@
+# AGDF Copilot instructions
+
+AGDF is active in this repository.
+
+- Treat `AGENTS.md` as the primary repository instruction source.
+- Use `.github/skills/` for AGDF task workflows instead of inventing parallel process rules.
+- Use `.agdf/control/` for durable run state, backlog pointers, source-of-truth ownership, Context Graph knowledge and quality contracts.
+- Before non-trivial implementation or formal delivery work, determine whether the request is a Quick Task or Structured Delivery.
+- If approval, evidence, ownership or the next allowed action is unclear, run the AGDF gate-check workflow before creating later artefacts or code.
+- Do not treat chat history as the source of truth for gate state, approvals, evidence or delivery status.

package/generated/.github/instructions/agdf-governance.instructions.md

@@ -0,0 +1,13 @@
+---
+applyTo: "AGENTS.md,AGENTS.agdf.md,.agdf/**,.github/skills/**,.github/copilot-instructions.md,.github/instructions/**"
+---
+
+# AGDF governance artefacts
+
+These files are control artefacts, not general documentation.
+
+- Keep AGDF rules sourced from `AGENTS.md`, `.github/skills/` and `.github/skills/agdf-runtime-contract.md`.
+- Do not duplicate the full gate model, Quality Contract table or Context Graph relationship language in new files.
+- Keep generated AGDF files small, reviewable and linked to the owning source of truth.
+- Preserve the rule that missing approval, missing evidence or unclear ownership blocks later delivery steps.
+- If changing AGDF bootstrap behaviour, update the generated files, smoke test and affected setup documentation together.

package/generated/AGENTS.md

@@ -2,76 +2,66 @@
 
 ## Role
 You are an autonomous agent operating in an AGDF-governed delivery system.
-Your goal is not to produce answers. Your goal is to create trustworthy progress:
-reduce uncertainty, establish evidence, maintain artefacts, verify outcomes, and make the next step explicit.
 
-## Operating Modes
-| Mode | Use When | Required |
-|---|---|---|
-| Quick Task Mode | Questions, short reviews, local debugging, small fixes without new product semantics | Understand the local context, cite evidence, run relevant checks or name the gap, close briefly |
-| Structured Delivery Mode | New user capability, architecture/policy/persistence impact, release-critical work, formal artefacts, or explicit approvals | Respect gates, separate artefacts, make internal reviews visible, do not merge QA and OR |
+Use the plugin skills as workflow controls, not as documentation shortcuts.
+Your goal is trustworthy progress: reduce uncertainty, establish evidence, preserve artefacts, verify outcomes and make the next allowed step explicit.
 
-Quick Task Mode remains the default unless the request creates new product scope or asks for formal gate artefacts.
+## Surface Convention
+GitHub Copilot repository skills do not have a plugin namespace.
 
-## Operating Model
-Work in this order:
+Therefore generated Copilot skill names use the AGDF prefix:
 
-`Uncertainty Reduction -> Evidence -> Artefacts -> Verification -> Outcome`
+- `agdf-brownfield-analysis`
+- `agdf-clean-implementation-review`
+- `agdf-code-review`
+- `agdf-delivery-closeout`
+- `agdf-gate-check`
+- `agdf-qa-gate`
+- `agdf-release-or`
+- `agdf-task-plan-review`
 
-Evidence overrides assumptions and memory. If evidence is missing, state the uncertainty instead of smoothing it over.
+Do not remove that prefix in Copilot-facing repository skills.
+Codex and Claude Code plugin surfaces use the same canonical router with unprefixed skill names because their plugin namespace already carries `agdf`.
+## Mode Selection
+Use Quick Task Mode for questions, small reviews, local debugging and narrow fixes without new product semantics.
 
-## Gates
-- User gates: `UR -> PRD -> SD -> TP -> QA -> UAT`.
-- A user approval is valid only in this exact format: `Approval: <GateName>`.
-- Legacy German runs may be interpreted if they use `Freigabe: <GateName>`, but new artefacts must show `Approval: <GateName>`.
-- Implicit consent such as `ok`, `go`, `approved`, or similar wording is not approval.
-- Internal mandatory steps: `Brownfield Analysis -> CD+Tests -> CR -> OR`.
-- `CD+Tests` is not a done, QA, or release signal.
-- `agdf-qa-gate` is the only final QA decision for `pass | revise | block`.
-- `agdf-release-or` is mandatory at the end of relevant runs.
+Use Structured Delivery Mode for new capabilities, architecture, policy, persistence, release-critical work, formal artefacts or explicit approvals.
 
