@chinhae/atw-cli 0.4.0 → 0.6.0

package/README.md

@@ -25,7 +25,7 @@ by default.
 | --- | --- | --- |
 | For | Building software — whether or not you are an engineer | Work that is not code: writing, research, organizing material, planning |
 | The AI follows | Six stages, four stops, tickets, review by sub-agents — see [How It Works](#how-it-works) | Talk it through → write it down → do it → check it, with two stops |
-| Installed | 28 skills, the `/atw-continue` and `/atw-finish-work` commands, the `atw-implement-agent` and `atw-review` sub-agents, `.atw/spec/` by package and layer | 6 skills and one conventions file |
+| Installed | 29 skills, the `/atw-continue` and `/atw-finish-work` commands, the `atw-implement-agent` and `atw-review` sub-agents, `.atw/spec/` by package and layer | 6 skills and one conventions file |
 | Noob mode, for someone who never chose | Off | On |
 
 A project with no `mode:` line is a `dev` project, so one set up before modes
@@ -113,7 +113,7 @@ Dropped:
   a task?" question and no `/atw-implement` to run. The two stops left are the
   two above: confirming what was written down, and accepting the result. You
   never type a command to move the work along.
-- **22 of the 28 skills.** The six that stay: `atw-interview`, `atw-research`,
+- **23 of the 29 skills.** The six that stay: `atw-interview`, `atw-research`,
   `atw-session-insight` and `atw-noob-mode`, which the AI also uses on its own,
   and `/atw-askme` and `/atw-handoff`, which start only when you type them.
 - **The `/atw-continue` and `/atw-finish-work` commands.** `/atw-start` stays on
@@ -161,7 +161,7 @@ the repo and multi-platform setup hold in `general` mode as well.
 | **A task record with six stages** | Every task moves through `discover → specify → slice → implement → accept → completed`. The stage lives in `task.json`, and a per-turn hook injects that stage's rules into the session — so the AI knows where it is without being told again. |
 | **Four stops, all yours** | Everywhere else the AI advances on its own. At four points it must stop and wait for you: creating the task, confirming the spec, starting each ticket, and accepting the result. |
 | **Auto-injected specs** | Write conventions once in `.atw/spec/`, then let ATW inject the relevant context into each session instead of repeating yourself. |
-| **One ticket at a time** | Work is sliced into tickets with explicit dependencies. Exactly one is `doing`; two at once is a broken state, not a choice. The one exception is a whole-spec run you start yourself with `/atw-implement-spec`. |
+| **One ticket at a time** | Work is sliced into tickets with explicit dependencies. Exactly one is `doing`; two at once is a broken state, not a choice. The one exception is a parallel whole-spec run you start yourself with `/atw-implement-spec`; `/atw-implement-all` stays serial. |
 | **Project memory** | Journals in `.atw/workspace/` preserve what happened last time, so each new session starts with real context. `atw mem` searches conversation history across hosts. |
 | **Team-shared standards** | Specs and tasks live in the repo. Workspace journals stay per-developer, so two people on the same repo don't collide. |
 | **Multi-platform setup** | Bring the same ATW structure to 22 AI coding platforms instead of rebuilding your workflow per tool. |
@@ -290,7 +290,7 @@ Outside these four, the AI advances stages on its own. It does not stop to ask
 | --- | --- |
 | Before a task is created | Does this work deserve a record |
 | After `prd.md` is written | Is the spec right |
-| Before implementation starts | You run `/atw-implement` per ticket, or `/atw-implement-spec` once for the whole spec; the AI cannot invoke either |
+| Before implementation starts | You run `/atw-implement` per ticket, `/atw-implement-spec` once for the whole spec in parallel, or `/atw-implement-all` once for the whole spec serially; the AI cannot invoke any of the three |
 | Before archiving | "This is done" |
 
 ## What lands in your repo
@@ -332,7 +332,7 @@ actually does. `native` is the workflow that comes with the project's mode: the
 
 ## Skills and sub-agents
 
-In `dev` mode, 28 skills install into every configured platform; in `general`
+In `dev` mode, 29 skills install into every configured platform; in `general`
 mode, six do (see [Two modes](#two-modes)). The ones you reach for daily in
 `dev`:
 
@@ -345,6 +345,7 @@ mode, six do (see [Two modes](#two-modes)). The ones you reach for daily in
 | `/atw-tickets` | slice a confirmed spec into tickets |
 | `/atw-implement` | run one ticket's full chain — you invoke it, the AI can't |
