chore(framework): bump aidd-pm to 1.0.0 and apply audit fixes

Version: aidd-pm goes from 1.0.0-rc.1 to 1.0.0 (manifest, marketplace.json, plugin.json, README status).

Audit fixes (cross-plugin):
- aidd-context: project-init description in plugin README aligned with skill README (rule dirs are created lazily by 03-context-generate).
- aidd-dev: 02-implement README clarifies branching is the caller's responsibility (matches 00-sdlc policy).
- aidd-orchestrator/02-run-async-dev: rewrote action 05/06 descriptions and Outputs section to match SKILL.md contract (skill emits run-result.json, post-job owns audit, Check Run, label transition; no orchestrator vocabulary in delegation prompt).
- aidd-orchestrator/03-review-async-dev: action names aligned with files and SKILL.md (fix-iteration, finalize).
- aidd-orchestrator/01-setup-async-dev: drop "asks ~6 questions" tilde filler.
- aidd-refine/04-shadow-areas: drop dead reference to evals/validate-report.mjs.
- Plugin READMEs (context, dev, orchestrator, refine, vcs): strip "(or the first listed skill if no onboard exists)" filler.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

Author: blafourcade

.claude-plugin/marketplace.json

@@ -31,9 +31,9 @@
     },
     {
       "name": "aidd-pm",
-      "version": "1.0.0-rc.1",
+      "version": "1.0.0",
       "source": "./plugins/aidd-pm",
-      "description": "Product management (release candidate): ticket-info, user-stories-create, prd, spec",
+      "description": "Product management: ticket-info, user-stories-create, prd, spec",
       "strict": true,
       "recommended": true
     },

.release-please-manifest.json

@@ -3,7 +3,7 @@
   "plugins/aidd-context": "1.0.0",
   "plugins/aidd-dev": "1.0.0",
   "plugins/aidd-vcs": "1.0.0",
-  "plugins/aidd-pm": "1.0.0-rc.1",
+  "plugins/aidd-pm": "1.0.0",
   "plugins/aidd-orchestrator": "1.0.0",
   "plugins/aidd-refine": "1.0.0"
 }

README.md

@@ -112,7 +112,7 @@ Commits, pull / merge requests, release tags, issue creation.
 
 ### 📋 [aidd-pm](plugins/aidd-pm/README.md)
 
-`4 skills` · release candidate
+`4 skills` · stable
 
 Ticket info, user stories, PRD, spec drafting.
 

plugins/aidd-context/README.md

@@ -6,7 +6,7 @@ Knowledge production plugin for the AI-Driven Development framework.
 
 > Status: stable.
 
-First time? Install with `/plugin install aidd-context@aidd-framework`, then run `aidd-context:00:onboard` (or the first listed skill if no onboard exists).
+First time? Install with `/plugin install aidd-context@aidd-framework`, then run `aidd-context:00:onboard`.
 
 Covers project bootstrap, project initialisation, context generation, Mermaid diagrams, learning, discovery, and a state-aware onboarding loop.
 
@@ -16,7 +16,7 @@ Covers project bootstrap, project initialisation, context generation, Mermaid di
 | ---------- | -------------- | --------------------------------------------------------------------------------------------------------------------------------------------------------------- |
 | [1.0]      | [onboard](skills/00-onboard/README.md)                 | Detect the project's aidd-context state and guide the user to ONE next aidd-context action through a state -> recommend -> execute loop.                       |
 | [1.1]      | [bootstrap](skills/01-bootstrap/README.md)             | Imagine and validate the technical architecture of a new SaaS through interactive Q&A, candidate-stack comparison, multi-agent audit, and an INSTALL.md output. |
-| [1.2]      | [project-init](skills/02-project-init/README.md)       | Initialize project memory bank and scaffold the rules directory structure.                                                                                      |
+| [1.2]      | [project-init](skills/02-project-init/README.md)       | Initialize the project memory bank (rule directories are created lazily by `03-context-generate`).                                                              |
 | [1.3]      | [context-generate](skills/03-context-generate/README.md) | Generate Claude Code context artifacts - router-based skills, agents, and rules.                                                                                |
 | [1.4]      | [mermaid](skills/04-mermaid/README.md)                 | Generate high-quality Mermaid diagrams from markdown content using a structured plan-validate workflow.                                                         |
 | [1.5]      | [learn](skills/05-learn/README.md)                     | Capture and store learnings from recently implemented features into memory bank, decisions, or coding rules.                                                    |

plugins/aidd-dev/README.md

@@ -6,7 +6,7 @@ Code transformation plugin for the AI-Driven Development framework.
 
 > Status: stable.
 
-First time? Install with `/plugin install aidd-dev@aidd-framework`, then run `aidd-dev:00:sdlc` (or the first listed skill if no onboard exists).
+First time? Install with `/plugin install aidd-dev@aidd-framework`, then run `aidd-dev:00:sdlc`.
 