-## Brownfield Rules
-- Brownfield is the normal case.
-- Before non-trivial implementation in an existing system, inspect existing artefacts, ownership, behaviour, and tests.
-- Reuse-before-create and minimal clean slice take precedence over new structure.
-- No silent parallel structures, no second SoT, no unjustified fallbacks.
-- SoT/runtime/product-semantics drift must be named explicitly and can trigger an early product gate.
+Quick Task Mode must still cite evidence and close with a concrete result.
+Structured Delivery Mode must respect gates, reviews and closeout discipline.
 
 ## Skill Routing
 | Skill | Use For | Boundary |
 |---|---|---|
+| `agdf-brownfield-analysis` | before non-trivial implementation in existing systems | clarifies reuse, owners and risks |
+| `agdf-clean-implementation-review` | inspect workarounds, fallbacks, parallel structures or symptom fixes | not a TP or QA substitute |
+| `agdf-code-review` | mandatory CR step after code changes, focused on defects, regression and security findings | does not replace TP review, clean review or QA |
+| `agdf-delivery-closeout` | commit/PR-near handoff after QA/OR/UAT | never performs VCS actions automatically |
 | `agdf-gate-check` | unclear approval, Structured Delivery, later-gate artefact requested | does not create later artefacts |
-| `agdf-brownfield-analysis` | before non-trivial implementation in existing systems | clarifies reuse, owners, risks |
-| `agdf-task-plan-review` | after implementation and before QA, verify TP coverage | no final QA decision |
-| `agdf-clean-implementation-review` | inspect workarounds, fallbacks, parallel structures, or symptom fixes | not a TP or QA substitute |
-| `agdf-code-review` | mandatory CR step after code changes, focused on defects, regression, and security findings | does not replace TP review, clean review, or QA |
 | `agdf-qa-gate` | final QA decision | only instance for `pass | revise | block` |
 | `agdf-release-or` | auditable closeout for every relevant run | not a QA substitute |
-| `agdf-delivery-closeout` | commit/PR-near handoff after QA/OR/UAT | never performs VCS actions automatically |
+| `agdf-task-plan-review` | after implementation and before QA, verify TP coverage | no final QA decision |
 
-Select exactly one primary skill first. Add more only when they cover a distinct concrete risk dimension.
+Select exactly one primary skill first.
+Add more only when they cover a distinct concrete risk dimension.
 
-## Skill Contract
-For repeated output, gate, Quality Contract, and Context Graph rules, use:
-the repository-local `agdf-runtime-contract.md` artifact.
+## Runtime Contract
+For repeated output, gate, Quality Contract and Context Graph rules, use:
 
-Skills may include short runtime reminders, but must not carry a second complete rule or code table.
+`agdf-runtime-contract.md`
 
-## Durable Control State
-When this repository uses the AGDF control scaffold, keep live control files under `.agdf/control/`.
-Use the templates as starting points only:
+Skills may include short reminders, but they must not carry a second complete rule or code table.
 
-- `.agdf/control/templates/AGDF_RUN.md`
-- `.agdf/control/templates/MASTER_BACKLOG.md`
-- `.agdf/control/templates/SOT_REGISTRY.md`
-- `.agdf/control/templates/CONTEXT_GRAPH.md`
-- `.agdf/control/templates/AGENT_QUALITY_CONTRACTS.json`
+## Durable Control State
+When the target repository uses the AGDF control scaffold, keep live control files under `.agdf/control/`.
+Use templates as starting points only.
 
 Do not let chat history become the source of truth for gate state, approvals, evidence, backlog status or durable Brownfield knowledge.
 
 ## Closeout
-After relevant code, documentation, skill, or governance changes:
+After relevant code, documentation, skill or governance changes:
+
 - run relevant checks or state the test gap
-- never commit, push, or open a PR automatically
+- never commit, push or open a PR automatically
 - include exactly one `Next step:`
 - include exactly one `Quality outlook:`

package/generated/plugins/agdf/.codex-plugin/plugin.json

@@ -1,6 +1,6 @@
 {
   "name": "agdf",
-  "version": "0.1.4",
+  "version": "0.1.6",
   "description": "Codex-first workflow skills for gated, auditable AI-assisted software delivery.",
   "author": {
     "name": "AI-native Governance & Delivery Framework",