 | `/atw-implement-spec` | run every ticket of a sliced spec in one parallel run on an integration branch, reviewed once at the end — you invoke it, the AI can't |
+| `/atw-implement-all` | run every ticket of a sliced spec in one serial run in place on the current branch, reviewed per ticket; `--max N` stops cleanly after N tickets and running it again resumes — you invoke it, the AI can't |
 | `/atw-diagnosing-bugs` | the same bug got fixed more than once |
 | `/atw-update-spec` | promote a learning back into `.atw/spec/` |
 | `/atw-channel` | multi-agent collaboration over a durable local event log |

package/dist/migrations/manifests/0.5.0.json

@@ -0,0 +1,9 @@
+{
+  "version": "0.5.0",
+  "description": "/atw-implement-all implements a whole sliced spec in one serial run, with a review per ticket. A ticket marked ready-for-human is no longer implemented by the AI without the user's explicit say. The acceptance check now ticks the criteria it verified and commits them.",
+  "breaking": false,
+  "recommendMigrate": false,
+  "changelog": "/atw-implement-all, a third way through stop ③. Until now a sliced spec was implemented either one ticket at a time, with the user running /atw-implement for each, or all at once in parallel with /atw-implement-spec and one review at the end. /atw-implement-all is run once by the user and works the tickets serially: the main session takes the lowest-numbered ticket on the frontier, claims it with the plain tickets.py claim, dispatches one implementer sub-agent that works in place on the current branch and commits there, reviews that ticket with atw-code-review against the base recorded at claim time, has findings fixed once and re-checks only what was fixed, writes spec updates back, marks the ticket done and commits the state — then takes the next ticket. No worktrees, no integration branch, and never more than one ticket at doing. --max N stops cleanly after N tickets. The run comes back to the user when an implementer meets an ambiguity that would change the result, when a finding is still open after the one re-check, when a ticket cannot be finished as written, or when only tickets marked for a person are left. Stopping needs no cleanup: every closed ticket is already written back and committed, a ticket left at doing is the breakpoint, and running the same command again resumes from it. Like the other two ways, only the user can start it, and it needs a platform that dispatches sub-agents. A dev project now installs 29 skills instead of 28. .atw/workflow.md gains step 2.8 for the run, and /atw-continue names all three ways at stop ③. Tickets for a person. The Status: line on a ticket used to be a fixed placeholder; it now carries a decision. /atw-tickets marks a ticket ready-for-human when a person must do it — it needs an external account, a manual test pass, or a design or legal decision. /atw-implement reads that line before touching code: it says the ticket is marked for a person, quotes the reason the ticket gives, and asks the user to either do it themselves or explicitly authorize the AI to do it in their place; an authorization is written into the commit the run makes. /atw-implement-all never dispatches such a ticket. tickets.py does not read the field, so the frontier and tickets.py claim behave as before. Acceptance leaves a record and a clean tree. During the acceptance check the AI ticks each criterion's checkbox in prd.md and in the ticket that carried it as the criterion checks out, and commits the ticks once (chore(task): <task> acceptance check) before asking the user to accept; nothing earlier in the chain ticks them. When the last ticket closes and the task moves to accept, the task.json change is committed as well, so the acceptance check starts from a clean tree.",
+  "migrations": [],
+  "notes": "No migration required. atw update deletes and renames nothing. In a dev project it adds one skill, atw-implement-all, to every configured platform, and updates these templates: .atw/workflow.md, .atw/config.yaml (one comment; no setting changes), the atw-implement, atw-tickets, atw-noob-mode and atw-init-repo skills, /atw-continue in each platform's own form, the inject-workflow-state.py hook on the platforms that install it, and SNOW.md on Snow. In a general project it adds nothing and updates the atw-noob-mode skill, the same hook and the same comment in .atw/config.yaml; the mode: line is kept. They update as Template updated where the project left them untouched; where a project edited them locally, atw update asks before replacing. Tickets written before this release carry Status: ready-for-agent, the value tickets.py writes, so /atw-implement does not stop on them."
