thisguymartin · thisguymartin · Oct 5, 2026 · Oct 5, 2026 · Oct 5, 2026 · Oct 5, 2026
diff --git a/.agents/plugins/marketplace.json b/.agents/plugins/marketplace.json
@@ -1,7 +1,7 @@
 {
-  "name": "open-pstack",
+  "name": "pstack-flex",
   "interface": {
-    "displayName": "pstack"
+    "displayName": "pstack-flex"
   },
   "plugins": [
     {

diff --git a/.claude-plugin/marketplace.json b/.claude-plugin/marketplace.json
@@ -1,9 +1,9 @@
 {
-  "name": "open-pstack",
+  "name": "pstack-flex",
   "owner": {
-    "name": "Eric Litman"
+    "name": "Martin Patino"
   },
-  "description": "Pstack for Claude Code and Codex, tracking Cursor's upstream pstack.",
+  "description": "pstack for Claude Code and Codex on the models you choose: subscription CLIs or API-key gateway lanes.",
   "plugins": [
     {
       "name": "pstack",
@@ -13,7 +13,7 @@
       "author": {
         "name": "Lauren Tan (original)"
       },
-      "homepage": "https://github.com/ericlitman/open-pstack",
+      "homepage": "https://github.com/thisguymartin/pstack-flex",
       "license": "MIT",
       "keywords": [
         "pstack",

diff --git a/AGENTS.md b/AGENTS.md
@@ -1,11 +1,11 @@
-# open-pstack
+# pstack-flex
 
 Track all durable work in this repository's GitHub Issues. Do not create a parallel Linear queue. Read `UPSTREAM.md` before changing upstream-derived content.
 
 Cursor's `cursor/plugins/pstack` tree is the content upstream. Keep one shared skill tree for Claude Code and Codex; adapt harness primitives at the existing mapping boundaries instead of forking skills or adding compatibility layers. The parent harness resolves provider routing once. Children do not detect or reroute themselves.
 
-Before opening a pull request, run the Bun tests, strict typecheck, static invariants, and plugin validation.
+Before opening a pull request, run the Bun tests, strict typecheck, static invariants, and plugin validation: `bash scripts/check.sh` runs all of them.
 
-Nothing merges, tags, releases, or rolls out until the exact candidate is installed and the changed behavior passes a live test from the real user surface in every affected harness. Unit tests, validators, source inspection, and self-reports do not satisfy this gate. Record the installed version, surface, action, and observed result in the pull request template. A pull request without that evidence remains a draft.
+Nothing merges, tags, releases, or rolls out until the exact candidate is installed and the changed behavior passes a live test from the real user surface in every affected harness. Unit tests, validators, source inspection, and self-reports do not satisfy this gate. Record the installed version, surface, action, and observed result in the pull request template. A pull request without that evidence remains a draft. `docs/LIVE-GATE.md` lists the steps per change and the evidence format.
 
 Do not add an implicit runtime timeout or a weaker-model fallback.
diff --git a/CHANGES.md b/CHANGES.md
@@ -1,5 +1,11 @@
 # CHANGES — applied substitutions
 
+## Unreleased: pstack-flex becomes its own distribution
+
+- The marketplace is now `pstack-flex` (was `open-pstack`) in both the Claude Code and Codex marketplace files. Install with `pstack@pstack-flex`. The plugin keeps the name `pstack`, so skill names such as `pstack:poteto-mode` are unchanged. Manifests, package names, and docs point at `thisguymartin/pstack-flex`; attribution to open-pstack, pstack-claude, and Cursor pstack stays in README and NOTICE.
+- New skills: `intake` ([#10](https://github.com/thisguymartin/pstack-flex/issues/10)) turns GitHub issues into ready-to-run poteto-mode briefs with a playbook, an observable exit condition, a verification plan, and a worktree; it is read-only and parks briefs with open product questions. `diff-behavior` ([#15](https://github.com/thisguymartin/pstack-flex/issues/15)) runs the same scenarios on trunk and head through `swarm`, normalizes, and classifies every difference as intended, unintended, or noise. Neither changes an upstream skill body; wiring them into poteto-mode and the multi-phase-plan regression lane is a follow-up.
+- Fixes: `codex-tools.md` now says the default panel runs four lanes across three providers (it said four providers). `docs/LANES.md` replaces the stale claim that OpenRouter needs a local translator with OpenRouter's documented Claude Code connection and the probes from [#7](https://github.com/thisguymartin/pstack-flex/issues/7).
+
 ## Unreleased: lane journal
 