package/generated/plugins/agdf/hooks/hooks.json

@@ -0,0 +1,15 @@
+{
+    "hooks": {
+        "SessionStart": [
+            {
+                "hooks": [
+                    {
+                        "type":         "command",
+                        "command":      "bash -lc 'for hook in \"${CODEX_HOME:-$HOME/.codex}\"/plugins/cache/*/agdf/*/hooks/session-start.sh \"$PWD/plugins/agdf/hooks/session-start.sh\" \"$(dirname \"$0\")/session-start.sh\"; do [ -f \"$hook\" ] && exec bash \"$hook\"; done; exit 0'",
+                        "statusMessage": "Loading AGDF..."
+                    }
+                ]
+            }
+        ]
+    }
+}

package/generated/plugins/agdf/hooks/session-start.sh

@@ -0,0 +1,16 @@
+#!/usr/bin/env bash
+# AGDF Session Start Hook
+# Loads the AGDF plugin router and constitution into the agent session.
+
+SCRIPT_DIR="$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)"
+ROUTER="${SCRIPT_DIR}/../meta/agdf-agent-router.md"
+CONSTITUTION="${SCRIPT_DIR}/../meta/agdf-constitution.md"
+
+if [ -f "$ROUTER" ]; then
+    cat "$ROUTER"
+    printf "\n\n"
+fi
+
+if [ -f "$CONSTITUTION" ]; then
+    cat "$CONSTITUTION"
+fi

package/generated/plugins/agdf/meta/agdf-agent-router.md

@@ -0,0 +1,68 @@
+# AGDF Agent Router
+
+## Role
+You are operating inside the AGDF plugin namespace.
+
+Use the plugin skills as workflow controls, not as documentation shortcuts.
+Your goal is trustworthy progress: reduce uncertainty, establish evidence, preserve artefacts, verify outcomes and make the next allowed step explicit.
+
+## Surface Convention
+Codex and Claude Code already provide the `agdf` plugin namespace.
+
+Therefore plugin skill names are intentionally unprefixed:
+
+- `gate-check`
+- `brownfield-analysis`
+- `task-plan-review`
+- `clean-implementation-review`
+- `code-review`
+- `qa-gate`
+- `release-or`
+- `delivery-closeout`
+
+Do not duplicate the plugin namespace in Codex or Claude Code plugin skill names.
+That `agdf-` prefix is reserved for GitHub Copilot repository skills, where no plugin namespace exists.
+
+## Mode Selection
+Use Quick Task Mode for questions, small reviews, local debugging and narrow fixes without new product semantics.
+
+Use Structured Delivery Mode for new capabilities, architecture, policy, persistence, release-critical work, formal artefacts or explicit approvals.
+
+Quick Task Mode must still cite evidence and close with a concrete result.
+Structured Delivery Mode must respect gates, reviews and closeout discipline.
+
+## Skill Routing
+| Skill | Use For | Boundary |
+|---|---|---|
+| `brownfield-analysis` | before non-trivial implementation in existing systems | clarifies reuse, owners and risks |
+| `clean-implementation-review` | inspect workarounds, fallbacks, parallel structures or symptom fixes | not a TP or QA substitute |
+| `code-review` | mandatory CR step after code changes, focused on defects, regression and security findings | does not replace TP review, clean review or QA |
+| `delivery-closeout` | commit/PR-near handoff after QA/OR/UAT | never performs VCS actions automatically |
+| `gate-check` | unclear approval, Structured Delivery, later-gate artefact requested | does not create later artefacts |
+| `qa-gate` | final QA decision | only instance for `pass | revise | block` |
+| `release-or` | auditable closeout for every relevant run | not a QA substitute |
+| `task-plan-review` | after implementation and before QA, verify TP coverage | no final QA decision |
+
+Select exactly one primary skill first.
+Add more only when they cover a distinct concrete risk dimension.
+
+## Runtime Contract
+For repeated output, gate, Quality Contract and Context Graph rules, use:
+
+`agdf-runtime-contract.md`
+
+Skills may include short reminders, but they must not carry a second complete rule or code table.
+
+## Durable Control State
+When the target repository uses the AGDF control scaffold, keep live control files under `.agdf/control/`.
+Use templates as starting points only.
+
+Do not let chat history become the source of truth for gate state, approvals, evidence, backlog status or durable Brownfield knowledge.
+
+## Closeout
+After relevant code, documentation, skill or governance changes:
+
+- run relevant checks or state the test gap
+- never commit, push or open a PR automatically
+- include exactly one `Next step:`
+- include exactly one `Quality outlook:`

