2.0.0-rc.17: Lauren's eb4db2b, a skill that draws a TLA+ model as a statechart a PM can read

.claude-plugin/marketplace.json

@@ -10,7 +10,7 @@
       "name": "t3-pstack",
       "source": "./plugins/pstack",
       "description": "pstack for T3 Code: rigorous agent workflows whose panels and fan-outs run across model families through T3. Original pstack by Lauren Tan (poteto).",
-      "version": "2.0.0-rc.16"
+      "version": "2.0.0-rc.17"
     }
   ]
 }

.github/workflows/ci.yml

@@ -127,6 +127,22 @@ jobs:
       - name: Check formatting
         run: bunx prettier@3.6.2 --check watch-pr/settle.ts watch-pr/settle.test.ts watch-pr/verdicts.test.ts resolve-codex-transcript.ts
 
+  # The same step as upstream's validate-plugins.yml, on the Node it uses,
+  # which is also the oldest the installer accepts. The runner has no TLC, so
+  # the statechart tests that need it skip.
+  skill-scripts:
+    name: Skill script tests
+    runs-on: ubuntu-latest
+    steps:
+      - uses: actions/checkout@3d3c42e5aac5ba805825da76410c181273ba90b1 # v7.0.1
+        with:
+          persist-credentials: false
+      - uses: actions/setup-node@949feb2413d6458794dcd2491c4babbbce0c15c1 # v7.1.0
+        with:
+          node-version: "20"
+      - name: Test skill scripts
+        run: node --test plugins/pstack/skills/*/scripts/test/*.test.mjs
+
   shellcheck:
     name: Shell scripts
     runs-on: ubuntu-latest

CHANGES.md

@@ -2,6 +2,15 @@
 
 This file is the release changelog, with one `## <version> - <title>` entry per release, newest first. The Cursor-to-T3 rewrite rules live in [`tools/substitutions.json`](tools/substitutions.json), and the [sync boundary](CONTRIBUTING.md#the-sync-boundary) in `CONTRIBUTING.md` defines how a change to upstream's skill content is declared.
 
+## 2.0.0-rc.17 - Lauren's `eb4db2b`: a skill that draws a TLA+ model as a statechart a PM can read
+
+t3-pstack moves to Lauren Tan's pstack at cursor/plugins `eb4db2b` for all three components. Only pstack changed upstream, and its version moves to 0.15.30. The new `statechart` skill draws what an app's user sees as a Mermaid statechart generated from a TLA+ model, so a PM or a designer can judge the design without reading TLA+ ([pstack #741](https://github.com/cursor/plugins/pull/741)). TLC checks each rule the PM agrees to as an invariant. Each state is gray when it works, red when it is still wrong, and green when an open fix fixes it, and each class of counterexample is drawn as a numbered path. `from-spec` draws the chart from a model, `--fixed` shows what an open fix changes, and `--against` audits the code against an existing spec. `from-chart` turns a chart the PM agreed to into a TLA+ skeleton and compares the drawn chart with it. The skill is a `SKILL.md` and about 6,000 lines of Node scripts with a bundled `OutputFolder` model and a `node:test` suite. The agent runs them with `node`, which the installer already requires. The scripts find TLC only through `TLA2TOOLS`, the path to `tla2tools.jar`, and `JAVA`, and without `TLA2TOOLS` they say where to download it and exit 2. `--png` renders each chart through `npx @mermaid-js/mermaid-cli`. It keeps Lauren's `disable-model-invocation`, so on Claude Code it runs when the user types `/t3-pstack:statechart`. On Codex it is `$t3-pstack:statechart`, and Codex ignores the flag. poteto-help gains its row. `bun tools/sync.mjs` added the skill and updated poteto-help cleanly through existing substitutions, and the 12 new files are byte-identical to upstream. The skill names no Cursor tool, path, model, command, or subagent, so no rule was added, and the 15 declared forks are untouched. A new CI job, Skill script tests, runs `node --test plugins/pstack/skills/*/scripts/test/*.test.mjs` on Node 20, the step #741 added to upstream's `validate-plugins.yml`. The runner has no TLC, so 31 of the 58 tests skip there. With TLC 1.7.4 on Linux and Node 20, 57 pass and the PID-namespace test skips. On macOS two TLC tests fail on their own assumptions, not the scripts': one compares a `/var` temp path with Java's `/private/var` form, and one needs `LD_PRELOAD`, which macOS ignores. The README's skill count moves to 65. #741's version bump, upstream's README row, its guide page under `docs/guide/`, and its copies under `harness/pstack/claude-code/` sit outside every synced component. At `eb4db2b` each component's dry run reports no undeclared fork, no denylist hit, and no substitution that matches nothing. Neither hooks file changes.
+
+| Change | 2.0.0-rc.16 | 2.0.0-rc.17 | Source |
+| --- | --- | --- | --- |
+| Showing a TLA+ model to a PM | No skill. | `/statechart` draws the user's states from TLC's state graph, colors each by whether it works, and draws each bug as a numbered path. It also writes a TLA+ skeleton from an agreed chart and compares the two. | pstack #741 |
+| CI | No job runs a skill's own script tests. | Skill script tests runs every `plugins/pstack/skills/*/scripts/test/*.test.mjs` with `node --test` on Node 20. | pstack #741 |
+
 ## 2.0.0-rc.16 - setup opens the verification generators by path, and reflect follows Claude Code's transcript folder rule
 