 - `pstack-runner` writes an opt-in lane journal (start record with the head of the prompt, stdout as it arrives, receipt copy) under `~/.pstack-flex/lanes/` while that directory exists. `--label` names a lane. A journal failure never changes a lane's receipt, exit status, or output. [psf-monitor](https://github.com/thisguymartin/psf-monitor) reads the journal to show lanes while they run; the agent monitor that first shipped here moved there. Tracked in [pstack-flex #23](https://github.com/thisguymartin/pstack-flex/issues/23).

diff --git a/README.md b/README.md
@@ -1,10 +1,10 @@
 # pstack-flex
 
 [![CI](https://github.com/thisguymartin/pstack-flex/actions/workflows/ci.yml/badge.svg)](https://github.com/thisguymartin/pstack-flex/actions/workflows/ci.yml)
-[![Fork of open-pstack v1.5.0](https://img.shields.io/badge/fork%20of-open--pstack%20v1.5.0-blue)](https://github.com/ericlitman/open-pstack/releases/tag/v1.5.0)
+[![Based on open-pstack v1.5.0](https://img.shields.io/badge/based%20on-open--pstack%20v1.5.0-blue)](https://github.com/ericlitman/open-pstack/releases/tag/v1.5.0)
 [![MIT license](https://img.shields.io/github/license/thisguymartin/pstack-flex)](LICENSE)
 
-**pstack-flex runs [Lauren Tan (@poteto)](https://x.com/poteto)'s [pstack](https://github.com/cursor/plugins/tree/main/pstack) in Claude Code and Codex on the models you actually have.** It is a fork of [ericlitman/open-pstack](https://github.com/ericlitman/open-pstack), which translates pstack's Cursor-specific parts for Claude Code and Codex. open-pstack assumes four frontier subscriptions. This fork keeps its skills and workflows and changes one thing: which models setup accepts and how they are reached.
+**pstack-flex runs [Lauren Tan (@poteto)](https://x.com/poteto)'s [pstack](https://github.com/cursor/plugins/tree/main/pstack) in Claude Code and Codex on the models you actually have.** It is built on [ericlitman/open-pstack](https://github.com/ericlitman/open-pstack), which translates pstack's Cursor-specific parts for Claude Code and Codex. open-pstack assumes four frontier subscriptions. pstack-flex keeps its skills and workflows, changes which models setup accepts and how they are reached, and adds its own skills. The agent monitor lives in its own repository, [psf-monitor](https://github.com/thisguymartin/psf-monitor).
 
 Lauren built pstack from the skills she uses to ship code at Cursor. In a [55-minute interview with Denis Labelle](https://x.com/DenisLabelle/status/2091337807939706928), she says that she shipped 1,000 pull requests in one month after steadily improving how her agents work and verify their results.
 
@@ -80,7 +80,7 @@ Run these commands inside Claude Code:
 
 ```text
 /plugin marketplace add thisguymartin/pstack-flex
-/plugin install pstack@open-pstack
+/plugin install pstack@pstack-flex
 /reload-plugins
 ```
 
@@ -90,7 +90,7 @@ Run these commands in your shell:
 
 ```shell
 codex plugin marketplace add thisguymartin/pstack-flex --ref main
-codex plugin add pstack@open-pstack
+codex plugin add pstack@pstack-flex
 ```
 
 Turn on Codex subagents in `~/.codex/config.toml` so pstack can compare work in parallel:
@@ -161,6 +161,8 @@ The agent monitor is a separate plugin, [psf-monitor](https://github.com/thisguy
 | `maintain-verification-skill` | The project's verification instructions no longer match the product. |
 | `babysit` | A pull request needs CI failures and review comments handled until it is ready. |
 | `reflect` | A hard task is finished and its lessons should improve the next run. |
+| `intake` | You have GitHub issues and want each turned into a ready-to-run brief with a playbook, an observable exit condition, and a worktree. |
+| `diff-behavior` | You want to know what a change did from the outside: the same scenarios on trunk and head, with every unclaimed difference flagged. |
 
 Plugin skills include `pstack:` in their name. In Claude Code, invoke a native skill such as `/pstack:architect`. In Codex, ask for the skill, such as `Use pstack:architect for this design.` See the [technical reference](docs/reference.md) for the full list.
 