package/generated/plugins/agdf/meta/agdf-plugin.definition.json

@@ -0,0 +1,90 @@
+{
+  "schemaVersion": 1,
+  "id": "agdf",
+  "version": "0.1.6",
+  "displayName": "AI Governance & Delivery Framework",
+  "developerName": "AI-native Governance & Delivery Framework",
+  "description": "Codex-first workflow skills for gated, auditable AI-assisted software delivery.",
+  "claudeDescription": "Codex-first workflow skills and control templates for gated, auditable AI-assisted software delivery.",
+  "shortDescription": "Codex-first workflow skills for gated, auditable AI-assisted delivery.",
+  "longDescription": "AI Governance & Delivery Framework (AGDF) packages reusable Codex-first skills and control templates for gate checks, Brownfield analysis, task-plan review, solution-integrity review, QA decisions, durable run state and auditable delivery closeout.",
+  "homepage": "https://agdf.iself.eu",
+  "repository": "https://github.com/arndtgold/ai-native-governance-delivery-framework",
+  "license": "Apache-2.0",
+  "keywords": ["agentic", "governance", "delivery", "ai-native", "brownfield"],
+  "category": "Productivity",
+  "brandColor": "#14B8A6",
+  "author": {
+    "name": "AI-native Governance & Delivery Framework",
+    "url": "https://agdf.iself.eu"
+  },
+  "codex": {
+    "skills": "./skills/",
+    "skillPrefix": "",
+    "agentRouter": "meta/agdf-agent-router.md",
+    "capabilities": ["Read", "Write"],
+    "defaultPrompt": [
+      "Run an AGDF gate check for this request.",
+      "Create an AGDF control scaffold for this repository.",
+      "Use AGDF Brownfield analysis before implementation.",
+      "Close this run with an AGDF orchestration report."
+    ],
+    "hooks": "hooks/hooks.json"
+  },
+  "claude": {
+    "skillPrefix": "",
+    "agentRouter": "meta/agdf-agent-router.md"
+  },
+  "copilot": {
+    "skillPrefix": "agdf-",
+    "runtimeContractFileName": "agdf-runtime-contract.md"
+  },
+  "skillSet": [
+    {
+      "slug": "brownfield-analysis",
+      "useFor": "before non-trivial implementation in existing systems",
+      "boundary": "clarifies reuse, owners and risks"
+    },
+    {
+      "slug": "clean-implementation-review",
+      "useFor": "inspect workarounds, fallbacks, parallel structures or symptom fixes",
+      "boundary": "not a TP or QA substitute"
+    },
+    {
+      "slug": "code-review",
+      "useFor": "mandatory CR step after code changes, focused on defects, regression and security findings",
+      "boundary": "does not replace TP review, clean review or QA"
+    },
+    {
+      "slug": "delivery-closeout",
+      "useFor": "commit/PR-near handoff after QA/OR/UAT",
+      "boundary": "never performs VCS actions automatically"
+    },
+    {
+      "slug": "gate-check",
+      "useFor": "unclear approval, Structured Delivery, later-gate artefact requested",
+      "boundary": "does not create later artefacts"
+    },
+    {
+      "slug": "qa-gate",
+      "useFor": "final QA decision",
+      "boundary": "only instance for `pass | revise | block`"
+    },
+    {
+      "slug": "release-or",
+      "useFor": "auditable closeout for every relevant run",
+      "boundary": "not a QA substitute"
+    },
+    {
+      "slug": "task-plan-review",
+      "useFor": "after implementation and before QA, verify TP coverage",
+      "boundary": "no final QA decision"
+    }
+  ],
+  "marketplaces": {
+    "repository": {
+      "name": "agdf-repo",
+      "displayName": "This repository"
+    }
+  }
+}

package/generated/plugins/agdf/meta/agdf-runtime-contract.md

@@ -22,9 +22,9 @@ Structured Delivery must not bypass missing approvals.
 - Implicit consent is not approval.
 - The earliest blocking gate wins.
 - `CD+Tests` is implementation and test status only, not a delivery signal.
-- `agdf-code-review` standardizes the mandatory `CR` step, but does not replace QA.
-- `agdf-qa-gate` decides final `pass | revise | block`.
-- `agdf-release-or` reports the run, but does not replace QA.
+- `code-review` standardizes the mandatory `CR` step, but does not replace QA.
+- `qa-gate` decides final `pass | revise | block`.
+- `release-or` reports the run, but does not replace QA.
 
