create-agdf 0.1.1 → 0.1.3

package/README.md

@@ -1,6 +1,6 @@
 # create-agdf
 
-Bootstrap AGDF for one repository.
+Bootstrap AGDF repository instructions for one repository.
 
 ## Usage
 
@@ -16,15 +16,35 @@ Optional flags:
 
 ## Targets and existing AGENTS.md
 
-- `copilot` writes `AGENTS.md` and visible repository skills under `.github/skills/`
-- `both` writes the same Copilot-facing files and reminds you to install the Claude plugin separately
+- `copilot` writes `AGENTS.md`, visible repository skills under `.github/skills/`, and AGDF control templates under `.agdf/control/`
+- `both` writes the same Copilot-facing files and reminds you to install the Claude Code plugin separately
 
 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.
 
+Codex is supported through the AGDF Codex plugin in `plugin/.codex-plugin/plugin.json`, not through `create-agdf` package output.
+
+## Control scaffold
+
+The generated `.agdf/control/templates/` files are starting points for durable AGDF state:
+
+- `AGDF_RUN.md` for the current run dashboard
+- `MASTER_BACKLOG.md` for active delivery pointers
+- `SOT_REGISTRY.md` for one source of truth per domain
+- `CONTEXT_GRAPH.md` for durable Brownfield findings, decisions, risks, evidence and exit criteria
+- `AGENT_QUALITY_CONTRACTS.json` for reusable block, revise and warning conditions
+
+Copy or promote templates into live `.agdf/control/` files only when the target repository is ready to own them as source-of-truth artefacts.
+
 ## Single source of truth
 
-The AGDF skill contracts are maintained in `plugin/skills/`.
-The published package assets are generated from the repository sources only at pack/publish time. The package does not keep a second manually maintained template tree.
+The repository-facing AGDF sources are maintained in:
+
+- `plugin/meta/agdf-copilot-agents.md`
+- `plugin/skills/`
+- `plugin/meta/agdf-runtime-contract.md`
+- `plugin/control/`
+
+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

package/bin/create-agdf.js

@@ -11,6 +11,14 @@ const generatedRoot = join(packageRoot, "generated");
 const pluginInstallCommand = "claude plugin add arndtgold/ai-native-governance-delivery-framework";
 const allowedTargets = new Set(["copilot", "both"]);
 const agdfFragmentPath = "AGENTS.agdf.md";
+const controlFiles = [
+  join(".agdf", "control", "README.md"),
+  join(".agdf", "control", "templates", "AGDF_RUN.md"),
+  join(".agdf", "control", "templates", "MASTER_BACKLOG.md"),
+  join(".agdf", "control", "templates", "SOT_REGISTRY.md"),
+  join(".agdf", "control", "templates", "CONTEXT_GRAPH.md"),
+  join(".agdf", "control", "templates", "AGENT_QUALITY_CONTRACTS.json"),
+];
 const copilotSkillFiles = [
   join(".github", "skills", "README.md"),
   join(".github", "skills", "agdf-runtime-contract.md"),
@@ -18,6 +26,7 @@ const copilotSkillFiles = [
   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"),
@@ -126,6 +135,13 @@ function generatedFilesForTarget(target, targetDir, force) {
   ];
 
   if (target === "copilot" || target === "both") {
+    for (const controlPath of controlFiles) {
+      files.push({
+        path: controlPath,
+        content: loadAsset(controlPath),
+      });
+    }
+
     for (const skillPath of copilotSkillFiles) {
       files.push({
         path: skillPath,
@@ -156,6 +172,7 @@ function printNextSteps(target, destination, files, wroteAgentsFragment) {
   }
   if (target === "copilot" || target === "both") {
     console.log("- In GitHub Copilot CLI, run /instructions after the AGENTS.md step is complete to confirm that AGDF instructions and the repository skills are visible.");
+    console.log("- Copy the templates under .agdf/control/templates into live control files when the repository needs a durable run state, backlog pointer, SoT registry or context graph.");
   }
   console.log("- Commit the generated files so the repository becomes the source of truth.");
 }