+}

package/dist/migrations/manifests/0.6.0.json

@@ -0,0 +1,442 @@
+{
+  "version": "0.6.0",
+  "description": "atw-ui and atw-prototype are brought up to oil-ui 0.22.1. atw-prototype names the product's category, takes benchmarks apart and offers three directions in words before it builds any screen. atw-ui ships a screenshot tool and a separate manual for the review sub-agent. Three reference files are retired, and atw update removes them.",
+  "breaking": false,
+  "recommendMigrate": false,
+  "changelog": "The two interface skills, atw-prototype and atw-ui, are synced to oil-ui 0.22.1, the project they were forked from on 2026-10-01. Upstream's paid-version prompts, update check and first-use recommendations are not included. atw-prototype, choosing a direction. Stage one now starts by naming the product's category and two or three benchmarks, and taking the benchmarks apart from real screens saved under the task's references/. When no real screen can be fetched, the direction card says so and marks font, colour and main visual as not yet verified. The AI then writes three directions in three or four lines each, with a recommendation, sends that and stops. A direction picked from the text is the only one carried forward: stage one builds no first screen and no comparison page for it. Three first screens side by side are built only when the user wants to see them, and layout comparisons go words first too. When the user says to decide, or nobody is there, the three screens are still built for the record and the AI writes down why it chose one. Stage one is skipped only when ui-direction.md already exists or the user named one complete direction. Colour for each direction is derived in four steps from the product itself, and directions are no longer told apart by light and dark. The first screen is planned differently for a persuasion page and for a content or workspace page, where the first screen is the first row of content. The direction card gains columns for benchmarks and trade-offs, the form of each section, control grammar, and motion. The eight skeletons for persuasion pages move to a new file, references/direction-persuasion.md. atw-ui, scope and motion. Requests in an existing project are split three ways: polish the UI, change a flow, add a feature. A flow change or a new feature keeps the visual style the project has and does not go through direction exploration. Polishing a single component has its own path: one direction, with the visual protagonist chosen first. A new interface, or one whose operating flow changed, must have three baseline motions: feedback on the main action, where a state change comes from, and the first entrance. Two new guides: references/scroll-narrative.md, required reading for landing, brand, launch and exhibition pages, and references/play.md for small games, draws and controls that depend on feel. media.md takes upstream's structure and absorbs imagery.md; visual-language.md and layout-and-viewport.md follow upstream's current text. atw-ui, screenshot tool. The skill ships scripts/shoot.mjs and a guide to it, references/tools.md. One command takes the evidence set before review and before delivery: state shots, a side-by-side, a version with the text masked, a 2x shot and a screen recording. Each shot also reports default-pattern hints read from the page's styles, in two groups: readability problems to fix, and patterns to either change or justify in the delivery notes. The tool can compare a page against a reference image and draw numbered boxes on elements. It needs Node 22 or later and a local Chrome, Chromium or Edge; without them the skill falls back to the host's browser tool and hands over the same evidence. atw-ui, review. The review protocol is now two files. references/visual-review.md is the dispatch protocol the main agent reads: when to dispatch a reviewer and in which mode, what to hand over, and how to act on the feedback. references/reviewer-manual.md