@haaaiawd/anws 2.4.0 → 2.4.1

package/templates_en/.agents/skills/task-reviewer/SKILL.md

@@ -1,15 +1,14 @@
 ---
 name: task-reviewer
-description: "[ALPHA] Systematically reviews 05A_TASKS.md and 05B_VERIFICATION_PLAN.md as the task-contract and verification-contract evidence layer for the `/challenge` workflow; 7 passes (A→G), four semantic models, finding cap, and cross-document gates are unchanged; on-disk narration follows the alpha spec contract (precise, traceable, no generic filler, no duplication)."
+description: "Systematically reviews 05A_TASKS.md and 05B_VERIFICATION_PLAN.md as the task-contract and verification-contract evidence layer for the `/challenge` workflow; 7 passes (A→G), four semantic models, finding cap, and cross-document gates are unchanged; on-disk narration follows output-contract plus this skill's gates."
 ---
 
-# task-reviewer (ALPHA)
-
+# task-reviewer
 <phase_context>
 You are **TASK-REVIEWER**.  
 **Mission**: On the semantic model, run **Pass A→G** over tasks and the verification plan, producing a merge-ready structured inventory for whether commitments are borne by tasks, whether there is an executable verification path, and whether contracts can be closed with evidence; you supply **evidence slices** for challenge—not a restatement of challenge’s global ruling.  
 **Capabilities**: Modeling REQ / US / task mapping / contract; detection of duplication, ambiguity, underspecification, inconsistency, gaps, granularity, and contract coverage; severity attribution; overflow truncation summaries.  
-**Constraints**: Does not alter the normative force of shipped `templates/`; ALPHA compresses redundant asides only and must keep the hard constraints below and each Pass’s **checks, severity binding, and gate semantics** verbatim equivalent.  
+**Constraints**: Edits may compress redundant asides only; keep the hard constraints below and each Pass’s **checks, severity binding, and gate semantics** verbatim equivalent to this SKILL body.
 </phase_context>
 
 ---
@@ -29,12 +28,7 @@ You are **TASK-REVIEWER**.
 ## CRITICAL spec output contract
 
 > [!IMPORTANT]
-> Report segments from this skill (embedded in `07_CHALLENGE_REPORT.md` or as a standalone attachment) must satisfy simultaneously:
->
-> - **Precise**: Verifiable statements include `path:line`, section anchors, or model IDs (`REQ-*` / `US-*` / `T*.*.*` / `CONTRACT-*`).  
-> - **Traceable**: “Finding / evidence / impact / recommendation” traces back to files read or table lookup steps.  
-> - **No duplication**: One fact is not restated differently in summary versus detail; overview tables paste no long verbatim quotes.  
-> - **No generic filler**: Prohibited: objectless lines like “needs attention,” “to optimize,” “strengthen as appropriate”; recommendations must name task or doc change type.
+> Shared persisted-report rules (precision, evidence, non-repetition, no filler, single-writer, delegation closure) are defined in **`.agents/skills/output-contract/SKILL.md`**; this skill adds that every finding must map to `REQ-*` / `US-*` / `T*.*.*` / `CONTRACT-*` or a concrete `path:line` / section anchor.
 
 Challenge alignment bullets: In the **core findings list**, **Finding**, **Impact**, and **Recommendation** are each **one sentence** (short compound allowed); **Location** column uses minimal anchors (e.g. `PRD §…`, `path:line`, `05A §Task`).
 

package/templates_en/.agents/skills/tech-evaluator/SKILL.md

@@ -1,17 +1,17 @@
 ---
 name: tech-evaluator
-description: [ALPHA] Serves `/genesis` Step 3 "Technical selection": evaluates candidate stacks with ATAM and a 12-dimension weighted matrix, producing traceable comparison conclusions and ADR promotion material; does not author formal ADR files (persisted in Step 5). Same lineage as the same-named skill in shipped `templates/`; prefer references at the same relative path inside this bundle.
+description: Serves `/genesis` Step 3 "Technical selection": evaluates candidate stacks with ATAM and a 12-dimension weighted matrix, producing traceable comparison conclusions and ADR promotion material; does not author formal ADR files (persisted in Step 5). Prefer `references/` beside this SKILL.
 ---
 
-# Technical Evaluator Handbook — [ALPHA] Genesis Step 3
+# Technical Evaluator Handbook — Genesis Step 3
 
 > "There is no best technology stack—only the most suitable stack." — ThoughtWorks Technology Radar
 
-This skill is grounded in **SEI ATAM (Architecture Tradeoff Analysis Method)** and **weighted decision matrices**. In **`templates_alpha/`** / **`templates_alpha_en/`** ALPHA workflows it binds to **`/genesis`** as **Step 3**; formal **ADR authoring** and numbering are governed by **Step 5** and `genesis.md`.
+This skill is grounded in **SEI ATAM (Architecture Tradeoff Analysis Method)** and **weighted decision matrices**. In **`/genesis`** it binds as **Step 3**; formal **ADR authoring** and numbering are governed by **Step 5** and `genesis.md`.
 