package/generated/.agdf/control/README.md

@@ -0,0 +1,39 @@
+# AGDF Control Scaffold
+
+AGDF is primarily a control system for AI-assisted delivery. The skills guide the agent during a run; these files make the run state durable in a repository.
+
+Use this scaffold when a target repository should keep AGDF state outside chat history and tool memory.
+
+## Files
+
+| File | Purpose |
+|---|---|
+| `templates/AGDF_RUN.md` | Current run state: mode, gate, approvals, evidence, risks, next allowed action |
+| `templates/MASTER_BACKLOG.md` | Living backlog pointer: active initiatives and current UR/PRD/SD/TP artefacts |
+| `templates/SOT_REGISTRY.md` | Source-of-truth registry: one primary owner per domain |
+| `templates/CONTEXT_GRAPH.md` | Project memory: durable decisions, Brownfield findings, risks, evidence and exit criteria |
+| `templates/AGENT_QUALITY_CONTRACTS.json` | Machine-readable warning, revise and block contracts for review and QA |
+
+## Recommended Target Layout
+
+```text
+.agdf/
+  control/
+    AGDF_RUN.md
+    MASTER_BACKLOG.md
+    SOT_REGISTRY.md
+    CONTEXT_GRAPH.md
+    AGENT_QUALITY_CONTRACTS.json
+```
+
+Keep these files small and reviewable. They are control artefacts, not a second documentation site.
+
+## Operating Rules
+
+- `AGDF_RUN.md` is the current run dashboard.
+- `MASTER_BACKLOG.md` points to active delivery work; detailed artefacts live beside the work item.
+- `SOT_REGISTRY.md` decides which document owns which domain.
+- `CONTEXT_GRAPH.md` records durable project knowledge only when it has evidence and an exit criterion.
+- `AGENT_QUALITY_CONTRACTS.json` names reusable block, revise and warning conditions.
+
+Do not duplicate full product documentation in this scaffold. Link to the authoritative artefact instead.

package/generated/.agdf/control/templates/AGDF_RUN.md

@@ -0,0 +1,84 @@
+# AGDF Run State
+
+## Run Meta
+
+- run_id:
+- started_at:
+- mode: `quick_task | structured_delivery`
+- current_gate: `none | UR | PRD | SD | TP | CD+Tests | CR | QA | UAT | OR`
+- decision: `pass | revise | block | in_progress`
+- owner:
+
+## Objective
+
+What outcome is this run trying to make trustworthy?
+
+## Current Control State
+
+| Question | Answer |
+|---|---|
+| What is known? |  |
+| What is approved? |  |
+| What is missing? |  |
+| What is the next allowed action? |  |
+| What is explicitly forbidden right now? |  |
+
+## Approvals
+
+Valid approval format for new runs: `Approval: <GateName>`.
+
+| Gate | Status | Evidence |
+|---|---|---|
+| UR | `missing | approved | not_applicable` |  |
+| PRD | `missing | approved | not_applicable` |  |
+| SD | `missing | approved | not_applicable` |  |
+| TP | `missing | approved | not_applicable` |  |
+| QA | `missing | approved | not_applicable` |  |
+| UAT | `missing | approved | not_applicable` |  |
+
+## Artefacts
+
+| Type | Path | Status | Notes |
+|---|---|---|---|
+| UR |  | `draft | approved | superseded | not_applicable` |  |
+| PRD |  | `draft | approved | superseded | not_applicable` |  |
+| SD |  | `draft | approved | superseded | not_applicable` |  |
+| TP |  | `draft | approved | superseded | not_applicable` |  |
+| Review |  | `missing | done | not_applicable` |  |
+| QA |  | `missing | pass | revise | block | not_applicable` |  |
+| OR |  | `missing | done | not_applicable` |  |
+
+## Evidence
+
+| Evidence | Source | Covers | Strength |
+|---|---|---|---|
+|  |  |  | `direct | indirect | weak` |
+
+## Missing Evidence
+
+| Missing evidence | Impact | Required next step |
+|---|---|---|
+|  | `warn | revise | block` |  |
+
+## Risks
+
+| Risk | Impact | Mitigation or owner |
+|---|---|---|
+|  | `warn | revise | block` |  |
+
+## Context Graph Impact
+
+- context_graph_impact: `none | link_only | update_existing_node | new_node_required | sot_drift`
+- context_graph_refs:
+- context_graph_required_action: `none | link | update | create | resolve_drift`
+- context_graph_gate_effect: `none | warning | revise | block`
+- context_graph_evidence:
+
+## Closeout
+
+- delivered:
+- not_delivered:
+- verification_performed:
+- unverified:
+- next_allowed_action:
+- quality_outlook:

package/generated/.agdf/control/templates/AGENT_QUALITY_CONTRACTS.json

@@ -0,0 +1,78 @@
+{
+  "schema_version": "1",
+  "updated_at": "",
+  "contracts": [
+    {
+      "code": "AGDF_GATE_BYPASS",
+      "category": "agent_process",
+      "impact": "block",
+      "title": "Gate bypass",
+      "description": "A later artefact or implementation was produced without the required exact approval.",
+      "applies_to_modes": ["structured_delivery"],
+      "gate_effect": ["prd", "sd", "tp", "qa", "uat"],
+      "required_evidence": ["approval_log", "artifact_status"],
+      "evaluation": "review",
+      "owner": "governance"
+    },
+    {
+      "code": "AGDF_QA_WITHOUT_TASK_PLAN_REVIEW",
+      "category": "agent_process",
+      "impact": "block",
+      "title": "QA without task-plan review",
+      "description": "QA is evaluated for Structured Delivery without prior task-plan coverage evidence.",
+      "applies_to_modes": ["structured_delivery"],
+      "gate_effect": ["qa"],
+      "required_evidence": ["task_plan_review"],
+      "evaluation": "review",
+      "owner": "governance"
+    },
+    {
+      "code": "AGDF_PARALLEL_SOT",
+      "category": "architecture_integrity",
+      "impact": "block",
+      "title": "Parallel source of truth",
+      "description": "A second source of truth was introduced for product intent, runtime behavior, visible state, policy or persistent domain data.",
+      "applies_to_modes": ["structured_delivery", "quick_task"],
+      "gate_effect": ["prd", "sd", "tp", "qa"],
+      "required_evidence": ["brownfield_analysis", "source_of_truth_reference"],
+      "evaluation": "review",
+      "owner": "governance"
+    },
+    {
+      "code": "AGDF_DOC_IMPACT_UNCHECKED",
+      "category": "doc_spec_drift",
+      "impact": "revise",
+      "title": "Documentation or SoT impact unchecked",
+      "description": "A behavior, architecture, API, UX, policy or runtime change was completed without checking the affected source-of-truth artefacts.",
+      "applies_to_modes": ["structured_delivery", "quick_task"],
+      "gate_effect": ["qa"],
+      "required_evidence": ["sot_impact_review"],
+      "evaluation": "review",
+      "owner": "docs"
+    },
+    {
+      "code": "AGDF_TEST_SCOPE_UNCLEAR",
+      "category": "tp_coverage",
+      "impact": "revise",
+      "title": "Test scope unclear",
+      "description": "Tests were cited but are not traceable to affected acceptance criteria, tasks or risk paths.",
+      "applies_to_modes": ["structured_delivery", "quick_task"],
+      "gate_effect": ["qa"],
+      "required_evidence": ["test_result", "acceptance_mapping"],
+      "evaluation": "review",
+      "owner": "test"
+    },
+    {
+      "code": "AGDF_QUICK_TASK_EVIDENCE_LIGHT",
+      "category": "agent_process",
+      "impact": "warn",
+      "title": "Quick task evidence light",
+      "description": "A Quick Task has minimal evidence that may be acceptable for scope and risk but must remain visible.",
+      "applies_to_modes": ["quick_task"],
+      "gate_effect": ["none"],
+      "required_evidence": ["closeout_note"],
+      "evaluation": "review",
+      "owner": "governance"
+    }
+  ]
+}