is new and is the only file the review sub-agent reads: a three-second test, deductions for model-default patterns, a motion check, three uplift items, a 'redo' line and a 'keep' line, and a table of thresholds for scores 1 to 10. Its second section covers polishing an existing interface against the project's own design-system.md, in one round and without a score. Inside /atw-implement the pipeline's review step still dispatches the reviewer, not the main agent. One copy of shared documents. atw-prototype no longer carries its own visual-language.md and visual-review.md. Its documents link to atw-ui's copies by relative path; every platform installs the two skills side by side under the same skills directory.",
+  "migrations": [
+    {
+      "type": "safe-file-delete",
+      "from": ".agent/skills/atw-prototype/references/visual-language.md",
+      "description": "atw-prototype reads atw-ui's visual-language.md as of 0.6.0",
+      "allowed_hashes": [
+        "76fbb6bc5624fb30896347a4233b2e18944f2b9c6391495fc2ae154c25ca122f"
+      ]
+    },
+    {
+      "type": "safe-file-delete",
+      "from": ".agent/skills/atw-prototype/references/visual-review.md",
+      "description": "atw-prototype reads atw-ui's visual-review.md as of 0.6.0",
+      "allowed_hashes": [
+        "4ea6413171b1b19f1af593fa282bb772375b22b2e2fcfafa3912514d59a4b7b1"
+      ]
+    },
+    {
+      "type": "safe-file-delete",
+      "from": ".agent/skills/atw-ui/references/imagery.md",
+      "description": "Folded into media.md in 0.6.0",
+      "allowed_hashes": [
+        "6454e931f0a3428088b5158a7c5e5626f1722febf3b550337b209eccc90ba09b"
+      ]
+    },
+    {
+      "type": "safe-file-delete",
+      "from": ".agents/skills/atw-prototype/references/visual-language.md",
+      "description": "atw-prototype reads atw-ui's visual-language.md as of 0.6.0",
+      "allowed_hashes": [
+        "76fbb6bc5624fb30896347a4233b2e18944f2b9c6391495fc2ae154c25ca122f"
+      ]
+    },
+    {
+      "type": "safe-file-delete",
+      "from": ".agents/skills/atw-prototype/references/visual-review.md",
+      "description": "atw-prototype reads atw-ui's visual-review.md as of 0.6.0",
+      "allowed_hashes": [
+        "4ea6413171b1b19f1af593fa282bb772375b22b2e2fcfafa3912514d59a4b7b1"
+      ]
+    },
+    {
+      "type": "safe-file-delete",
+      "from": ".agents/skills/atw-ui/references/imagery.md",
+      "description": "Folded into media.md in 0.6.0",
+      "allowed_hashes": [
+        "6454e931f0a3428088b5158a7c5e5626f1722febf3b550337b209eccc90ba09b"
+      ]
+    },
+    {
+      "type": "safe-file-delete",
+      "from": ".claude/skills/atw-prototype/references/visual-language.md",
+      "description": "atw-prototype reads atw-ui's visual-language.md as of 0.6.0",
+      "allowed_hashes": [
+        "76fbb6bc5624fb30896347a4233b2e18944f2b9c6391495fc2ae154c25ca122f"
+      ]
+    },
+    {
+      "type": "safe-file-delete",
+      "from": ".claude/skills/atw-prototype/references/visual-review.md",
+      "description": "atw-prototype reads atw-ui's visual-review.md as of 0.6.0",
+      "allowed_hashes": [
+        "4ea6413171b1b19f1af593fa282bb772375b22b2e2fcfafa3912514d59a4b7b1"
+      ]
+    },
+    {
+      "type": "safe-file-delete",
+      "from": ".claude/skills/atw-ui/references/imagery.md",
+      "description": "Folded into media.md in 0.6.0",
+      "allowed_hashes": [
+        "6454e931f0a3428088b5158a7c5e5626f1722febf3b550337b209eccc90ba09b"
+      ]
+    },
+    {
+      "type": "safe-file-delete",
+      "from": ".codebuddy/skills/atw-prototype/references/visual-language.md",
+      "description": "atw-prototype reads atw-ui's visual-language.md as of 0.6.0",
+      "allowed_hashes": [
+        "76fbb6bc5624fb30896347a4233b2e18944f2b9c6391495fc2ae154c25ca122f"
+      ]
+    },
+    {
+      "type": "safe-file-delete",
+      "from": ".codebuddy/skills/atw-prototype/references/visual-review.md",