 ---
 
-## CRITICAL /genesis gates (difference from shipped skill)
+## CRITICAL /genesis gates (this track only)
 
 > [!IMPORTANT]
 >
@@ -206,7 +206,7 @@ The parent agent can open `references/ADR_TEMPLATE.md` in Step 5 and align secti
 
 ## references and bundle paths
 
-This bundle includes **`templates_alpha_en/.agents/skills/tech-evaluator/references/ADR_TEMPLATE.md`** mirrored from shipped **`templates/`**. Read **only** `references/` beside this SKILL; **do not** mix-read shipped `templates/.agents/skills/tech-evaluator/` in the same session.
+This bundle ships **`references/ADR_TEMPLATE.md`** beside this SKILL. Read **only** `references/` next to this SKILL.
 
 | File | Purpose |
 |------|---------|
@@ -248,5 +248,5 @@ Merged draft still meets spec; no contradictory scores or duplicate candidate na
 - Deliverables meet **CRITICAL spec delivery contract** (verifiable / countable / deducible / promotable / explicit verification strategy).
 - On the default `/genesis` Step 3 path, **no** ADR persisted under `.anws/v{N}/03_ADR/`.
 - Handoff checklist holds or exemptions are logged in the final section "Open items".
-- If loaded from `templates_alpha` or `templates_alpha_en`, use the **same overlay tree** as other skills in this session; do not mix shipped `templates/` variants for the same step to avoid gate drift.
+- Use the workspace **`.agents/skills/`** tree consistently with other skills in the session.
 </completion_criteria>

package/templates_en/.agents/workflows/blueprint.md

@@ -1,11 +1,11 @@
 ---
-description: "[ALPHA] Orchestrate /blueprint: generate 05A/05B from approved design inputs; host keeps order, gates, and handoff contracts; schemas/templates authoritative in **this overlay** `.agents/skills/task-planner/` (mirrors shipped `templates/` at the same relative path)."
+description: "Orchestrate /blueprint: generate 05A/05B from approved design inputs; host keeps order, gates, and handoff contracts; schemas/templates authoritative in workspace **`.agents/skills/task-planner/`**."
 ---
 
-# /blueprint (ALPHA)
+# /blueprint
 
 <phase_context>
-You are the **TASK ARCHITECT (ALPHA track)**.
+You are the **TASK ARCHITECT**.
 
 **Mission**: Orchestrate approved design inputs into executable `05A_TASKS.md` and `05B_VERIFICATION_PLAN.md`, then enforce closure gates.  
 **Capabilities**: version targeting, precondition checks, contract mapping, `task-planner` invocation, closure checks, `AGENTS.md` A/B entry updates.  
@@ -19,7 +19,7 @@ You are the **TASK ARCHITECT (ALPHA track)**.
 ## CRITICAL concision & layout (/craft + /challenge spirit)
 
 > [!IMPORTANT]
-> **craft**: Before editing, Read shipped `.agents/skills/craft-authoring/SKILL.md` and `.agents/workflows/craft.md`; each `## Step …` uses **`### What to do` / `### Why` / `### How to verify`**; `<completion_criteria>` required.  
+> **craft**: Before editing, Read **`.agents/skills/craft-authoring/SKILL.md`** and **`.agents/workflows/craft.md`**; each `## Step …` uses **`### What to do` / `### Why` / `### How to verify`**; `<completion_criteria>` required.  
 > **Concision**: Session and user-facing text—**one fact per sentence**; table semantics duplicated in `task-planner` stay **in SKILL/references**.  
 > **No injection**: Do not paste large excerpts of `TASK_TEMPLATE_05A` / `TASK_TEMPLATE_05B` here—**single authority** under **task-planner paths** below.
 
@@ -29,7 +29,7 @@ You are the **TASK ARCHITECT (ALPHA track)**.
 
 > [!IMPORTANT]
 > **Sole authority for `task-planner` (field / table schema)**  
-> Read **this overlay** `.agents/skills/task-planner/SKILL.md` (same relative path as shipped `templates/`—**do not** mix clauses from shipped vs alpha trees in one session).  
+> Read **`.agents/skills/task-planner/SKILL.md`** (same workspace `.agents/` tree as this workflow).
 > `.agents/skills/task-planner/references/TASK_TEMPLATE_05A.md`  
 > `.agents/skills/task-planner/references/TASK_TEMPLATE_05B.md`  
 >

package/templates_en/.agents/workflows/challenge.md

@@ -1,8 +1,8 @@
 ---
-description: "[ALPHA] Contract-fidelity challenge to design/tasks/implementation—evidence first, gates intact; produces 07_CHALLENGE_REPORT.md."
+description: "Contract-fidelity challenge to design/tasks/implementation—evidence first, gates intact; produces 07_CHALLENGE_REPORT.md."
 ---
 
-# /challenge (ALPHA)
+# /challenge
 
 <phase_context>
 You are the **CHALLENGER**.
@@ -31,14 +31,9 @@ You are the **CHALLENGER**.
 ## CRITICAL Writing constraints and report contract
 
 > [!IMPORTANT]
-> **Normative gates cannot be weakened**: Contract sources and commitment model, severity definitions, full adherence to `REVIEW_MODE` and each reviewer skill, Step 4.5 review gate, routing logic `/blueprint` before `/forge`, and round archival protocol are hard constraints; do not shorten, soften, or replace with implication because this is ALPHA or for length targets. The only tightening allowed is duplicate explanation, filler, and paraphrase already carried by tables.
+> **Normative gates cannot be weakened**: Contract sources and commitment model, severity definitions, full adherence to `REVIEW_MODE` and each reviewer skill, Step 4.5 review gate, routing logic `/blueprint` before `/forge`, and round archival protocol are hard constraints; do not shorten, soften, or replace with implication for length targets. The only tightening allowed is duplicate explanation, filler, and paraphrase already carried by tables.
 >
-> **Output documents (spec / report) writing contract**:
->
-> - **Precise**: Verifiable statements carry source, `path:line`, or section anchor.  
-> - **Traceable**: Findings, evidence, and recommendations map back to concrete files, interfaces, or search steps.  
-> - **Non-repetitive**: The same fact is not restated differently; overview must not paste long detail blocks.  
-> - **No generic filler**: Ban object-less phrases like “needs attention,” “to be optimized,” “recommend strengthening.”
+> **Shared report contract**: Persisted-report rules (precision, evidence, non-repetition, no filler, single-writer, delegation closure) are defined in **`.agents/skills/output-contract/SKILL.md`**.
 >
 > **Challenge table rule**: In **Core findings**, **Finding**, **Impact**, and **Recommendation** are each **one sentence** (very short compound allowed); the **Location** column uses minimal anchors (e.g. `PRD §x`, `path:line`, `05A §Task`).
 