package/generated/.agdf/control/templates/CONTEXT_GRAPH.md

@@ -0,0 +1,51 @@
+# AGDF Context Graph
+
+This file keeps durable delivery knowledge discoverable. It is not a second PRD, SD or task plan.
+
+## Admission Rules
+
+A node belongs here only when it has:
+
+- concrete evidence
+- affected artefacts or paths
+- a visible risk, decision, invariant or reusable Brownfield finding
+- a next clean step
+- an exit criterion
+
+Do not add nodes for general opinions, one-off chat summaries or local observations without future decision value.
+
+## Node Index
+
+| ID | Type | Status | Title | Evidence | Next Step |
+|---|---|---|---|---|---|
+| CG-001 | `decision | brownfield_finding | quality_node | sot_invariant | cleanup_obligation | integration_surface` | `draft | active | resolved | superseded | rejected` |  |  |  |
+
+## Relationship Language
+
+| Relationship | Meaning |
+|---|---|
+| `derived_from` | An artefact was derived from another artefact |
+| `satisfies` | A task or implementation satisfies a requirement or acceptance criterion |
+| `tests` | A test checks a criterion or risk |
+| `mitigates` | Evidence reduces a risk |
+| `depends_on` | A decision or artefact depends on another |
+| `changes` | A requirement changes a component, artefact or behavior |
+| `supersedes` | A newer artefact replaces an older basis |
+| `blocks` | A defect or risk blocks a gate |
+| `approved_by` | An artefact was approved by a gate |
+| `evidenced_by` | A claim is backed by evidence |
+
+## Nodes
+
+### CG-001 Example
+
+- type:
+- status:
+- title:
+- introduced_by:
+- affects:
+- evidence:
+- risk_or_value:
+- next_clean_step:
+- exit_criterion:
+- links:

package/generated/.agdf/control/templates/MASTER_BACKLOG.md

@@ -0,0 +1,29 @@
+# AGDF Master Backlog
+
+This file is the living control pointer for active AGDF delivery work. Detailed UR, PRD, SD, TP, QA and OR artefacts should live in stable paths and be linked from here.
+
+## Rules
+
+1. Keep only steering-relevant work in `Active Backlog`.
+2. Every active item has exactly one current spec pointer.
+3. Historical artefacts remain linkable but do not override the current pointer.
+4. If an item is superseded, mark the replacement.
+5. If active work grows beyond roughly ten items, triage the backlog.
+
+## Active Backlog
+
+| Prio | Key | Title | Status | Current Spec | Notes |
+|---:|---|---|---|---|---|
+| P1 |  |  | `in_progress | blocked` |  |  |
+
+## Planned / Parking Lot
+
+| Prio | Key | Title | Status | Current Spec | Notes |
+|---:|---|---|---|---|---|
+| P2 |  |  | `planned | review_needed` |  |  |
+
+## Completed / Superseded Pointers
+
+| Key | Title | Final Status | Current or Historical Link | Notes |
+|---|---|---|---|---|
+|  |  | `done | superseded | abandoned` |  |  |

package/generated/.agdf/control/templates/SOT_REGISTRY.md

@@ -0,0 +1,25 @@
+# AGDF Source-of-Truth Registry
+
+Use this file to prevent parallel sources of truth. Each domain should have one primary owner.
+
+## Primary Sources of Truth
+
+| Domain | SoT Document | Status | Owner | Last Verified |
+|---|---|---|---|---|
+| Product intent |  | `active | draft | superseded` |  |  |
+| Architecture |  | `active | draft | superseded` |  |  |
+| Runtime contracts |  | `active | draft | superseded` |  |  |
+| UX / user flows |  | `active | draft | superseded` |  |  |
+| Operations / release |  | `active | draft | superseded` |  |  |
+
+## Secondary References
+
+Secondary references may support decisions, but they do not override the primary SoT.
+
+| Reference | Purpose | Limit |
+|---|---|---|
+|  |  |  |
+
+## Conflict Rule
+
+When a secondary document, generated output, old snapshot or chat summary conflicts with the primary SoT, the primary SoT wins until a new approved artefact changes it.