+      "description": "atw-prototype reads atw-ui's visual-review.md as of 0.6.0",
+      "allowed_hashes": [
+        "4ea6413171b1b19f1af593fa282bb772375b22b2e2fcfafa3912514d59a4b7b1"
+      ]
+    },
+    {
+      "type": "safe-file-delete",
+      "from": ".codebuddy/skills/atw-ui/references/imagery.md",
+      "description": "Folded into media.md in 0.6.0",
+      "allowed_hashes": [
+        "6454e931f0a3428088b5158a7c5e5626f1722febf3b550337b209eccc90ba09b"
+      ]
+    },
+    {
+      "type": "safe-file-delete",
+      "from": ".cursor/skills/atw-prototype/references/visual-language.md",
+      "description": "atw-prototype reads atw-ui's visual-language.md as of 0.6.0",
+      "allowed_hashes": [
+        "76fbb6bc5624fb30896347a4233b2e18944f2b9c6391495fc2ae154c25ca122f"
+      ]
+    },
+    {
+      "type": "safe-file-delete",
+      "from": ".cursor/skills/atw-prototype/references/visual-review.md",
+      "description": "atw-prototype reads atw-ui's visual-review.md as of 0.6.0",
+      "allowed_hashes": [
+        "4ea6413171b1b19f1af593fa282bb772375b22b2e2fcfafa3912514d59a4b7b1"
+      ]
+    },
+    {
+      "type": "safe-file-delete",
+      "from": ".cursor/skills/atw-ui/references/imagery.md",
+      "description": "Folded into media.md in 0.6.0",
+      "allowed_hashes": [
+        "6454e931f0a3428088b5158a7c5e5626f1722febf3b550337b209eccc90ba09b"
+      ]
+    },
+    {
+      "type": "safe-file-delete",
+      "from": ".devin/skills/atw-prototype/references/visual-language.md",
+      "description": "atw-prototype reads atw-ui's visual-language.md as of 0.6.0",
+      "allowed_hashes": [
+        "76fbb6bc5624fb30896347a4233b2e18944f2b9c6391495fc2ae154c25ca122f"
+      ]
+    },
+    {
+      "type": "safe-file-delete",
+      "from": ".devin/skills/atw-prototype/references/visual-review.md",
+      "description": "atw-prototype reads atw-ui's visual-review.md as of 0.6.0",
+      "allowed_hashes": [
+        "4ea6413171b1b19f1af593fa282bb772375b22b2e2fcfafa3912514d59a4b7b1"
+      ]
+    },
+    {
+      "type": "safe-file-delete",
+      "from": ".devin/skills/atw-ui/references/imagery.md",
+      "description": "Folded into media.md in 0.6.0",
+      "allowed_hashes": [
+        "6454e931f0a3428088b5158a7c5e5626f1722febf3b550337b209eccc90ba09b"
+      ]
+    },
+    {
+      "type": "safe-file-delete",
+      "from": ".factory/skills/atw-prototype/references/visual-language.md",
+      "description": "atw-prototype reads atw-ui's visual-language.md as of 0.6.0",
+      "allowed_hashes": [
+        "76fbb6bc5624fb30896347a4233b2e18944f2b9c6391495fc2ae154c25ca122f"
+      ]
+    },
+    {
+      "type": "safe-file-delete",
+      "from": ".factory/skills/atw-prototype/references/visual-review.md",
+      "description": "atw-prototype reads atw-ui's visual-review.md as of 0.6.0",
+      "allowed_hashes": [
+        "4ea6413171b1b19f1af593fa282bb772375b22b2e2fcfafa3912514d59a4b7b1"
+      ]
+    },
+    {
+      "type": "safe-file-delete",
+      "from": ".factory/skills/atw-ui/references/imagery.md",
+      "description": "Folded into media.md in 0.6.0",
+      "allowed_hashes": [
+        "6454e931f0a3428088b5158a7c5e5626f1722febf3b550337b209eccc90ba09b"
+      ]
+    },
+    {
+      "type": "safe-file-delete",
+      "from": ".github/skills/atw-prototype/references/visual-language.md",
+      "description": "atw-prototype reads atw-ui's visual-language.md as of 0.6.0",
+      "allowed_hashes": [
+        "76fbb6bc5624fb30896347a4233b2e18944f2b9c6391495fc2ae154c25ca122f"
+      ]
+    },
+    {
+      "type": "safe-file-delete",
+      "from": ".github/skills/atw-prototype/references/visual-review.md",
+      "description": "atw-prototype reads atw-ui's visual-review.md as of 0.6.0",
+      "allowed_hashes": [
+        "4ea6413171b1b19f1af593fa282bb772375b22b2e2fcfafa3912514d59a4b7b1"
+      ]
+    },
+    {
+      "type": "safe-file-delete",
+      "from": ".github/skills/atw-ui/references/imagery.md",