 ## Quality Contract Output
 

package/generated/plugins/agdf/skills/{agdf-brownfield-analysis → brownfield-analysis}/SKILL.md

@@ -1,5 +1,5 @@
 ---
-name: agdf-brownfield-analysis
+name: brownfield-analysis
 description: Use this skill before implementation in an existing codebase, especially for feature extensions, bug fixes, refactorings, or changes to existing modules. It analyzes existing artefacts, current coverage, reuse strategy, risks, and the minimal clean implementation path. Use it before CD+Tests.
 ---
 

package/generated/plugins/agdf/skills/{agdf-brownfield-analysis → brownfield-analysis}/help.md

@@ -1,10 +1,10 @@
 ## NAME
 
-`agdf-brownfield-analysis` - brownfield analysis
+`brownfield-analysis` - brownfield analysis
 
 ## SYNOPSIS
 
-`/agdf-brownfield-analysis` [`--help`|`-h`]
+`/brownfield-analysis` [`--help`|`-h`]
 
 ## DESCRIPTION
 
@@ -15,7 +15,7 @@ Ensures implementation in an existing system is Brownfield-oriented rather than
 Trigger the skill:
 
 ```text
-> /agdf-brownfield-analysis
+> /brownfield-analysis
 ```
 
 ## SEE ALSO

package/generated/plugins/agdf/skills/{agdf-clean-implementation-review → clean-implementation-review}/SKILL.md

@@ -1,5 +1,5 @@
 ---
-name: agdf-clean-implementation-review
+name: clean-implementation-review
 description: Use this skill to determine whether an implementation is a clean primary solution or whether fallbacks, workarounds, guards, defaults, shims, or parallel structures have made it unnecessarily complex. Use it after code changes, before QA, or whenever symptom treatment is suspected.
 ---
 
@@ -49,7 +49,7 @@ Use what is available:
 - Code Deliverables
 - changed files
 - tests and test results
-- `agdf-code-review` or Code Review Report
+- `code-review` or Code Review Report
 - QA Report
 - Brownfield Analysis findings
 - PRD or SD architecture notes

package/generated/plugins/agdf/skills/{agdf-clean-implementation-review → clean-implementation-review}/help.md

@@ -1,10 +1,10 @@
 ## NAME
 
-`agdf-clean-implementation-review` - clean implementation review
+`clean-implementation-review` - clean implementation review
 
 ## SYNOPSIS
 
-`/agdf-clean-implementation-review` [`--help`|`-h`]
+`/clean-implementation-review` [`--help`|`-h`]
 
 ## DESCRIPTION
 
@@ -15,7 +15,7 @@ Evaluates solution integrity: whether the implementation is a clean primary solu
 Trigger the skill:
 
 ```text
-> /agdf-clean-implementation-review
+> /clean-implementation-review
 ```
 
 ## SEE ALSO

package/generated/plugins/agdf/skills/{agdf-code-review → code-review}/SKILL.md

@@ -1,5 +1,5 @@
 ---
-name: agdf-code-review
+name: code-review
 description: Use this skill after code changes and before QA to produce the mandatory Code Review Report for correctness, regression, security, and maintainability findings in the actual diff. It standardizes the CR step without replacing TP review, clean review, or QA.
 ---
 

package/generated/plugins/agdf/skills/{agdf-code-review → code-review}/help.md

@@ -1,10 +1,10 @@
 ## NAME
 
-`agdf-code-review` - code review
+`code-review` - code review
 
 ## SYNOPSIS
 
-`/agdf-code-review` [`--help`|`-h`]
+`/code-review` [`--help`|`-h`]
 
 ## DESCRIPTION
 
@@ -15,7 +15,7 @@ Produces the mandatory Code Review Report for changed code and focuses on correc
 Trigger the skill:
 
 ```text
-> /agdf-code-review
+> /code-review
 ```
 
 ## SEE ALSO

package/generated/plugins/agdf/skills/{agdf-delivery-closeout → delivery-closeout}/SKILL.md

@@ -1,5 +1,5 @@
 ---
-name: agdf-delivery-closeout
+name: delivery-closeout
 description: Use this skill for the final delivery handoff after QA, OR, or UAT when a run should move toward commit, push, or PR. It standardizes commit-ready summaries, UAT-gated commit offers, and the next delivery step without replacing QA or OR decisions.
 ---
 
@@ -17,7 +17,7 @@ It answers:
 - whether evidence-based technical follow-up remains useful
 - whether Context Graph follow-up from OR/QA remains open
 
-This skill does not replace `agdf-qa-gate`, `agdf-release-or`, user approvals, or gate decisions.
+This skill does not replace `qa-gate`, `release-or`, user approvals, or gate decisions.
 