package/generated/.github/skills/README.md

@@ -1,11 +1,12 @@
 # AGDF repository skills
 
-These repository skills are generated from `plugin/skills/`, which is the single source of truth for the AGDF skill contracts.
+These repository skills were generated from the AGDF source repository and are intended to be checked into this repository.
 
 ## Skills
 
 - `agdf-brownfield-analysis`
 - `agdf-clean-implementation-review`
+- `agdf-code-review`
 - `agdf-delivery-closeout`
 - `agdf-gate-check`
 - `agdf-qa-gate`
@@ -14,4 +15,4 @@ These repository skills are generated from `plugin/skills/`, which is the single
 
 ## Runtime contract
 
-Shared output and gate rules live in `agdf-runtime-contract.md`.
+Shared output and gate rules for this checkout live in `agdf-runtime-contract.md`.

package/generated/.github/skills/agdf-clean-implementation-review/SKILL.md

@@ -49,7 +49,7 @@ Use what is available:
 - Code Deliverables
 - changed files
 - tests and test results
-- Code Review Report
+- `agdf-code-review` or Code Review Report
 - QA Report
 - Brownfield Analysis findings
 - PRD or SD architecture notes

package/generated/.github/skills/agdf-code-review/SKILL.md

@@ -0,0 +1,94 @@
+---
+name: agdf-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.
+---
+
+# code-review
+
+## Purpose
+Produce the mandatory Code Review Report (CR) for a relevant run.
+
+It answers:
+
+- whether the changed code shows functional defects, security issues, regression risks, or maintainability problems that matter
+- whether findings are blocking, revisable, or advisory
+- which concrete evidence in files, diffs, tests, or runtime observations supports each finding
+- which issues must be fixed before QA
+- whether Brownfield, TP, or clean-review follow-up remains open
+
+## Runtime Contract
+Use `../agdf-runtime-contract.md` for Quality Contract output, Context Graph fields, gate terms, and non-duplication rules.
+
+Code-review-specific output must make actual findings, missing review scope, evidence strength, and the next required step visible.
+
+## Rules
+1. Review the actual diff and impacted code, not intent alone.
+2. Findings require concrete evidence.
+3. Prioritize correctness, safety, data integrity, compatibility, and maintainability over style.
+4. Do not generate style-only noise.
+5. Missing review scope or evidence must stay visible.
+6. Brownfield owners and existing conventions are binding unless deviation is justified.
+7. Distinguish blocking defects from fixable review findings.
+8. CR does not grant QA pass.
+
+## When To Use
+- after `CD+Tests`
+- before `QA`
+- when code changes exist
+- when multiple agents or contributors touched the same area
+- when a commit-near change needs explicit review evidence
+
+## Inputs
+Use what is available:
+
+- changed files and diff
+- affected neighbouring code
+- test/build results
+- Brownfield Analysis
+- Task Plan and TP Review
+- Clean Implementation Review
+- runtime or UI evidence
+- known risks or follow-up decisions
+
+If no code changes are present, do not invent a CR result.
+
+## Workflow
+1. Inspect the changed files and directly impacted neighbours.
+2. Check correctness, edge cases, and error paths.
+3. Check security, data handling, and state ownership risks.
+4. Check regression and compatibility risks.
+5. Check maintainability only where it creates real defect or change-risk exposure.
+6. Classify the overall result:
+   - `pass`
+   - `revise`
+   - `block`
+   - `not_applicable`
+7. Set exactly one required next step.
+
+## Output
+Use this compact structure:
+
+```text
+## Code Review
+- decision: pass | revise | block | not_applicable
+- findings:
+  - [severity] file/path - issue - evidence
+- missing_evidence:
+- risks:
+- required_next_step:
+```
+
+## Decision Guidance
+- `pass`: no meaningful review finding remains evident in reviewed scope.
+- `revise`: fixable correctness, regression, or maintainability issues remain.
+- `block`: a hard defect, security risk, data-integrity risk, or unresolved critical uncertainty remains.
+- `not_applicable`: no code changes were present for review.
+
+## Forbidden
+This skill must not:
+
+- decide final QA
+- accept a green build as sufficient review evidence
+- hide missing review scope
+- generate style-only findings
+- duplicate TP Review or QA as if they were the same step