+      "description": "Folded into media.md in 0.6.0",
+      "allowed_hashes": [
+        "6454e931f0a3428088b5158a7c5e5626f1722febf3b550337b209eccc90ba09b"
+      ]
+    },
+    {
+      "type": "safe-file-delete",
+      "from": ".grok/skills/atw-prototype/references/visual-language.md",
+      "description": "atw-prototype reads atw-ui's visual-language.md as of 0.6.0",
+      "allowed_hashes": [
+        "76fbb6bc5624fb30896347a4233b2e18944f2b9c6391495fc2ae154c25ca122f"
+      ]
+    },
+    {
+      "type": "safe-file-delete",
+      "from": ".grok/skills/atw-prototype/references/visual-review.md",
+      "description": "atw-prototype reads atw-ui's visual-review.md as of 0.6.0",
+      "allowed_hashes": [
+        "4ea6413171b1b19f1af593fa282bb772375b22b2e2fcfafa3912514d59a4b7b1"
+      ]
+    },
+    {
+      "type": "safe-file-delete",
+      "from": ".grok/skills/atw-ui/references/imagery.md",
+      "description": "Folded into media.md in 0.6.0",
+      "allowed_hashes": [
+        "6454e931f0a3428088b5158a7c5e5626f1722febf3b550337b209eccc90ba09b"
+      ]
+    },
+    {
+      "type": "safe-file-delete",
+      "from": ".kilocode/skills/atw-prototype/references/visual-language.md",
+      "description": "atw-prototype reads atw-ui's visual-language.md as of 0.6.0",
+      "allowed_hashes": [
+        "76fbb6bc5624fb30896347a4233b2e18944f2b9c6391495fc2ae154c25ca122f"
+      ]
+    },
+    {
+      "type": "safe-file-delete",
+      "from": ".kilocode/skills/atw-prototype/references/visual-review.md",
+      "description": "atw-prototype reads atw-ui's visual-review.md as of 0.6.0",
+      "allowed_hashes": [
+        "4ea6413171b1b19f1af593fa282bb772375b22b2e2fcfafa3912514d59a4b7b1"
+      ]
+    },
+    {
+      "type": "safe-file-delete",
+      "from": ".kilocode/skills/atw-ui/references/imagery.md",
+      "description": "Folded into media.md in 0.6.0",
+      "allowed_hashes": [
+        "6454e931f0a3428088b5158a7c5e5626f1722febf3b550337b209eccc90ba09b"
+      ]
+    },
+    {
+      "type": "safe-file-delete",
+      "from": ".kiro/skills/atw-prototype/references/visual-language.md",
+      "description": "atw-prototype reads atw-ui's visual-language.md as of 0.6.0",
+      "allowed_hashes": [
+        "76fbb6bc5624fb30896347a4233b2e18944f2b9c6391495fc2ae154c25ca122f"
+      ]
+    },
+    {
+      "type": "safe-file-delete",
+      "from": ".kiro/skills/atw-prototype/references/visual-review.md",
+      "description": "atw-prototype reads atw-ui's visual-review.md as of 0.6.0",
+      "allowed_hashes": [
+        "4ea6413171b1b19f1af593fa282bb772375b22b2e2fcfafa3912514d59a4b7b1"
+      ]
+    },
+    {
+      "type": "safe-file-delete",
+      "from": ".kiro/skills/atw-ui/references/imagery.md",
+      "description": "Folded into media.md in 0.6.0",
+      "allowed_hashes": [
+        "6454e931f0a3428088b5158a7c5e5626f1722febf3b550337b209eccc90ba09b"
+      ]
+    },
+    {
+      "type": "safe-file-delete",
+      "from": ".omp/skills/atw-prototype/references/visual-language.md",
+      "description": "atw-prototype reads atw-ui's visual-language.md as of 0.6.0",
+      "allowed_hashes": [
+        "76fbb6bc5624fb30896347a4233b2e18944f2b9c6391495fc2ae154c25ca122f"
+      ]
+    },
+    {
+      "type": "safe-file-delete",
+      "from": ".omp/skills/atw-prototype/references/visual-review.md",
+      "description": "atw-prototype reads atw-ui's visual-review.md as of 0.6.0",
+      "allowed_hashes": [
+        "4ea6413171b1b19f1af593fa282bb772375b22b2e2fcfafa3912514d59a4b7b1"
+      ]
+    },
+    {
+      "type": "safe-file-delete",
+      "from": ".omp/skills/atw-ui/references/imagery.md",
+      "description": "Folded into media.md in 0.6.0",
+      "allowed_hashes": [
+        "6454e931f0a3428088b5158a7c5e5626f1722febf3b550337b209eccc90ba09b"
+      ]
+    },
+    {
+      "type": "safe-file-delete",
+      "from": ".opencode/skills/atw-prototype/references/visual-language.md",