@@ -79,11 +74,11 @@ You are the **CHALLENGER**.
 
 ---
 
-## ALPHA paired skills (same bundle as this line)
+## Paired skills (same bundle as this line)
 
 > [!IMPORTANT]
-> When using the **`templates_alpha/`** or **`templates_alpha_en/`** overlay, Step 3 / 3.5 / 3.7 must read **`design-reviewer`**, **`task-reviewer`**, and **`code-reviewer`** from the **same tree**: `.agents/skills/<id>/SKILL.md` (sibling of `workflows/challenge.md`). **Do not** mix, in one session, with skill revisions under shipped `templates/`—gates and table semantics will drift.  
-> **`nexus-mapper`**: **prefer** this bundle **`.agents/skills/nexus-mapper/`**; fall back to shipped **`templates/`** only if the full alpha tree is not mounted.
+> Step 3 / 3.5 / 3.7 read **`design-reviewer`**, **`task-reviewer`**, and **`code-reviewer`** from workspace `.agents/skills/<id>/SKILL.md` (sibling of `workflows/challenge.md`).
+> **`nexus-mapper`**: read **`.agents/skills/nexus-mapper/SKILL.md`** when installed by `anws`.
 
 ---
 

package/templates_en/.agents/workflows/change.md

@@ -1,11 +1,11 @@
 ---
-description: "[ALPHA] /change: controlled in-version changes and 05A/05B backflow after /forge; permission + ten-question gates preserved; align edits with task-planner; no long signature templates in host."
+description: "/change: controlled in-version changes and 05A/05B backflow after /forge; permission + ten-question gates preserved; align edits with task-planner; no long signature templates in host."
 ---
 
-# /change (ALPHA)
+# /change
 
 <phase_context>
-You are **CHANGE MANAGER (ALPHA track)**.
+You are **CHANGE MANAGER**.
 
 **Mission**: After **`/forge` coding has started**, handle controlled in-version changes, contracts, and task/verification backflow for current `v{N}`; escalate to `/genesis` only on **foundational evolution**.  
 **Capabilities**: version targeting, ten-question tiering, impact mapping, signed writes to `05A`/`05B`/`06`, ADR↔`04` reference checks, field-level edits aligned to `task-planner`.  
@@ -19,7 +19,7 @@ You are **CHANGE MANAGER (ALPHA track)**.
 ## CRITICAL concision & layout (/craft + /challenge spirit)
 
 > [!IMPORTANT]
-> **craft**: Before editing, Read shipped `.agents/skills/craft-authoring/SKILL.md` and `.agents/workflows/craft.md`; each `## Step …` uses **`### What to do` / `### Why` / `### How to verify`**; `<completion_criteria>` required.  
+> **craft**: Before editing, Read **`.agents/skills/craft-authoring/SKILL.md`** and **`.agents/workflows/craft.md`**; each `## Step …` uses **`### What to do` / `### Why` / `### How to verify`**; `<completion_criteria>` required.  
 > **Concision**: Plans and user-facing reports—**one fact per sentence**; ten-question logic must stay **answerable in full**—trim only duplicate prose, not gates.  
 > **No injection**: Do not embed full “impact assessment” or “signature checkpoint” fences—**required fields/functions** are named in Steps 1 and 3.
 
@@ -28,7 +28,7 @@ You are **CHANGE MANAGER (ALPHA track)**.
 ## CRITICAL permission boundaries (gates cannot be weakened)
 
 > [!IMPORTANT]
-> Boundaries depend on **whether the current version’s core premise changes**—**not** on which file you touch. This table is **semantically equivalent** to shipped `.agents/workflows/change.md`; if it conflicts, shipped wins and this alpha should be fixed.
+> Boundaries depend on **whether the current version’s core premise changes**—**not** on which file you touch. This table is the **normative gate** for `/change`.
 
 | Capability | Allowed | Forbidden |
 |------------|:-------:|:---------:|
@@ -78,7 +78,7 @@ No `05A` → no anchored task backflow.
 
 ### What to do
 
-Answer **all ten** questions (session or compact table; **no** full sample table pasted from shipped):
+Answer **all ten** questions (session or compact table; **no** pasting a full sample table into this workflow):
 
 1. Change requirement goals / user-story set / boundary?  
 2. Change system boundary / key execution model / arch baseline?  
@@ -145,7 +145,7 @@ Signature is the only legitimate pre-write gate.
 
 ### What to do
 
-Explain why `/change` cannot absorb the change, need new `v{N+1}`, and Git track-switch (freeze `feature/*`, new line from `main`) per shipped `change` intent—**without** embedding a long notification template here.
+Explain why `/change` cannot absorb the change, need new `v{N+1}`, and Git track-switch (freeze `feature/*`, new line from `main`) per **Step 4 intent**—**without** embedding a long notification template here.
 
 ### Why
 

package/templates_en/.agents/workflows/craft.md

@@ -1,11 +1,11 @@
 ---
-description: "[ALPHA] /craft: forge Workflow / Skill / Prompt; methodology + scoring gate preserved; craft-authoring + RUBRIC live only under shipped templates; host does not inject full score sheets."
+description: "/craft: forge Workflow / Skill / Prompt; methodology + scoring gate preserved; `craft-authoring` + RUBRIC authoritative under **`.agents/skills/craft-authoring/references/`** in the package; host does not inject full score sheets."
 ---
 
-# /craft (ALPHA)
+# /craft
 
 <phase_context>
-You are **CRAFTSMAN (Cognitive Craft Architect) — ALPHA track**.
+You are **CRAFTSMAN (Cognitive Craft Architect)**.
 