package/generated/.github/skills/agdf-qa-gate/SKILL.md

@@ -40,7 +40,7 @@ QA-specific `decision` is exactly `pass | revise | block`.
 
 ## When To Use
 - after `CD+Tests`
-- after Code Review
+- after `agdf-code-review`
 - after `agdf-task-plan-review`
 - after `agdf-clean-implementation-review`
 - before UAT
@@ -58,7 +58,7 @@ Use what is available:
 - approved TP and TP Review
 - Brownfield Analysis
 - Clean Implementation Review
-- Code Review Report
+- `agdf-code-review` or Code Review Report
 - test/build results
 - documentation impact review
 - runtime or UI evidence

package/generated/.github/skills/agdf-release-or/SKILL.md

@@ -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 CR
+- after `agdf-code-review`
 - after QA
 - after UAT
 - whenever a compact audit closeout is needed
@@ -62,6 +62,7 @@ Use what is available:
 - `agdf-task-plan-review`
 - `agdf-brownfield-analysis`
 - `agdf-clean-implementation-review`
+- `agdf-code-review`
 - QA Report
 - UAT Report
 - documentation impact review

package/generated/.github/skills/agdf-runtime-contract.md

@@ -22,6 +22,7 @@ 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.
 
@@ -52,6 +53,18 @@ When a run affects project memory or a Context Graph, use:
 Do not create a new node for a mere version, a general chat summary, or a local observation without a concrete next clean step.
 `sot_drift` must not pass silently as a warning.
 
+## Control Scaffold
+
+When a repository needs durable AGDF state, use the plugin-local `control/` scaffold as the starting point.
+
+- `AGDF_RUN.md` is the current run dashboard.
+- `MASTER_BACKLOG.md` is the living pointer for active delivery work.
+- `SOT_REGISTRY.md` prevents parallel sources of truth.
+- `CONTEXT_GRAPH.md` stores durable Brownfield findings, decisions, risks, evidence and exit criteria.
+- `AGENT_QUALITY_CONTRACTS.json` stores reusable block, revise and warning conditions.
+
+The scaffold is not a second documentation site. Link to authoritative artefacts instead of copying them.
+
 ## Skill Output
 
 Every skill output should be as short as possible and as concrete as needed.

package/generated/AGENTS.md

@@ -44,6 +44,7 @@ Evidence overrides assumptions and memory. If evidence is missing, state the unc
 | `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 |
@@ -52,10 +53,22 @@ Select exactly one primary skill first. Add more only when they cover a distinct
 
 ## Skill Contract
 For repeated output, gate, Quality Contract, and Context Graph rules, use:
-`plugin/meta/agdf-runtime-contract.md`
+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

package/package.json

@@ -1,7 +1,7 @@
 {
   "name": "create-agdf",
-  "version": "0.1.1",
-  "description": "Bootstrap AGDF for GitHub Copilot, Claude Code, or both.",
+  "version": "0.1.3",
+  "description": "Bootstrap AGDF repository instructions, skills and control templates for GitHub Copilot; AGDF also ships as Claude Code and Codex plugins.",
   "type": "module",
   "files": [
     "bin",
@@ -20,6 +20,8 @@
     "agdf",
     "copilot",
     "claude-code",
+    "codex",
+    "control",
     "scaffold",
     "bootstrap"
   ],