+      "description": "atw-prototype reads atw-ui's visual-language.md as of 0.6.0",
+      "allowed_hashes": [
+        "76fbb6bc5624fb30896347a4233b2e18944f2b9c6391495fc2ae154c25ca122f"
+      ]
+    },
+    {
+      "type": "safe-file-delete",
+      "from": ".opencode/skills/atw-prototype/references/visual-review.md",
+      "description": "atw-prototype reads atw-ui's visual-review.md as of 0.6.0",
+      "allowed_hashes": [
+        "4ea6413171b1b19f1af593fa282bb772375b22b2e2fcfafa3912514d59a4b7b1"
+      ]
+    },
+    {
+      "type": "safe-file-delete",
+      "from": ".opencode/skills/atw-ui/references/imagery.md",
+      "description": "Folded into media.md in 0.6.0",
+      "allowed_hashes": [
+        "6454e931f0a3428088b5158a7c5e5626f1722febf3b550337b209eccc90ba09b"
+      ]
+    },
+    {
+      "type": "safe-file-delete",
+      "from": ".qoder/skills/atw-prototype/references/visual-language.md",
+      "description": "atw-prototype reads atw-ui's visual-language.md as of 0.6.0",
+      "allowed_hashes": [
+        "76fbb6bc5624fb30896347a4233b2e18944f2b9c6391495fc2ae154c25ca122f"
+      ]
+    },
+    {
+      "type": "safe-file-delete",
+      "from": ".qoder/skills/atw-prototype/references/visual-review.md",
+      "description": "atw-prototype reads atw-ui's visual-review.md as of 0.6.0",
+      "allowed_hashes": [
+        "4ea6413171b1b19f1af593fa282bb772375b22b2e2fcfafa3912514d59a4b7b1"
+      ]
+    },
+    {
+      "type": "safe-file-delete",
+      "from": ".qoder/skills/atw-ui/references/imagery.md",
+      "description": "Folded into media.md in 0.6.0",
+      "allowed_hashes": [
+        "6454e931f0a3428088b5158a7c5e5626f1722febf3b550337b209eccc90ba09b"
+      ]
+    },
+    {
+      "type": "safe-file-delete",
+      "from": ".reasonix/skills/atw-prototype/references/visual-language.md",
+      "description": "atw-prototype reads atw-ui's visual-language.md as of 0.6.0",
+      "allowed_hashes": [
+        "76fbb6bc5624fb30896347a4233b2e18944f2b9c6391495fc2ae154c25ca122f"
+      ]
+    },
+    {
+      "type": "safe-file-delete",
+      "from": ".reasonix/skills/atw-prototype/references/visual-review.md",
+      "description": "atw-prototype reads atw-ui's visual-review.md as of 0.6.0",
+      "allowed_hashes": [
+        "4ea6413171b1b19f1af593fa282bb772375b22b2e2fcfafa3912514d59a4b7b1"
+      ]
+    },
+    {
+      "type": "safe-file-delete",
+      "from": ".reasonix/skills/atw-ui/references/imagery.md",
+      "description": "Folded into media.md in 0.6.0",
+      "allowed_hashes": [
+        "6454e931f0a3428088b5158a7c5e5626f1722febf3b550337b209eccc90ba09b"
+      ]
+    },
+    {
+      "type": "safe-file-delete",
+      "from": ".snow/skills/atw-prototype/references/visual-language.md",
+      "description": "atw-prototype reads atw-ui's visual-language.md as of 0.6.0",
+      "allowed_hashes": [
+        "76fbb6bc5624fb30896347a4233b2e18944f2b9c6391495fc2ae154c25ca122f"
+      ]
+    },
+    {
+      "type": "safe-file-delete",
+      "from": ".snow/skills/atw-prototype/references/visual-review.md",
+      "description": "atw-prototype reads atw-ui's visual-review.md as of 0.6.0",
+      "allowed_hashes": [
+        "4ea6413171b1b19f1af593fa282bb772375b22b2e2fcfafa3912514d59a4b7b1"
+      ]
+    },
+    {
+      "type": "safe-file-delete",
+      "from": ".snow/skills/atw-ui/references/imagery.md",
+      "description": "Folded into media.md in 0.6.0",
+      "allowed_hashes": [
+        "6454e931f0a3428088b5158a7c5e5626f1722febf3b550337b209eccc90ba09b"
+      ]
+    },
+    {
+      "type": "safe-file-delete",
+      "from": ".trae/skills/atw-prototype/references/visual-language.md",
+      "description": "atw-prototype reads atw-ui's visual-language.md as of 0.6.0",
+      "allowed_hashes": [
+        "76fbb6bc5624fb30896347a4233b2e18944f2b9c6391495fc2ae154c25ca122f"
+      ]
+    },
+    {
+      "type": "safe-file-delete",