 **Mission**: Turn vague intent into reusable AI protocol assets (Workflow / Skill / Prompt) and treat them as shippable only after the **scoring gate** passes.  
 **Capabilities**: clarify requirements, pick mode, research grounding, apply `craft-authoring` scaffolds, preflight checks, static scoring with RUBRIC/SCORECARD and iteration.  
@@ -16,19 +16,19 @@ You are **CRAFTSMAN (Cognitive Craft Architect) — ALPHA track**.
 
 ---
 
-## CRITICAL concision & layout (read shipped `/craft` + `craft-authoring`)
+## CRITICAL concision & layout (read `/craft` + `craft-authoring`)
 
 > [!IMPORTANT]
-> **craft**: Before editing, Read **`.agents/skills/craft-authoring/SKILL.md`** and **`.agents/workflows/craft.md`** (canonical `/craft`); this ALPHA host stays **semantically aligned**—if they conflict, **shipped `templates/`** wins and this file should be fixed.  
+> **craft**: Before editing, Read **`.agents/skills/craft-authoring/SKILL.md`** and **`.agents/workflows/craft.md`** (`/craft`); stay **semantically aligned** with that host.
 > **Concision**: **One fact per sentence** in delivered prose; layout duplicated in `craft-authoring` stays **in SKILL/references**.  
 > **No injection**: Do not paste full `PROMPT_QUALITY_RUBRIC.md` / `SCORECARD_TEMPLATE.md` bodies; Step 6 names only **required paths and output responsibilities** (Tier, seven-dimension score, evidence, fixes, confidence, Hard Fail behavior).
 
 ---
 
-## CRITICAL methodological anchors (equivalent to shipped)
+## CRITICAL methodological anchors (compress prose, keep semantics)
 
 > [!IMPORTANT]
-> **Awaken, do not merely declare**; **expand, do not stay single-track**; **rise, then descend**; **rebuild, do not repeat**—same intent as shipped `craft.md` **CRITICAL Methodology Anchors**; do not weaken into implication-only prose for ALPHA length.
+> **Awaken, do not merely declare**; **expand, do not stay single-track**; **rise, then descend**; **rebuild, do not repeat**—same intent as **`/craft` CRITICAL Methodology Anchors**; do not weaken into implication-only prose for length targets.
 
 ---
 
@@ -72,7 +72,7 @@ Mode sets activation and skeleton; wrong mode lowers adherence.
 
 ### What to do
 
-Research before drafting; for heavy topics invoke **`/explore`** (if **`templates_alpha`** is mounted, follow the same bundle **`explore.md`** triggers and OUTPUT rules). Findings must flow into structure and constraints.
+Research before drafting; for heavy topics invoke **`/explore`** and follow the **same workspace** **`.agents/workflows/explore.md`** triggers and OUTPUT rules. Findings must flow into structure and constraints.
 
 ### Why
 
@@ -125,7 +125,7 @@ Last defense before assets enter team memory.
 
 ### What to do
 
-1. **Must** read **`.agents/skills/craft-authoring/references/PROMPT_QUALITY_RUBRIC.md`** and **`SCORECARD_TEMPLATE.md`** (same **`templates_alpha_en/.agents/`** install root as this workflow; diff against shipped `templates/` when both trees exist).  
+1. **Must** read **`.agents/skills/craft-authoring/references/PROMPT_QUALITY_RUBRIC.md`** and **`SCORECARD_TEMPLATE.md`** (under the workspace **`.agents/`** tree alongside this workflow).
 2. Emit: **Tier (T0–T3)**, **weighted seven-dimension score**, **evidence**, **fixes**, **confidence**; prefer **subagent** review—if unavailable, main agent applies the **same** standard.  
 3. **Hard Fail (T3)** → verdict **`Infeasible`**, **no** release.  
 4. No Hard Fail and weighted **< 4.0** → **iterate and re-score**.  

package/templates_en/.agents/workflows/design-system.md

@@ -1,11 +1,11 @@
 ---
-description: "[ALPHA] /design-system: single-system detailed design; host owns order, gates, paths; sections, L0/L1 split, and 6D depth are authoritative in **this overlay** `.agents/skills/system-designer/` (mirrors shipped `templates/` at the same relative path)."
+description: "/design-system: single-system detailed design; host owns order, gates, paths; sections, L0/L1 split, and 6D depth are authoritative in workspace **`.agents/skills/system-designer/`**."
 ---
 
-# /design-system (ALPHA)
+# /design-system
 
 <phase_context>
-You are the **SYSTEM DESIGNER (ALPHA track)**.
+You are the **SYSTEM DESIGNER**.
 
 **Mission**: Produce (optionally two-layer) system design docs for one `<system-id>` with research, traceability, and conditional review gates satisfied.  
 **Capabilities**: version targeting, context load, `/explore` research, `sequential-thinking` selection, L0/L1 persistence from templates, conditional `/challenge`, `AGENTS.md` navigation line.  
@@ -19,7 +19,7 @@ You are the **SYSTEM DESIGNER (ALPHA track)**.
 ## CRITICAL concision & layout (/craft + /challenge spirit)
 
 > [!IMPORTANT]
-> **craft**: Before editing, Read shipped `.agents/skills/craft-authoring/SKILL.md` and `.agents/workflows/craft.md`; each `## Step …` uses **`### What to do` / `### Why` / `### How to verify`**; `<completion_criteria>` required.  
+> **craft**: Before editing, Read **`.agents/skills/craft-authoring/SKILL.md`** and **`.agents/workflows/craft.md`**; each `## Step …` uses **`### What to do` / `### Why` / `### How to verify`**; `<completion_criteria>` required.  
 > **Concision**: Persisted prose **one fact per sentence**; table discipline aligns with `/challenge` spirit (do not paste challenge body).  
 > **No injection**: Do not unfold full 6D prose, long FAQ, or giant optional-skill catalogs—**authority** is **`.agents/skills/system-designer/SKILL.md`** and the two reference templates above.
 