 Two lines from the port were wrong on Claude Code, and neither came from Lauren's text. After the user says yes, `/setup-pstack`'s steps 7 and 8 told the agent to invoke `/create-verification-skill` or `/create-formal-verification-skill`. Both generators carry Lauren's `disable-model-invocation`, so the Skill tool refuses them: "cannot be used with Skill tool due to disable-model-invocation. Ask the user to run /create-verification-skill themselves". The agent then stops and asks the user to type the command. Eric Litman's open-pstack hit the same conflict in its 0.15.29 sync (issue #234) and dropped the flag in [`614075f`](https://github.com/ericlitman/open-pstack/commit/614075f5abceef0b8d22497bddb13dc55c10872a). In a throwaway Claude Code 2.1.306 home, the yes turn of a real setup run was resampled. Sonnet 5.5 and Haiku 5.5 called the Skill tool, were refused, and stopped in 4 of 4 runs, and a T3 Claude thread on Sonnet 5.5 did the same. Opus 5.5 and Fable 5.1 found the files with `find` and read them. Steps 7 and 8 now link `../create-verification-skill/SKILL.md` or `../create-formal-verification-skill/SKILL.md` from setup-pstack's own file and say to read it and follow it without the Skill tool, the way poteto-mode reaches its leaves. As links, both fail the generator's link check if a generator is renamed. After the change, none of 15 resampled runs across the four models called the Skill tool, and they read the generators by path. A full Sonnet 5.5 run generated both skills and ran them. The generators keep `disable-model-invocation`, so they still never load on their own. setup-pstack is a declared fork, and its entry in `tools/forks.json` now names the change.

NOTICE-skills.md

@@ -4,9 +4,9 @@ This plugin contains MIT-licensed work from six sources. The copyright notices a
 