+      "from": ".trae/skills/atw-prototype/references/visual-review.md",
+      "description": "atw-prototype reads atw-ui's visual-review.md as of 0.6.0",
+      "allowed_hashes": [
+        "4ea6413171b1b19f1af593fa282bb772375b22b2e2fcfafa3912514d59a4b7b1"
+      ]
+    },
+    {
+      "type": "safe-file-delete",
+      "from": ".trae/skills/atw-ui/references/imagery.md",
+      "description": "Folded into media.md in 0.6.0",
+      "allowed_hashes": [
+        "6454e931f0a3428088b5158a7c5e5626f1722febf3b550337b209eccc90ba09b"
+      ]
+    },
+    {
+      "type": "safe-file-delete",
+      "from": ".zcode/skills/atw-prototype/references/visual-language.md",
+      "description": "atw-prototype reads atw-ui's visual-language.md as of 0.6.0",
+      "allowed_hashes": [
+        "76fbb6bc5624fb30896347a4233b2e18944f2b9c6391495fc2ae154c25ca122f"
+      ]
+    },
+    {
+      "type": "safe-file-delete",
+      "from": ".zcode/skills/atw-prototype/references/visual-review.md",
+      "description": "atw-prototype reads atw-ui's visual-review.md as of 0.6.0",
+      "allowed_hashes": [
+        "4ea6413171b1b19f1af593fa282bb772375b22b2e2fcfafa3912514d59a4b7b1"
+      ]
+    },
+    {
+      "type": "safe-file-delete",
+      "from": ".zcode/skills/atw-ui/references/imagery.md",
+      "description": "Folded into media.md in 0.6.0",
+      "allowed_hashes": [
+        "6454e931f0a3428088b5158a7c5e5626f1722febf3b550337b209eccc90ba09b"
+      ]
+    }
+  ],
+  "notes": "No manual migration required. atw update deletes three retired files from the skills directory of every configured platform: atw-ui/references/imagery.md, atw-prototype/references/visual-language.md and atw-prototype/references/visual-review.md. A copy the project left untouched is deleted without asking; a copy that was edited is kept and listed as modified, skipped. In a dev project atw update also adds six files per skills directory (atw-ui/scripts/shoot.mjs, atw-ui/references/tools.md, reviewer-manual.md, scroll-narrative.md and play.md, and atw-prototype/references/direction-persuasion.md) and updates ten: in atw-ui, SKILL.md and references/layout-and-viewport.md, media.md, motion.md, visual-language.md and visual-review.md; in atw-prototype, SKILL.md, UI.md, references/design-direction.md and references/style-explorer.md. They update as Template updated where the project left them untouched; where a project edited them locally, atw update asks before replacing. A general project installs neither skill, so nothing in it changes. No setting in .atw/config.yaml changes, and .atw/workflow.md is the same as in 0.5.0."
+}

package/dist/templates/atw/config.yaml

@@ -114,12 +114,13 @@ channel:
 # atw-review sub-agents for the two review axes. On the per-ticket path
 # implementation is never dispatched on any platform: it runs inside
 # `/atw-implement` in the main session (`atw-implement-agent` ships only as a
-# reserved role). Only a `/atw-implement-spec` run dispatches implementers. This does
-# not rely on inherited parent transcripts: `fork_turns` remains
-# caller-controlled, while Codex's native SubagentStart hook injects task
-# context when trusted and child-side loading remains the fallback when it is
-# unavailable. Set to "inline" only to run the review axes in the main
-# session too. "sub-agent" remains a backwards-compatible alias for "auto".
+# reserved role). Only a `/atw-implement-spec` or `/atw-implement-all` run
+# dispatches implementers. This does not rely on inherited parent transcripts:
+# `fork_turns` remains caller-controlled, while Codex's native SubagentStart
+# hook injects task context when trusted and child-side loading remains the
+# fallback when it is unavailable. Set to "inline" only to run the review axes
+# in the main session too. "sub-agent" remains a backwards-compatible alias
+# for "auto".
 # Invalid explicit values safely use inline mode.
 #
 # In "auto" mode, dispatched sub-agents inherit the main session's model