 ## Runtime Contract
 Use `../../meta/agdf-runtime-contract.md` for closeout discipline, gate terms, Context Graph fields, and non-duplication rules.
@@ -39,7 +39,7 @@ Use `../../meta/agdf-runtime-contract.md` for closeout discipline, gate terms, C
 - after `Approval: UAT`
 - when the user asks for commit, push, or PR handoff
 
-Do not use as a substitute for `agdf-qa-gate`, `agdf-release-or`, or `agdf-gate-check`.
+Do not use as a substitute for `qa-gate`, `release-or`, or `gate-check`.
 
 ## Inputs
 Use what is available:

package/generated/plugins/agdf/skills/{agdf-delivery-closeout → delivery-closeout}/help.md

@@ -1,10 +1,10 @@
 ## NAME
 
-`agdf-delivery-closeout` - delivery closeout
+`delivery-closeout` - delivery closeout
 
 ## SYNOPSIS
 
-`/agdf-delivery-closeout` [`--help`|`-h`]
+`/delivery-closeout` [`--help`|`-h`]
 
 ## DESCRIPTION
 
@@ -15,7 +15,7 @@ Standardizes the operational delivery closeout for a run with a commit-ready Git
 Trigger the skill:
 
 ```text
-> /agdf-delivery-closeout
+> /delivery-closeout
 ```
 
 ## SEE ALSO

package/generated/plugins/agdf/skills/{agdf-gate-check → gate-check}/SKILL.md

@@ -1,5 +1,5 @@
 ---
-name: agdf-gate-check
+name: gate-check
 description: Use this skill when the active gate is unclear, when a later-gate artefact is requested, when an exact approval may be missing, or when the next permissible step must be determined. Use it before creating formal artefacts in Structured Delivery and whenever implicit consent might be mistaken for approval.
 ---
 

package/generated/plugins/agdf/skills/{agdf-gate-check → gate-check}/help.md

@@ -1,10 +1,10 @@
 ## NAME
 
-`agdf-gate-check` - gate check
+`gate-check` - gate check
 
 ## SYNOPSIS
 
-`/agdf-gate-check` [`--help`|`-h`]
+`/gate-check` [`--help`|`-h`]
 
 ## DESCRIPTION
 
@@ -15,7 +15,7 @@ Determines the earliest blocking user approval gate and derives which artefacts
 Trigger the skill:
 
 ```text
-> /agdf-gate-check
+> /gate-check
 ```
 
 ## SEE ALSO

package/generated/plugins/agdf/skills/{agdf-qa-gate → qa-gate}/SKILL.md

@@ -1,5 +1,5 @@
 ---
-name: agdf-qa-gate
+name: qa-gate
 description: Use this skill before any QA decision to determine whether implementation can be classified as pass, revise, or block based on TP coverage, Brownfield fit, solution integrity, evidence, and open blockers. Use it after CD+Tests, after reviews, and before UAT or release decisions.
 ---
 
@@ -40,9 +40,9 @@ QA-specific `decision` is exactly `pass | revise | block`.
 
 ## When To Use
 - after `CD+Tests`
-- after `agdf-code-review`
-- after `agdf-task-plan-review`
-- after `agdf-clean-implementation-review`
+- after `code-review`
+- after `task-plan-review`
+- after `clean-implementation-review`
 - before UAT
 - before any claim that implementation is done, releasable, or QA-ready
 - when evidence from Brownfield, TP, or clean-review skills exists
@@ -58,7 +58,7 @@ Use what is available:
 - approved TP and TP Review
 - Brownfield Analysis
 - Clean Implementation Review
-- `agdf-code-review` or Code Review Report
+- `code-review` or Code Review Report
 - test/build results
 - documentation impact review
 - runtime or UI evidence

package/generated/plugins/agdf/skills/{agdf-qa-gate → qa-gate}/help.md

@@ -1,10 +1,10 @@
 ## NAME
 
-`agdf-qa-gate` - QA gate
+`qa-gate` - QA gate
 
 ## SYNOPSIS
 
-`/agdf-qa-gate` [`--help`|`-h`]
+`/qa-gate` [`--help`|`-h`]
 
 ## DESCRIPTION
 
@@ -15,7 +15,7 @@ Makes the formal QA gate decision (`pass | revise | block`) based on TP coverage
 Trigger the skill:
 
 ```text
-> /agdf-qa-gate
+> /qa-gate
 ```
 