@@ -194,8 +196,8 @@ Also kept here: [the original README](README-UPSTREAM.md), unchanged; [the techn
 
 Fixes for Claude Code or Codex, new lanes, and help bringing over new pstack releases are welcome. Search this repository's [GitHub Issues](https://github.com/thisguymartin/pstack-flex/issues) before opening a new one. For changes to upstream-derived content, explain why the change belongs here instead of in open-pstack or Lauren's original project.
 
-Read [UPSTREAM.md](UPSTREAM.md) and [UPSTREAM-FLEX.md](UPSTREAM-FLEX.md) before changing content brought over from either upstream. Pull requests must keep one shared skill tree for Claude Code and Codex and pass the repository's tests, type checks, plugin validation, and static checks. Nothing merges until the exact candidate is installed and the changed behavior passes a live test from the real user surface in every affected harness; the [pull request template](.github/pull_request_template.md) records that evidence, and a PR without it stays a draft. Adding a gateway provider has its own checklist in [docs/LANES.md](docs/LANES.md#adding-a-gateway-provider).
+Read [UPSTREAM.md](UPSTREAM.md) and [UPSTREAM-FLEX.md](UPSTREAM-FLEX.md) before changing content brought over from either upstream. Pull requests must keep one shared skill tree for Claude Code and Codex and pass the repository's tests, type checks, plugin validation, and static checks. Nothing merges until the exact candidate is installed and the changed behavior passes a live test from the real user surface in every affected harness; the [pull request template](.github/pull_request_template.md) records that evidence, and a PR without it stays a draft. Run `bash scripts/check.sh` for the local checks and follow [docs/LIVE-GATE.md](docs/LIVE-GATE.md) for the live test. Adding a gateway provider has its own checklist in [docs/LANES.md](docs/LANES.md#adding-a-gateway-provider).
 
 ## License
 
-MIT. pstack was created by Lauren Tan. open-pstack builds on Michael Denyer's [pstack-claude](https://github.com/michael-denyer/pstack-claude) port and includes attributed MIT-licensed work from Cursor Team Kit and Superpowers. pstack-flex is a fork of open-pstack. See [NOTICE.md](NOTICE.md) and the preserved license files for details.
+MIT. pstack was created by Lauren Tan. open-pstack builds on Michael Denyer's [pstack-claude](https://github.com/michael-denyer/pstack-claude) port and includes attributed MIT-licensed work from Cursor Team Kit and Superpowers. pstack-flex started as a fork of open-pstack and is maintained as its own distribution. See [NOTICE.md](NOTICE.md) and the preserved license files for details.
diff --git a/UPSTREAM-FLEX.md b/UPSTREAM-FLEX.md
@@ -37,6 +37,7 @@ All flex changes are additive and live in port-owned files so upstream merges st
 - The assignment-first restructure of `skills/setup-pstack/SKILL.md`
 - `docs/LANES.md`, this file, the README fork section, and the NOTICE/LICENSE/CHANGES additions
 - `plugins/pstack/hooks/session-start-context.md`, which the fork rewrote from open-pstack's auto-fire mandate into an opt-in gate, and the docs lines that describe it
+- The `intake` and `diff-behavior` skills: `plugins/pstack/skills/intake/` and `plugins/pstack/skills/diff-behavior/`. Upstream has no equivalent, so they never conflict.
 - The lane journal: `runner/flex-journal.ts` and its test (new), its call sites in `runner/{types,run,cli}.ts` (an optional stdout callback on the model run, the journal opened after output reservation and finished on both return paths, and the `--label` flag), the journal tests in `run.test.ts`, and the pstack-flex paragraph after the invocation block in `references/provider-dispatch.md`. On a sync, keep these call sites; they change no receipt or exit status.
 