 | Included work | Upstream | Copyright | License |
 | --- | --- | --- | --- |
-| The pstack skills, principles, scripts, and the `poteto-agent` and `comment-sicko` definitions | [cursor/plugins/pstack](https://github.com/cursor/plugins/tree/88d47514b82e7c44f00f2b2a72ff6dd12158038c/pstack) | (c) 2026 Lauren Tan | [MIT](LICENSE) |
-| `deslop`, `make-pr-easy-to-review`, `fix-ci`, `fix-merge-conflicts`, `get-pr-comments`, and `what-did-i-get-done` | [cursor/plugins/cursor-team-kit](https://github.com/cursor/plugins/tree/88d47514b82e7c44f00f2b2a72ff6dd12158038c/cursor-team-kit) | (c) 2026 Cursor | [MIT](LICENSE-cursor-team-kit) |
-| `thermos`, `thermo-nuclear-review`, `thermo-nuclear-code-quality-review`, and the `thermo-nuclear-review-subagent` and `thermo-nuclear-code-quality-review-subagent` definitions | [cursor/plugins/thermos](https://github.com/cursor/plugins/tree/88d47514b82e7c44f00f2b2a72ff6dd12158038c/thermos) | (c) 2026 Cursor | [MIT](LICENSE-thermos) |
+| The pstack skills, principles, scripts, and the `poteto-agent` and `comment-sicko` definitions | [cursor/plugins/pstack](https://github.com/cursor/plugins/tree/eb4db2b55b2b7dec3d9282754cddf0a56bf4ff10/pstack) | (c) 2026 Lauren Tan | [MIT](LICENSE) |
+| `deslop`, `make-pr-easy-to-review`, `fix-ci`, `fix-merge-conflicts`, `get-pr-comments`, and `what-did-i-get-done` | [cursor/plugins/cursor-team-kit](https://github.com/cursor/plugins/tree/eb4db2b55b2b7dec3d9282754cddf0a56bf4ff10/cursor-team-kit) | (c) 2026 Cursor | [MIT](LICENSE-cursor-team-kit) |
+| `thermos`, `thermo-nuclear-review`, `thermo-nuclear-code-quality-review`, and the `thermo-nuclear-review-subagent` and `thermo-nuclear-code-quality-review-subagent` definitions | [cursor/plugins/thermos](https://github.com/cursor/plugins/tree/eb4db2b55b2b7dec3d9282754cddf0a56bf4ff10/thermos) | (c) 2026 Cursor | [MIT](LICENSE-thermos) |
 | The session-start hook scripts, `read-sheet.sh`, and `reflect/scripts/find-transcript.mjs`, which t3-pstack modified, and four `poteto-mode` rules, the worktree and head-guard rules in the Feature, Opening a PR, and Shipping playbooks, three `watch-pr` fixes, and the ignored-file and reflog-only-commit holds in `poteto-mode/scripts/worktree-audit.sh`, which t3-pstack reworded or adapted for T3, and the plugin icon | [michael-denyer/pstack-claude](https://github.com/michael-denyer/pstack-claude) | (c) 2026 Michael Denyer | [MIT](LICENSE) |
 | The plain-remove prune step in the worktree-cleanup playbook, which t3-pstack adapted | [sergchil/jutsu](https://github.com/sergchil/jutsu/commit/da9442422c72cc99442c1ce3500d2f2485234a31) | (c) 2026 Sergey Chilingaryan | [MIT](LICENSE) |
 | `poteto-mode/scripts/resolve-codex-transcript` and `resolve-codex-transcript.ts`, which t3-pstack modified | [ericlitman/open-pstack](https://github.com/ericlitman/open-pstack/tree/c5c8e237c324359a3d1929037da78fe66da3d1ed/plugins/pstack/skills/poteto-mode/scripts), [PR #151](https://github.com/ericlitman/open-pstack/pull/151) | (c) 2026 Eric A. Litman and Donncha O'Toole | [MIT](LICENSE) |

NOTICE.md

@@ -6,9 +6,9 @@ t3-pstack is a port of [pstack](https://github.com/cursor/plugins/tree/main/psta
 