 ## SEE ALSO

package/generated/plugins/agdf/skills/{agdf-release-or → release-or}/SKILL.md

@@ -1,5 +1,5 @@
 ---
-name: agdf-release-or
+name: release-or
 description: Use this skill at the end of every relevant run to produce a compact, auditable Orchestration Report. It summarizes gate status, delivered and intentionally not delivered work, TP coverage, Brownfield fit, solution integrity, open risks, and the next permissible step.
 ---
 
@@ -46,7 +46,7 @@ OR-specific output must make gate status, delivered and intentionally not delive
 - after artefact creation
 - when a gate blocks
 - after `CD+Tests`
-- after `agdf-code-review`
+- after `code-review`
 - after QA
 - after UAT
 - whenever a compact audit closeout is needed
@@ -59,10 +59,10 @@ Use what is available:
 - artefacts created in this run
 - intentionally not delivered content
 - Task Plan
-- `agdf-task-plan-review`
-- `agdf-brownfield-analysis`
-- `agdf-clean-implementation-review`
-- `agdf-code-review`
+- `task-plan-review`
+- `brownfield-analysis`
+- `clean-implementation-review`
+- `code-review`
 - QA Report
 - UAT Report
 - documentation impact review
@@ -117,7 +117,7 @@ Migration/Rollout note:
 ## Forbidden
 This skill must not:
 
-- decide QA in place of `agdf-qa-gate`
+- decide QA in place of `qa-gate`
 - call `CD+Tests` complete, QA-ready, or release-ready
 - hide missing approvals
 - provide later-gate content while an earlier gate blocks

package/generated/plugins/agdf/skills/{agdf-release-or → release-or}/help.md

@@ -1,10 +1,10 @@
 ## NAME
 
-`agdf-release-or` - release OR
+`release-or` - release OR
 
 ## SYNOPSIS
 
-`/agdf-release-or` [`--help`|`-h`]
+`/release-or` [`--help`|`-h`]
 
 ## DESCRIPTION
 
@@ -15,7 +15,7 @@ Creates the mandatory Orchestration Report (OR) for a run. Summarizes gate statu
 Trigger the skill:
 
 ```text
-> /agdf-release-or
+> /release-or
 ```
 
 ## SEE ALSO

package/generated/plugins/agdf/skills/{agdf-task-plan-review → task-plan-review}/SKILL.md

@@ -1,5 +1,5 @@
 ---
-name: agdf-task-plan-review
+name: task-plan-review
 description: Use this skill after code changes and before QA to verify whether the approved Task Plan was actually fulfilled. It checks each task_id against implementation, acceptance criteria, tests, visible evidence, and deviations, and provides TP coverage for QA.
 ---
 
@@ -14,7 +14,7 @@ For each relevant task, this skill determines:
 - which acceptance criteria are done, partial, missing, or not verifiable
 - which files, tests, runtime evidence, or UI evidence support the finding
 - evidence strength
-- which gaps must be handed to `agdf-qa-gate`
+- which gaps must be handed to `qa-gate`
 
 This skill provides TP coverage. It is not the final QA decision.
 

package/generated/plugins/agdf/skills/{agdf-task-plan-review → task-plan-review}/help.md

@@ -1,10 +1,10 @@
 ## NAME
 
-`agdf-task-plan-review` - task plan review
+`task-plan-review` - task plan review
 
 ## SYNOPSIS
 
-`/agdf-task-plan-review` [`--help`|`-h`]
+`/task-plan-review` [`--help`|`-h`]
 
 ## DESCRIPTION
 
@@ -15,7 +15,7 @@ Checks after code changes and before QA whether the approved Task Plan tasks wer
 Trigger the skill:
 
 ```text
-> /agdf-task-plan-review
+> /task-plan-review
 ```
 
 ## SEE ALSO

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "create-agdf",
-  "version": "0.1.4",
+  "version": "0.1.6",
   "description": "Bootstrap AGDF repository-local Codex plugin marketplaces, Copilot instructions, skills and control templates.",
   "type": "module",
   "files": [
@@ -13,7 +13,8 @@
   },
   "scripts": {
     "sync-package-assets": "node ./scripts/sync-package-assets.js",
-    "smoke-test": "npm run sync-package-assets && node ./scripts/smoke-test.js",
+    "test:routing": "npm run sync-package-assets && node ./scripts/test-routing.js",
+    "smoke-test": "npm run sync-package-assets && node ./scripts/smoke-test.js && node ./scripts/test-routing.js",
     "prepack": "npm run sync-package-assets"
   },
   "keywords": [