 Every upstream skill body is byte-unchanged except for the default-descriptor mentions listed above. Since [#17](https://github.com/thisguymartin/pstack-flex/issues/17), the stock matrix carries three fork-owned GPT-6 rows and the first-run sheet uses them, so those two surfaces conflict on every upstream sync and are resolved by hand: keep the fork's rows and defaults, take upstream's wording for everything else.

diff --git a/UPSTREAM.md b/UPSTREAM.md
@@ -45,7 +45,7 @@ No output means the tracked pstack tree has not changed. This comparison does no
 
 ## Incorporate a change
 
-1. Create or update a GitHub issue in `ericlitman/open-pstack` and branch from current `main`.
+1. Create or update a GitHub issue in `thisguymartin/pstack-flex` and branch from current `main`.
 2. Read each upstream pstack commit in order. Bring over its intent and content, then apply only the Claude Code and Codex substitutions documented in `CHANGES.md`.
 3. Keep one shared `plugins/pstack/skills/` tree. Put harness translation in the existing `codex-tools.md` and provider routing in `provider-dispatch.md`; do not fork a skill per harness.
 4. Update the commit and version in this file, the affected provenance rows in `NOTICE.md`, and `README-UPSTREAM.md` when upstream changes it.

diff --git a/docs/LANES.md b/docs/LANES.md
@@ -126,7 +126,7 @@ Quality note: this trades peak capability for cost control. The hardest-task rol
 
 ## Optional lanes
 
-- **OpenRouter (off by default).** OpenRouter has no Anthropic-format endpoint, so a lane needs a local translator that serves `/v1/messages` — musistudio/claude-code-router or a version-pinned LiteLLM — with `ANTHROPIC_BASE_URL` pointed at it. That is one extra long-running local process, which is why it is documented rather than shipped. Expect roughly a 5.5% credit fee on top of provider list prices. If you build it, model it as another gateway provider in `flex-providers.ts`.
+- **OpenRouter (not shipped).** OpenRouter documents a direct Claude Code connection (`ANTHROPIC_BASE_URL=https://openrouter.ai/api`, `ANTHROPIC_AUTH_TOKEN` from `OPENROUTER_API_KEY`, and an explicitly empty `ANTHROPIC_API_KEY`), so no local translator is needed. It guarantees that route only for Anthropic models, so DeepSeek, MiniMax, and other catalog models through OpenRouter must pass the live probes in [issue #7](https://github.com/thisguymartin/pstack-flex/issues/7) (tool call, second turn, effort, model identity) before a lane ships. If it does, model it as another gateway provider in `flex-providers.ts`. Expect a credit fee on top of provider list prices; check OpenRouter's current pricing page.
 - **Local via Ollama (planned).** Ollama serves an Anthropic-compatible API since v0.14, so a `local` gateway provider pointed at it is the natural next lane: full compute control, zero per-token cost, your hardware. Not wired in yet.
 