 | Component | Upstream | Copyright | License | License file |
 | --- | --- | --- | --- | --- |
-| Every skill under `plugins/pstack/skills/` except those named in the next two rows, `plugins/pstack/agents/poteto-agent.md`, `plugins/pstack/agents/comment-sicko.md`, and the vendored scripts under `plugins/pstack/skills/poteto-mode/scripts/` | [cursor/plugins/pstack @ 88d4751](https://github.com/cursor/plugins/tree/88d47514b82e7c44f00f2b2a72ff6dd12158038c/pstack) | (c) 2026 Lauren Tan | MIT | [LICENSE](LICENSE) |
-| `plugins/pstack/skills/{deslop,fix-ci,fix-merge-conflicts,get-pr-comments,make-pr-easy-to-review,what-did-i-get-done}/` | [cursor/plugins/cursor-team-kit @ 88d4751](https://github.com/cursor/plugins/tree/88d47514b82e7c44f00f2b2a72ff6dd12158038c/cursor-team-kit) | (c) 2026 Cursor | MIT | [LICENSE-cursor-team-kit](LICENSE-cursor-team-kit) |
-| `plugins/pstack/skills/{thermos,thermo-nuclear-review,thermo-nuclear-code-quality-review}/`, `plugins/pstack/agents/thermo-nuclear-review-subagent.md`, `plugins/pstack/agents/thermo-nuclear-code-quality-review-subagent.md` | [cursor/plugins/thermos @ 88d4751](https://github.com/cursor/plugins/tree/88d47514b82e7c44f00f2b2a72ff6dd12158038c/thermos) | (c) 2026 Cursor | MIT | [LICENSE-thermos](LICENSE-thermos) |
+| Every skill under `plugins/pstack/skills/` except those named in the next two rows, `plugins/pstack/agents/poteto-agent.md`, `plugins/pstack/agents/comment-sicko.md`, and the vendored scripts under `plugins/pstack/skills/poteto-mode/scripts/` | [cursor/plugins/pstack @ eb4db2b](https://github.com/cursor/plugins/tree/eb4db2b55b2b7dec3d9282754cddf0a56bf4ff10/pstack) | (c) 2026 Lauren Tan | MIT | [LICENSE](LICENSE) |
+| `plugins/pstack/skills/{deslop,fix-ci,fix-merge-conflicts,get-pr-comments,make-pr-easy-to-review,what-did-i-get-done}/` | [cursor/plugins/cursor-team-kit @ eb4db2b](https://github.com/cursor/plugins/tree/eb4db2b55b2b7dec3d9282754cddf0a56bf4ff10/cursor-team-kit) | (c) 2026 Cursor | MIT | [LICENSE-cursor-team-kit](LICENSE-cursor-team-kit) |
+| `plugins/pstack/skills/{thermos,thermo-nuclear-review,thermo-nuclear-code-quality-review}/`, `plugins/pstack/agents/thermo-nuclear-review-subagent.md`, `plugins/pstack/agents/thermo-nuclear-code-quality-review-subagent.md` | [cursor/plugins/thermos @ eb4db2b](https://github.com/cursor/plugins/tree/eb4db2b55b2b7dec3d9282754cddf0a56bf4ff10/thermos) | (c) 2026 Cursor | MIT | [LICENSE-thermos](LICENSE-thermos) |
 | `tools/sync.mjs`, `tools/generate.mjs`, `tools/validate-skills.mjs`, `tools/plugin.mjs`, `plugins/pstack/skills/reflect/scripts/find-transcript.mjs`, `plugins/pstack/hooks/session-start.sh`, `plugins/pstack/hooks/session-start.ps1`, `plugins/pstack/skills/setup-pstack/scripts/read-sheet.sh`, and the tests that cover them, each modified by t3-pstack | [michael-denyer/pstack-claude](https://github.com/michael-denyer/pstack-claude), as merged into t3-pstack through 1.0.14 | (c) 2026 Michael Denyer | MIT | [LICENSE](LICENSE) |
 | Four rules in `plugins/pstack/skills/poteto-mode/SKILL.md` (load a platform's skill before deploying, stop an abandoned agent and confirm it stopped, keep a review gate closed with no independent reviewer, the `todo.md` fallback), the per-delegate worktree rule in `playbooks/feature.md`, the stop-live-agents rule in `playbooks/opening-a-pr.md`, the `--match-head-commit` guard in `playbooks/shipping.md`, and the review-gate, stale-check, and no-checks fixes in `plugins/pstack/skills/poteto-mode/scripts/watch-pr/` with their tests in `verdicts.test.ts`, each reworded or adapted for T3 by t3-pstack | [michael-denyer/pstack-claude](https://github.com/michael-denyer/pstack-claude), pull requests [#95](https://github.com/michael-denyer/pstack-claude/pull/95), [#97](https://github.com/michael-denyer/pstack-claude/pull/97), and [#153](https://github.com/michael-denyer/pstack-claude/pull/153) for watch-pr | (c) 2026 Michael Denyer | MIT | [LICENSE](LICENSE) |
 | The ignored-file and reflog-only-commit holds in `plugins/pstack/skills/poteto-mode/scripts/worktree-audit.sh`, ported from JavaScript to bash, and their wording in `playbooks/worktree-cleanup.md`, with the test cases in `tests/worktree-audit.test.mjs`; the plugin icon with its C2PA manifest removed (`plugins/pstack/.claude-plugin/icon.png`, `plugins/pstack/assets/pstack-icon.png`) and `tests/image-metadata.test.mjs` | [michael-denyer/pstack-claude](https://github.com/michael-denyer/pstack-claude), pull requests [#277](https://github.com/michael-denyer/pstack-claude/pull/277) and [#271](https://github.com/michael-denyer/pstack-claude/pull/271) | (c) 2026 Michael Denyer | MIT | [LICENSE](LICENSE) |