package/generated/plugins/agdf/meta/agdf-copilot-agents.md

@@ -1,77 +0,0 @@
-# AGENTS.md
-
-## Role
-You are an autonomous agent operating in an AGDF-governed delivery system.
-Your goal is not to produce answers. Your goal is to create trustworthy progress:
-reduce uncertainty, establish evidence, maintain artefacts, verify outcomes, and make the next step explicit.
-
-## Operating Modes
-| Mode | Use When | Required |
-|---|---|---|
-| Quick Task Mode | Questions, short reviews, local debugging, small fixes without new product semantics | Understand the local context, cite evidence, run relevant checks or name the gap, close briefly |
-| Structured Delivery Mode | New user capability, architecture/policy/persistence impact, release-critical work, formal artefacts, or explicit approvals | Respect gates, separate artefacts, make internal reviews visible, do not merge QA and OR |
-
-Quick Task Mode remains the default unless the request creates new product scope or asks for formal gate artefacts.
-
-## Operating Model
-Work in this order:
-
-`Uncertainty Reduction -> Evidence -> Artefacts -> Verification -> Outcome`
-
-Evidence overrides assumptions and memory. If evidence is missing, state the uncertainty instead of smoothing it over.
-
-## Gates
-- User gates: `UR -> PRD -> SD -> TP -> QA -> UAT`.
-- A user approval is valid only in this exact format: `Approval: <GateName>`.
-- Legacy German runs may be interpreted if they use `Freigabe: <GateName>`, but new artefacts must show `Approval: <GateName>`.
-- Implicit consent such as `ok`, `go`, `approved`, or similar wording is not approval.
-- Internal mandatory steps: `Brownfield Analysis -> CD+Tests -> CR -> OR`.
-- `CD+Tests` is not a done, QA, or release signal.
-- `agdf-qa-gate` is the only final QA decision for `pass | revise | block`.
-- `agdf-release-or` is mandatory at the end of relevant runs.
-
-## Brownfield Rules
-- Brownfield is the normal case.
-- Before non-trivial implementation in an existing system, inspect existing artefacts, ownership, behaviour, and tests.
-- Reuse-before-create and minimal clean slice take precedence over new structure.
-- No silent parallel structures, no second SoT, no unjustified fallbacks.
-- SoT/runtime/product-semantics drift must be named explicitly and can trigger an early product gate.
-
-## Skill Routing
-| Skill | Use For | Boundary |
-|---|---|---|
-| `agdf-gate-check` | unclear approval, Structured Delivery, later-gate artefact requested | does not create later artefacts |
-| `agdf-brownfield-analysis` | before non-trivial implementation in existing systems | clarifies reuse, owners, risks |
-| `agdf-task-plan-review` | after implementation and before QA, verify TP coverage | no final QA decision |
-| `agdf-clean-implementation-review` | inspect workarounds, fallbacks, parallel structures, or symptom fixes | not a TP or QA substitute |
-| `agdf-code-review` | mandatory CR step after code changes, focused on defects, regression, and security findings | does not replace TP review, clean review, or QA |
-| `agdf-qa-gate` | final QA decision | only instance for `pass | revise | block` |
-| `agdf-release-or` | auditable closeout for every relevant run | not a QA substitute |
-| `agdf-delivery-closeout` | commit/PR-near handoff after QA/OR/UAT | never performs VCS actions automatically |
-
-Select exactly one primary skill first. Add more only when they cover a distinct concrete risk dimension.
-
-## Skill Contract
-For repeated output, gate, Quality Contract, and Context Graph rules, use:
-the repository-local `agdf-runtime-contract.md` artifact.
-
-Skills may include short runtime reminders, but must not carry a second complete rule or code table.
-
-## Durable Control State
-When this repository uses the AGDF control scaffold, keep live control files under `.agdf/control/`.
-Use the templates as starting points only:
-
-- `.agdf/control/templates/AGDF_RUN.md`
-- `.agdf/control/templates/MASTER_BACKLOG.md`
-- `.agdf/control/templates/SOT_REGISTRY.md`
-- `.agdf/control/templates/CONTEXT_GRAPH.md`
-- `.agdf/control/templates/AGENT_QUALITY_CONTRACTS.json`
-
-Do not let chat history become the source of truth for gate state, approvals, evidence, backlog status or durable Brownfield knowledge.
-
-## Closeout
-After relevant code, documentation, skill, or governance changes:
-- run relevant checks or state the test gap
-- never commit, push, or open a PR automatically
-- include exactly one `Next step:`
-- include exactly one `Quality outlook:`