@@ -48,7 +48,7 @@ You are the **SYSTEM DESIGNER (ALPHA track)**.
 
 > [!IMPORTANT]
 > When this design defines public APIs, CLI semantics, config/file formats, error semantics, or cross-system protocols, Step 6 **must** run `/challenge` on `{system-id}.md`.  
-> If the host mounts **`templates_alpha` / `templates_alpha_en`** `challenge.md`, reviewer skills are read **only** from the **same bundle** `.agents/skills/*` paired there—**do not** mix, in one session, with shipped `templates/` skills of the same names.
+> When the host runs **`/challenge`**, read reviewer skills from the paired paths under the **same workspace** `.agents/skills/*` as that `challenge.md`.
 
 ---
 
@@ -196,7 +196,7 @@ Human sign-off plus team entry makes design externally visible.
 <completion_criteria>
 - **Concision & layout**: all Steps have the three subsections; no SKILL/template wall-of-text pasted as substitute for reading files.  
 - `system_id` + `TARGET_DIR` explicit; missing inputs caused correct stop.  
-- `/explore` executed with usable `_research`; Step 5 read shipped `system-designer` + templates and wrote L0 (+ conditional L1).  
+- `/explore` executed with usable `_research`; Step 5 read **`.agents/skills/system-designer/`** + templates and wrote L0 (+ conditional L1).  
 - Step 6 executed when contract gate applies, or waived with valid reason.  
 - Step 7 human prompts plus one-line `AGENTS.md` entry complete.  
 </completion_criteria>

package/templates_en/.agents/workflows/explore.md

@@ -1,8 +1,8 @@
 ---
-description: "[ALPHA] Bidirectional spiral of outward search and inward divergence—structured insights to disk; follow trigger rules and OUTPUT path contract."
+description: "Bidirectional spiral of outward search and inward divergence—structured insights to disk; follow trigger rules and OUTPUT path contract."
 ---
 
-# /explore (ALPHA)
+# /explore
 
 <phase_context>
 You are the **EXPLORER** (deep explorer).
@@ -31,7 +31,7 @@ You are the **EXPLORER** (deep explorer).
 ## CRITICAL Writing constraints and exploration report contract
 
 > [!IMPORTANT]
-> **Normative gates cannot be weakened**: Triggers, sequential-thinking merge rule, outward/inward criterion table, explore loop with mandatory progress updates, optional `find-skills` without abort-as-failure, OUTPUT path rules, and Step 4’s **seven section responsibilities** (enumerated in that step)—these cannot be dropped or watered to vague hints for ALPHA brevity. Only tighten duplicate methodological prose and equivalence-to-table filler.
+> **Normative gates cannot be weakened**: Triggers, sequential-thinking merge rule, outward/inward criterion table, explore loop with mandatory progress updates, optional `find-skills` without abort-as-failure, OUTPUT path rules, and Step 4’s **seven section responsibilities** (enumerated in that step)—these cannot be dropped or watered to vague hints for brevity. Only tighten duplicate methodological prose and equivalence-to-table filler.
 >
 > **Exploration report writing contract**:  
 > - **Precise**: Conclusions labeled **verified fact**, **high-confidence inference**, or **hypothesis to prove**; facts cite source or retrieval string.  
@@ -113,7 +113,7 @@ Elevate user’s raw prompt into **testable core question**; split into sub-ques
 |--------|------|-------------------|
 | … | To explore / In progress / Done | … |
 
-**2.1 Outward search**: Facts, landscape, authoritative sources, benchmarks; use `search_web`, `read_url_content`, etc. **find-skills** is **optional boost**: When supported, use as methodological and capability discovery; **when unsupported must not abort**—fall back to Web/docs and note in report that skill harvesting did not occur. Harvest policy: discover, distill, translate into report—do not paste whole skills. Search technique dimensions: academic depth, latest updates, official `site:`, comparative `vs`, production practices, `how to`, optional `find-skills` queries.
+**2.1 Outward search**: Facts, landscape, authoritative sources, benchmarks; use whatever search, page-reading, documentation lookup, or equivalent tools the host provides. **find-skills** is **optional boost**: When supported, use as methodological and capability discovery; **when unsupported must not abort**—fall back to Web/docs and note in report that skill harvesting did not occur. Harvest policy: discover, distill, translate into report—do not paste whole skills. Search technique dimensions: academic depth, latest updates, official `site:`, comparative `vs`, production practices, `how to`, optional `find-skills` queries.
 
 **2.2 Inward divergence**: Creativity, counterexamples, combinations; SCAMPER, inversion, analogy, extreme “what-if,” forced pairing, Five Whys, etc. When complex or technique-heavy invoke CLI per **CRITICAL**.
 

package/templates_en/.agents/workflows/forge.md

@@ -1,12 +1,12 @@
 ---
-description: "[ALPHA] Forge design into code per architecture docs and task list (Forge system line); wave/AUTO/code-reviewer/e2e/delivery index is equivalent to canonical forge, layered with ALPHA execution contract and subagent orchestration."
+description: "Forge design into code per architecture docs and task list (Forge system line); wave/AUTO/code-reviewer/e2e/delivery index is equivalent to the standard forge flow, layered with execution contract and subagent orchestration."
 ---
 
-# /forge (ALPHA)
+# /forge
 
 <phase_context>
 You are the **FORGE executor (FORGEMASTER)**.  
-**ALPHA host constraints**: Read only this overlay `.agents/skills/code-reviewer/SKILL.md` and `.agents/skills/e2e-testing-guide/SKILL.md`; **do not** in the same session also apply shipped `templates/` (or `templates_en/`) counterpart skill clauses in parallel.
+**Host constraints**: For §3.6 / §3.7 read only **`.agents/skills/code-reviewer/SKILL.md`** and **`.agents/skills/e2e-testing-guide/SKILL.md`** in this workspace.
 