 ## Adding a gateway provider

diff --git a/docs/LIVE-GATE.md b/docs/LIVE-GATE.md
@@ -0,0 +1,72 @@
+# Live gate
+
+AGENTS.md says nothing merges, tags, releases, or rolls out until the exact candidate is installed and the changed behavior passes a live test from the real user surface in every affected harness. Unit tests, validators, and source reading do not count. This page is how to run that test and where to record it.
+
+There are two halves:
+
+1. **Local gate.** One command, runs anywhere: `bash scripts/check.sh`. It installs both Bun packages, runs their tests and strict typechecks, parses every manifest, runs the static invariants, and runs `claude plugin validate` on the marketplace and both plugins when the `claude` CLI is present.
+2. **Live gate.** You, in a real Claude Code and a real Codex session, with the candidate installed. Steps below.
+
+## 1. Install the exact candidate
+
+Push the branch first, so both harnesses install the same commit.
+
+Claude Code: check out the branch, then add that checkout as the marketplace (inside a session):
+
+```text
+! git clone -b <branch> https://github.com/thisguymartin/pstack-flex ~/src/pstack-flex-candidate
+/plugin marketplace add ~/src/pstack-flex-candidate
+/plugin install pstack@pstack-flex
+/reload-plugins
+```
+
+Codex (shell):
+
+```shell
+codex plugin marketplace add thisguymartin/pstack-flex --ref <branch>
+codex plugin add pstack@pstack-flex
+```
+
+Start a new session in each harness afterwards. Record the installed version: the `pstack` version from the plugin list, plus `claude --version` and `codex --version`.
+
+If you had open-pstack or an older pstack-flex installed under the `open-pstack` marketplace name, remove it first so only one plugin named `pstack` is active.
+
+## 2. Run the checks for what changed
+
+Run the rows that match the change. A change that touches the runner or the model sheet runs rows A to C in both harnesses.
+
+| Row | Action | Pass when |
+| --- | --- | --- |
+| A. Opt-in gate | In a fresh session, ask for a two-line fix without naming pstack. Then ask again with "Use pstack for this." | The first request runs no `pstack:` skill. The second enters `pstack:poteto-mode`. |
+| B. Setup | Run `/pstack:setup-pstack` (Claude Code) or `Use pstack:setup-pstack.` (Codex). Keep defaults or change one role. | Every assigned family probes `complete`, the sheet is written to `~/.claude/pstack-models.md` or `~/.codex/pstack-models.md`, and a failed probe writes nothing. |
+| C. Mixed panel | `Use pstack:interrogate on the last commit.` | Each configured reviewer returns, external lanes write receipts with `status: complete`, and any missing CLI shows as a named dropout, not a substitute. |
+| D. Gateway lane | With `DEEPSEEK_API_KEY` or `MINIMAX_API_KEY` exported, assign one role to that family in setup and run it once. | The receipt shows `status: complete`, the requested model, and `costUsd: null`. |
+| E. Lane journal | `mkdir -p ~/.pstack-flex/lanes`, run one external lane (for example an interrogate with a Codex reviewer from Claude Code), then `rm -rf ~/.pstack-flex/lanes`. With [psf-monitor](https://github.com/thisguymartin/psf-monitor) installed, watch the lane on its page instead. | While it runs, the lane's directory holds `lane.json` and a growing `stream.jsonl`; after it ends, `receipt.json` matches the runner's receipt. With the directory removed, the next lane writes nothing there and its receipt is unchanged. |
+| F. intake | In a scratch repo with a real issue: `Use pstack:intake for #<n>.` | A brief appears under `.pstack/intake/`, with one playbook, an observable exit condition, and open questions when the issue is vague. No product code changes. |
+| G. diff-behavior | In a scratch repo, make a branch that changes one scenario on purpose and one by accident. `Use pstack:diff-behavior on this branch.` | The report lists the accidental change as unintended and the deliberate one as intended, with evidence for both sides. |
+
+## 3. Record the evidence
+
+Paste this into the pull request under "Live evidence", one block per harness:
+
+```text
+Harness: Claude Code <claude --version> | Codex <codex --version>
+Installed: pstack <version> @ <commit>
+Row <letter>: <action you took>
+Observed: <what happened, with receipt or screenshot path>
+Result: pass | fail
+```
+
+A pull request without this stays a draft.
+
+## Outstanding live tests
+
+These merged without an installed live test. Clear them with one session per harness on current `main`, then record the results in a tracking issue and tick the rows.
+
+| PR | Change | Rows to run | Status |
+| --- | --- | --- | --- |
+| #16 | GPT-6 families and first-run defaults | B, C | not run |
+| #19, #20 | Opt-in gate (Claude Code and Codex) | A | not run |
+| #22 | open-pstack 1.5.0 merge, setup step order, grok-4.7 pin | B, C | not run |
+| #24, #25 | Lane journal (the monitor itself moved to psf-monitor in #28) | E | checkout build only, not installed |
+| #26 | Rename to pstack-flex, intake, diff-behavior, doc fixes | A, B, F, G | not run |