 Covers the full SDLC coding loop: orchestrator, planning, assertions, audits, code review, testing, refactoring, debugging, and the for-sure workflow. Also hosts AI agents.
 

plugins/aidd-dev/skills/02-implement/README.md

@@ -28,10 +28,11 @@ Use skill aidd-dev:02:implement
 
 Pass the plan path or content as `$ARGUMENTS`. The skill exposes 1 action:
 
-1. `implement` - branch (if specified), then loop each plan phase: spawn the
-   `implementer` agent, wait for structured output, re-spawn with
-   `items_remaining` until the phase hits 100 %. Plan amendments are made
-   inline and tagged with the robot marker.
+1. `implement` - loop each plan phase: spawn the `implementer` agent, wait
+   for structured output, re-spawn with `items_remaining` until the phase
+   hits 100 %. Branching is the caller's responsibility; this skill never
+   creates branches. Plan amendments are made inline and tagged with the
+   robot marker.
 
 ## Outputs
 

plugins/aidd-orchestrator/README.md

@@ -6,7 +6,7 @@ Orchestration plugin for the AI-Driven Development framework.
 
 > Status: stable for use case `async-dev`; other use cases on the roadmap are experimental.
 
-First time? Install with `/plugin install aidd-orchestrator@aidd-framework`, then run `aidd-orchestrator:01:setup-async-dev` (or the first listed skill if no onboard exists).
+First time? Install with `/plugin install aidd-orchestrator@aidd-framework`, then run `aidd-orchestrator:01:setup-async-dev`.
 
 Composes capabilities into deterministic, auditable flows. Each skill is one orchestration brick; several use cases coexist inside the same plugin.
 

plugins/aidd-orchestrator/skills/01-setup-async-dev/README.md

@@ -23,7 +23,7 @@ from a fresh clone to the first triggered run.
 Use skill aidd-orchestrator:01:setup-async-dev
 ```
 
-The skill asks ~6 questions:
+The skill asks 6 questions:
 
 | Question | Default | Notes |
 |----------|---------|-------|

plugins/aidd-orchestrator/skills/02-run-async-dev/README.md

@@ -63,20 +63,22 @@ The skill walks 6 atomic actions:
 2. `resolve-deps` - filter out blocked ones.
 3. `acquire-lock` - swap `to-implement` → `claude/working`.
 4. `check-sdlc` - discover the SDLC capability by description.
-5. `delegate-sdlc` - invoke that capability via the `Skill` tool with the
-   delegation contract (branch name, base, body containing `Closes #N`).
-6. `write-audit` - commit and push the audit JSON to the PR branch, create
-   the GitHub Check Run, transition the label to `claude/awaiting-review`.
+5. `delegate-sdlc` - invoke that capability via the `Skill` tool with a
+   single free-text `request` plus any human comments. No branch name, no
+   `Closes #N`, no PR-title format - the SDLC owns those decisions so it
+   runs identically whether called by the orchestrator or by a human.
+6. `write-audit` - emit `$RUNNER_TEMP/run-result.json` and exit.
 
 ## Outputs
 
-- A feature branch `feat/issue-<N>-<slug>` on the repo.
-- A pull request with body containing `Closes #<N>`.
-- `aidd_docs/async-runs/<YYYY_MM>/<run-id>.json` on the PR branch.
-- A GitHub Check Run `aidd-async/<run-id>`.
-- Label transition on the issue: `to-implement` → `claude/working` →
-  `claude/awaiting-review` (or `claude/blocked` on failure, with a comment
-  describing the cause).
+This skill emits one artifact: `$RUNNER_TEMP/run-result.json`.
+
+Everything else (audit log persistence under `aidd_docs/async-runs/`, the
+GitHub Check Run, the label transition to `claude/awaiting-review` or
+`claude/blocked`, the completion marker) is owned by the workflow's
+post-job step, which reads `run-result.json` after the skill exits. Branch
+name and pull-request body shape are owned by the SDLC that action 05
+delegated to.
 
 ## Prerequisites
 

plugins/aidd-orchestrator/skills/03-review-async-dev/README.md

@@ -33,10 +33,10 @@ The skill walks 4 atomic actions:
 2. `detect-stop` - decide whether to fix or stop. Stop reasons:
    `blocked_label`, `max_iterations`, `human_reviewer` (only iteration >1),
    `no_comments`.
-3. `delegate-fix` - invoke the SDLC capability with the comment context to
+3. `fix-iteration` - invoke the SDLC capability with the comment context to
    produce one fix commit on the PR branch; reply inline on each addressed
    comment and resolve the thread.
-4. `write-summary` - post a structured iteration summary comment, transition
+4. `finalize` - post a structured iteration summary comment, transition
    the label back to `claude/awaiting-review`, write the audit record.
 
 ## Outputs