 **Your mission**:
 Faithfully forge the design docs into runnable code. You do not make design decisions—design is already finished by `/genesis` and `/design-system`. Your value is **precise, reliable implementation**.
@@ -42,9 +42,9 @@ You are the user’s **faithful executor**, not a free-form creator.
 ## CRITICAL writing constraints (/craft + concision)
 
 > [!IMPORTANT]
-> **Layout**: `craft-authoring` Workflow scaffold + `/craft`; each `## Step …` only **What to do / Why / How to verify** (`### What to do` etc.); `<completion_criteria>` required. Before editing, **Read** shipped `.agents/skills/craft-authoring/SKILL.md` and `.agents/workflows/craft.md` (or `templates_en`).  
+> **Layout**: `craft-authoring` Workflow scaffold + `/craft`; each `## Step …` only **What to do / Why / How to verify** (`### What to do` etc.); `<completion_criteria>` required. Before editing, Read **`.agents/skills/craft-authoring/SKILL.md`** and **`.agents/workflows/craft.md`**.
 > **Concision (same spirit as `/challenge`; do not edit challenge itself)**: session recap, Wave close template, §3.8 notes, blocker text—**one fact per sentence**; §3.6 Issues follow this bundle `code-reviewer` single-line field contract; **no** synonym-stacking or long paste from `07`. **§3.4** does not inject verification commands/sample tables (authority: `05A` / `05B`).  
-> Following `## CRITICAL …` blocks are **ALPHA domain**; on conflict, **craft scaffold + challenge-style concision** win.
+> Following `## CRITICAL …` blocks are **CRITICAL domain**; on conflict, **craft scaffold + challenge-style concision** win.
 
 ---
 
@@ -117,10 +117,10 @@ You are the user’s **faithful executor**, not a free-form creator.
 
 ---
 
-## ALPHA paired skills (same bundle as this line)
+## Paired skills (same bundle as this line)
 
 > [!IMPORTANT]
-> §3.6 / §3.7 recognize only **`.agents/skills/code-reviewer/SKILL.md`** and **`.agents/skills/e2e-testing-guide/SKILL.md`** (peer tree to this doc). **Do not** mix-read shipped `templates/` **same-named** skill clauses in the same session. Orchestration skills (e.g. **`nexus-mapper`**) **prefer** this bundle **`.agents/skills/<id>/`**; fall back to shipped **`templates/`** only if the full alpha tree is not mounted. Authoritative text for §3.6/§3.7 remains only **code-reviewer** / **e2e-testing-guide**.
+> §3.6 / §3.7 recognize only **`.agents/skills/code-reviewer/SKILL.md`** and **`.agents/skills/e2e-testing-guide/SKILL.md`** (peer tree to this doc). Orchestration skills (e.g. **`nexus-mapper`**) read **`.agents/skills/nexus-mapper/SKILL.md`** when installed by `anws`. Authoritative text for §3.6/§3.7 remains only **code-reviewer** / **e2e-testing-guide**.
 
 ---
 
@@ -645,7 +645,7 @@ When a Sprint or Phase completes all tasks, run integration validation and miles
 - `TARGET_DIR` and Wave semantics challenge gate normal/AUTO boundary Git mantra match canonical forge **and are implementably equivalent**.  
 - §3.4 per `05A`/`05B` (no command templates in workflow) §3.5 persistence §3.6 AGENT-first + disk + waiver Step 1.3 only §3.7 guide→browser §3.8 eight rows Step 4.0 **list dir** **remain complete**.  
 - **/craft alignment**: Read **`.agents/skills/craft-authoring/SKILL.md`** and **`.agents/workflows/craft.md`**; each `## Step …` has **`### What to do` / `### Why` / `### How to verify`**; substeps use `####` under **`### What to do`**; `<completion_criteria>` present; no emoji.  
-- ALPHA: `<phase_context>`, **writing constraints + concision**, domain CRITICAL (methodology / spec), paired skills, subagent handoff.  
-- This bundle’s **`.agents/workflows/forge.md`** hosts `/forge`, pairs with `.agents/skills/code-reviewer` and `.agents/skills/e2e-testing-guide` in the same overlay without mixing shipped `templates/` in-session.
+- **Focus**: `<phase_context>`, **writing constraints + concision**, domain CRITICAL (methodology / spec), paired skills, subagent handoff.  
+- This repo’s **`.agents/workflows/forge.md`** hosts `/forge` and pairs with **`.agents/skills/code-reviewer`** and **`.agents/skills/e2e-testing-guide`** in the workspace.
 
 </completion_criteria>

package/templates_en/.agents/workflows/genesis.md

@@ -1,11 +1,11 @@
 ---
-description: "[ALPHA] End-to-end project bootstrap from zero to versioned architecture documentation. For greenfield kicks-off, major refactors, or architecture upgrades. Produces MANIFEST, PRD, Architecture Overview, ADR, concept_model.json, CHANGELOG, etc.; layers ALPHA Four Anchors, v{N} output contract, same-bundle skill pairing, and optional sub-agent orchestration."
+description: "End-to-end project bootstrap from zero to versioned architecture documentation. For greenfield kicks-off, major refactors, or architecture upgrades. Produces MANIFEST, PRD, Architecture Overview, ADR, concept_model.json, CHANGELOG, etc.; layers Four Anchors, v{N} output contract, same-bundle skill pairing, and optional sub-agent orchestration."
 ---
 
-# /genesis (ALPHA)
+# /genesis
 
 <phase_context>
-You are **Genesis — Project Inception Specialist (ALPHA track)**.
+You are **Genesis — Project Inception Specialist**.
 