README.md

@@ -14,7 +14,7 @@ npx -y github:chhoumann/t3-pstack update
 npx -y github:chhoumann/t3-pstack doctor
 ```
 
-`npx -y github:chhoumann/t3-pstack` runs the installer from the latest commit on `main`. That is the rolling channel, the same one each home's marketplace auto-updates from. To run one release's installer, name its tag, as in `npx -y github:chhoumann/t3-pstack#v2.0.0-rc.16 doctor`.
+`npx -y github:chhoumann/t3-pstack` runs the installer from the latest commit on `main`. That is the rolling channel, the same one each home's marketplace auto-updates from. To run one release's installer, name its tag, as in `npx -y github:chhoumann/t3-pstack#v2.0.0-rc.17 doctor`.
 
 `install` and `update` are the same command, and a second run changes nothing. With Node 20 or later, it installs or updates the `t3-pstack@t3-pstack` plugin in every Claude Code and Codex config home T3 can run: `~/.claude` and `~/.codex`, `$CLAUDE_CONFIG_DIR` and `$CODEX_HOME`, and the home of each `claudeAgent` and `codex` instance in T3's settings, disabled ones included. Name any other home with `--claude-home <dir>` or `--codex-home <dir>`. Each home's `t3-pstack` marketplace must come from `chhoumann/t3-pstack`, or from `--source <owner/repo|git URL|dir>` on the same run, and a home whose marketplace has another source is left as it is. A local directory needs a path such as `./t3-pstack`, since `owner/repo` always means GitHub. On Codex it also trusts t3-pstack's session-start hook, once its hooks file is the one this release pins. Codex runs a plugin's hook only once it is trusted, and T3's Codex sessions never ask, so without this step the hook never runs. Run `update` after each release.
 
@@ -30,11 +30,11 @@ Use poteto-mode to fix the search filter resetting when I change pages.
 
 The session-start hook tells each new chat when to enter `poteto-mode` on its own: work that touches more than one file, a design choice, or a bug whose cause is unknown. `poteto-mode` matches the task to a playbook and opens the other skills from there. They ship as upstream ships them, invoked by `poteto-mode` or typed by you (`/t3-pstack:<name>` on Claude Code, `$t3-pstack:<name>` on Codex).
 
-The plugin carries 64 skill directories, 24 of them `principle-*` leaves, and 4 agents.
+The plugin carries 65 skill directories, 24 of them `principle-*` leaves, and 4 agents.
 
 ## Staying current
 
-This repository syncs from Lauren's tree directly, synced against upstream `88d4751`. `tools/upstream.json` pins each component, `tools/substitutions.json` holds the rewrite rules and a denylist of Cursor terms, and `tools/forks.json` declares every file the port keeps in its own form and why. `bun tools/sync.mjs <component> <sha>` derives each upstream file through the rules, merges it three ways with the port's copy, and fails on an undeclared fork, a denylist hit, or a rule that no longer matches upstream. [CONTRIBUTING.md](CONTRIBUTING.md#the-sync-boundary) has the details.
+This repository syncs from Lauren's tree directly, synced against upstream `eb4db2b`. `tools/upstream.json` pins each component, `tools/substitutions.json` holds the rewrite rules and a denylist of Cursor terms, and `tools/forks.json` declares every file the port keeps in its own form and why. `bun tools/sync.mjs <component> <sha>` derives each upstream file through the rules, merges it three ways with the port's copy, and fails on an undeclared fork, a denylist hit, or a rule that no longer matches upstream. [CONTRIBUTING.md](CONTRIBUTING.md#the-sync-boundary) has the details.
 
 ## Data handling
 

VERSION

@@ -1 +1 @@
-2.0.0-rc.16
+2.0.0-rc.17

package.json

@@ -1,7 +1,7 @@
 {
   "name": "t3-pstack",
   "private": true,
-  "version": "2.0.0-rc.16",
+  "version": "2.0.0-rc.17",
   "description": "The installer and development tooling for t3-pstack, Lauren Tan's pstack rewritten in place for T3 Code. The plugin itself lives in plugins/pstack.",
   "author": {
     "name": "Christian Bager Bach Houmann",

plugins/pstack/.claude-plugin/plugin.json

@@ -1,7 +1,7 @@
 {
   "name": "t3-pstack",
   "displayName": "t3-pstack (pstack for T3 Code)",
-  "version": "2.0.0-rc.16",
+  "version": "2.0.0-rc.17",
   "description": "pstack for T3 Code: Lauren Tan's pstack with its Cursor mechanics rewritten in place for T3, so subagents, panels, schedules, and PR watches dispatch through T3's orchestration and panels mix Claude, GPT, and Grok.",
   "author": {
     "name": "Christian Bager Bach Houmann",

plugins/pstack/.codex-plugin/plugin.json

@@ -1,6 +1,6 @@
 {
   "name": "t3-pstack",
-  "version": "2.0.0-rc.16",
+  "version": "2.0.0-rc.17",
   "description": "pstack for T3 Code on a Codex host: Lauren Tan's pstack with its Cursor mechanics rewritten in place for T3, so subagents, panels, schedules, and PR watches dispatch through T3's orchestration.",
   "author": {
     "name": "Christian Bager Bach Houmann",