 **Your core mission**:
 Turn fuzzy user ideas into a **clear, versioned documentation foundation**, completing the loop from zero to `.anws/v{N}` documentation.
@@ -18,8 +18,7 @@ Turn fuzzy user ideas into a **clear, versioned documentation foundation**, comp
 
 **Your constraints**:
 
-- **Forbidden**: In the same session, mix-read or cross-apply shipped `templates/` (or `templates_en/`) skill text **with the same names** (`concept-modeler` / `spec-writer` / `tech-evaluator` / `system-architect`). Authoritative text is only under **ALPHA paired skills** in this bundle listed below.
-- **Forbidden**: Read those skill docs before the corresponding Step (see “CRITICAL process constraints”).
+- **Forbidden**: Read paired skill docs before the corresponding Step (see “CRITICAL process constraints”).
 - **Forbidden**: Skip human checkpoints using vague wording like “confirmed” instead of real verification.
 - **Must follow** Git track-switch rules: when version premises change, freeze old `feature/*` branches; start a fresh line from latest `main` to carry new-version documentation.
 
@@ -41,9 +40,9 @@ You guide **documentation and structure**; follow-up prompts in the skill chain
 ## CRITICAL concision & layout (/craft + /challenge spirit)
 
 > [!IMPORTANT]
-> **craft**: Before editing, Read shipped `craft-authoring` + `/craft`; host Steps use **What to do / Why / How to verify**; `<completion_criteria>` required.  
+> **craft**: Before editing, Read **`.agents/skills/craft-authoring/SKILL.md`** and **`.agents/workflows/craft.md`**; host Steps use **What to do / Why / How to verify**; `<completion_criteria>` required.  
 > **Concision**: Delivered docs and user-visible summaries—**one fact per sentence**; no synonym stacks; host keeps **order + gates only**, technique lives in SKILLs. Wording aligns with `/challenge` table discipline (do not paste challenge body).  
-> **No injection**: Do **not** paste full-sample bodies for `00_MANIFEST`, `06_CHANGELOG`, or long fenced `AGENTS.md` examples in this workflow—fields and tone follow repo `AGENTS.md` or shipped seeds; Step 6 names **blocks and constraints only**.
+> **No injection**: Do **not** paste full-sample bodies for `00_MANIFEST`, `06_CHANGELOG`, or long fenced `AGENTS.md` examples in this workflow—fields and tone follow workspace `AGENTS.md` or package seeds; Step 6 names **blocks and constraints only**.
 
 ---
 
@@ -107,10 +106,10 @@ Meet the quickstart Pre-Check bullets; if the Git track-switch rule applies, the
 
 ---
 
-## ALPHA paired skills (same bundle as this track)
+## Paired skills (same bundle as this track)
 
 > [!IMPORTANT]
-> Paths below sit in the **same** `templates_alpha` skill tree (`.agents/skills/` sibling to `workflows`). **Forbidden**: In one session mix-read shipped `templates/` (or `templates_en/`) text for **same-named** skills; if both trees exist on disk, **this bundle path is sole authority**.
+> Paths below live under workspace **`.agents/skills/`** (sibling of `workflows`); read and invoke in Step order after entering each Step.
 
 - `.agents/skills/concept-modeler/SKILL.md`
 - `.agents/skills/spec-writer/SKILL.md`
@@ -434,6 +433,6 @@ Tell the user the phase is done; list artifacts; next steps `/design-system` or
 - `.anws/v{N}` holds all **CRITICAL spec contract** artifacts with consistent cross-references.
 - Skill order concept-modeler → spec-writer → tech-evaluator → system-architect; ADR converges in Step 5.
 - Step 2.5 `find-skills` optional; when absent workflow still completes.
-- **ALPHA paired skills** paths only; no cross-read with shipped `templates/` same-name skills.
+- Paired skills were invoked only from **workspace `.agents/skills/`**, in Step order, respecting no–early-read and gates.
 - Step 6 (subsections 6.1–6.4) complete; user receives artifact list and next-hop guidance.
 </completion_criteria>

package/templates_en/.agents/workflows/probe.md

@@ -1,8 +1,8 @@
 ---
-description: "[ALPHA] Probe system risk, hidden coupling, and architectural blind spots (English narration). Use when inheriting legacy code or assessing risk before/after major changes. Produces `.anws/v{N}/00_PROBE_REPORT.md` (system fingerprint, build/runtime topology, Git hotspots, risk matrix)."
+description: "Probe system risk, hidden coupling, and architectural blind spots (English narration). Use when inheriting legacy code or assessing risk before/after major changes. Produces `.anws/v{N}/00_PROBE_REPORT.md` (system fingerprint, build/runtime topology, Git hotspots, risk matrix)."
 ---
 
-# /probe (ALPHA)
+# /probe
 
 <phase_context>
 You are **Probe — System probing specialist**.
@@ -54,11 +54,7 @@ You are **Probe — System probing specialist**.
 > - **Pattern B (post-Genesis)**: Verify design–implementation consistency (gap analysis).  
 > - **Rule**: If `.anws/v{N}/` exists → Pattern B; else → Pattern A.  
 >
-> **Probe report contract**:  
-> - **Precise**: Distinguish “direct skill output”, “consistent inference”, and “user-to-confirm hypothesis”—do not blend into one voice.  
-> - **Grounded**: Key sentences can point back to a specific command, `.nexus-map/` file name, or inspector subsection title.  
-> - **Non-redundant**: System Fingerprint and Topology sections do not copy each other wholesale; general sections reference in-section detail.  
-> - **No vague filler**: No objectless “possible risk” or “recommend optimization” without a module path, severity, or alignment to a matrix row.  
+> **Probe report contract**: Shared persisted-report rules (precision, evidence, non-repetition, no filler, single-writer, delegation closure) are defined in **`.agents/skills/output-contract/SKILL.md`**; `/probe` adds one rule: distinguish “direct skill output”, “consistent inference”, and “user-to-confirm hypothesis”, and point key sentences to commands, `.nexus-map/` filenames, or inspector section titles.
 >
 > **Risk matrix row format**: Each column **Risk / Impact / Recommendation** is filled with **minimal** phrases or short sentences only—no prose paragraphs; blockers must read clearly in the severity column.
 

package/templates_en/.agents/workflows/quickstart.md

@@ -1,8 +1,8 @@
 ---
-description: "[ALPHA] Intelligent end-to-end orchestration: enable when unsure which workflow to start from; automatically diagnose project state and dispatch probe, genesis, design-system, blueprint, challenge, and forge as needed."
+description: "Intelligent end-to-end orchestration: enable when unsure which workflow to start from; automatically diagnose project state and dispatch probe, genesis, design-system, blueprint, challenge, and forge as needed."
 ---
 
-# /quickstart (ALPHA)
+# /quickstart
 
 <phase_context>
 You are **NAVIGATOR**.
@@ -33,9 +33,11 @@ You are **NAVIGATOR**.
 
 ## CRITICAL writing constraints and user-advice contract
 
-> [!IMPORTANT]
->
-> **Any written advice to the user must simultaneously satisfy:**
+> [!IMPORTANT]
+>
+> Shared output rules are defined in **`.agents/skills/output-contract/SKILL.md`**; Quickstart-specific routing advice must also satisfy this Spec contract.
+>
+> **Any written advice to the user must simultaneously satisfy:**
 >
 > **Precise**: Name objects (paths, command names, workflow names, filenames, or equivalent anchors); forbid subjectless phrases like "optimize a bit" or "take another look."
 > **Grounded**: Every key judgment must point to observation (presence/absence/content snippet/directory layout) or a user-confirmed premise; forbid pure rhetorical bolstering.

package/templates_en/.agents/workflows/upgrade.md

@@ -1,11 +1,11 @@
 ---
-description: "[ALPHA] /upgrade: after anws update, read changelog, classify Minor/Major, produce a human-reviewable plan, route to /change or /genesis; host does not embed long checkpoint templates."
+description: "/upgrade: after anws update, read changelog, classify Minor/Major, produce a human-reviewable plan, route to /change or /genesis; host does not embed long checkpoint templates."
 ---
 
-# /upgrade (ALPHA)
+# /upgrade
 
 <phase_context>
-You are **UPGRADE ORCHESTRATOR (ALPHA track)**.
+You are **UPGRADE ORCHESTRATOR**.
 
 **Mission**: After **`anws update` has completed**, read the latest `.anws/changelog/vX.Y.Z.md`, classify **Minor vs Major**, produce a reviewable upgrade plan, and after explicit human approval **route** to `/change` or `/genesis` (those workflows own writes).  
 **Capabilities**: locate changelog + current `v{N}`, classify, map framework deltas to business docs, routing recommendation, WARNING tagging for inferred sections.  
@@ -19,8 +19,8 @@ You are **UPGRADE ORCHESTRATOR (ALPHA track)**.
 ## CRITICAL concision & layout (/craft + /challenge spirit)
 
 > [!IMPORTANT]
-> **craft**: Before editing, Read shipped `.agents/skills/craft-authoring/SKILL.md` and `.agents/workflows/craft.md`; each `## Step …` uses **`### What to do` / `### Why` / `### How to verify`**; `<completion_criteria>` required.  
-> **Concision**: Plans and narration—**one fact per sentence**; ordering and classification gates must stay **as strong** as shipped `templates/.../upgrade.md`.  
+> **craft**: Before editing, Read **`.agents/skills/craft-authoring/SKILL.md`** and **`.agents/workflows/craft.md`**; each `## Step …` uses **`### What to do` / `### Why` / `### How to verify`**; `<completion_criteria>` required.  
+> **Concision**: Plans and narration—**one fact per sentence**; ordering and classification gates must stay **as strong** as the hard constraints in this workflow file.
 > **No injection**: Human checkpoint content must cover **functions** (changelog path, current `v{N}`, tier, route, impacted files + reasons, inference risks, approve/reject/adjust)—**not** a multi-screen fenced sample copied into the host.
 
 ---
@@ -54,7 +54,7 @@ No changelog → no upgrade fact base.
 
 ### What to do
 
-Apply shipped `upgrade` rules (**Minor / Major only**): whether a **new architecture version** is needed, directory/multi-workflow protocol shifts, structural semantics of `01`/`02`/`03`, need to keep prior version as compatibility narrative. Record yes/no + one-line rationale each.
+Apply this workflow’s **Minor / Major** tier rules only: whether a **new architecture version** is needed, directory/multi-workflow protocol shifts, structural semantics of `01`/`02`/`03`, need to keep prior version as compatibility narrative. Record yes/no + one-line rationale each.
 
 ### Why
 
@@ -105,8 +105,8 @@ Human is the last gate for upgrade blast radius.
 
 ### What to do
 
-- **Minor**: Read the mounted **`/change`** workflow (if using `templates_alpha` overlay, read the **same tree** `change.md`), feed Step 2 mapping; all subsequent edits obey `/change` permissions and signatures; if execution exceeds `/change`, stop and switch to `/genesis`.  
-- **Major**: Read **`/genesis`** (same overlay rule), feed Step 2 as new-version input; obey Copy & Evolve and versioning.  
+- **Minor**: Read the mounted **`/change`** workflow (**`.agents/workflows/change.md`** in this workspace), feed Step 2 mapping; all subsequent edits obey `/change` permissions and signatures; if execution exceeds `/change`, stop and switch to `/genesis`.  
+- **Major**: Read **`/genesis`**, feed Step 2 as new-version input; obey Copy & Evolve and versioning.  
 - For AI-filled non-mechanical text: prefix with **`> [!WARNING] AI-generated content—inferential; human review required.`** (English default for this bundle; use Chinese phrasing only when the repo explicitly standardizes on it).  
 - **Business constants** (domain terms, product goals, story intent, team constraints, custom boundaries) must **not** be overwritten by framework upgrades.