Skip to content
Open
Show file tree
Hide file tree
Changes from all commits
Commits
File filter

Filter by extension

Filter by extension

Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
2 changes: 1 addition & 1 deletion docs/guide/02-poteto-mode.md
Original file line number Diff line number Diff line change
Expand Up @@ -104,7 +104,7 @@ A long chat accumulates context from the last task. When you change subjects, sa

## Give parallel work its own machine

If you run several agents against one repository on one computer, they will fight over the working tree, the ports, and the build output. The cleanest isolation is a [cloud Devin session](https://docs.devin.ai/cli/cloud) (`devin --cloud -p "<task>"`). Each one gets its own VM and branch, so it can install dependencies, run your app, and record video of the result without touching your machine. Ask the parent chat to hand work to cloud sessions.
If you run several agents against one repository on one computer, they will fight over the working tree, the ports, and the build output. The cleanest isolation is a [cloud Devin session](https://docs.devin.ai/cli/cloud) (`devin --cloud -- "<task>"`). Each one gets its own VM and branch, so it can install dependencies, run your app, and record video of the result without touching your machine. Ask the parent chat to hand work to cloud sessions.

When the work has to stay local, ask for a worktree up front:

Expand Down
4 changes: 2 additions & 2 deletions docs/guide/05-build-and-clean.md
Original file line number Diff line number Diff line change
Expand Up @@ -56,7 +56,7 @@ In context, that's enough. [`/pstack:tdd`](../../skills/tdd/SKILL.md) writes the

## Clean before you commit

The [Opening a PR playbook](../../skills/poteto-mode/playbooks/opening-a-pr.md) runs a slop-strip pass on the diff before each commit and applies [`/pstack:unslop`](../../skills/unslop/SKILL.md) to the PR description and commit bodies.
The [Opening a PR playbook](../../skills/poteto-mode/playbooks/opening-a-pr.md) runs `/pstack:deslop` on the diff before each commit and applies [`/pstack:unslop`](../../skills/unslop/SKILL.md) to the PR description and commit bodies.

For prose, `/pstack:unslop` takes a target and any extra rules you have:

Expand All @@ -76,7 +76,7 @@ Comments need their own pass, and not from the agent that wrote them. An author

[`/pstack:no-comments`](../../skills/no-comments/SKILL.md) spawns [Comment Sicko](../../agents/comment-sicko.md), a read-only reviewer with a short keep list: license headers, doc comments on a public API, links that explain what code can't, behavior forced by an external dependency you can't reshape. Everything else goes. A surprise in your own code gets no such pass. The comment comes back as a refactor flag, and `/pstack:no-comments` fixes the flags it accepts at the root cause. When a comment claims a constraint, "do not remove", the skill offers to encode the claim as a type, test, or lint. Either way, the comment comes out.

The division of labor is worth keeping straight. `/deslop` cleans slop out of the code, `/pstack:unslop` cleans it out of prose, and `/pstack:no-comments` hands the comments to a reviewer who didn't write them.
The division of labor is worth keeping straight. `/pstack:deslop` cleans slop out of the code, `/pstack:unslop` cleans it out of prose, and `/pstack:no-comments` hands the comments to a reviewer who didn't write them.

**Pitfall:** cleanup is not optional polish. A diff with narrating comments and defensive dead weight reads as unfinished to reviewers, and the extra code is where the next bug hides. If the diff feels padded, say `deslop it` before you commit, not after review calls it out.

Expand Down
2 changes: 1 addition & 1 deletion skills/poteto-help/SKILL.md
Original file line number Diff line number Diff line change
Expand Up @@ -136,7 +136,7 @@ Principles are one-rule skills that `/pstack:poteto-mode` reads and cites in its
| A new model choice had no effect | The rule from `/pstack:setup-pstack` applies to new chats. Start one. |
| Runs cost more than expected | See the cost paragraph under Get set up. |
| A skill didn't load on its own | Only `/pstack:setup-pstack` loads from the user's words. The others load when the user types them or when `/pstack:poteto-mode` runs them, and it doesn't run every skill. |
| Parallel agents overwrote each other | Give each agent its own worktree, or run them as cloud Devin sessions (`devin --cloud -p`), which each get their own machine. |
| Parallel agents overwrote each other | Give each agent its own worktree, or run them as cloud Devin sessions (`devin --cloud`), which each get their own machine. |
| An overnight run moved but finished nothing | `/loop` needs a check that can pass or fail, not a duration. See [guide page 7](../../docs/guide/07-overnight.md). |
| The reply claims success from a green build | Ask for the real command, flow, stored value, or profile. That's the prove-it-works principle. |

Expand Down
2 changes: 1 addition & 1 deletion skills/poteto-mode/SKILL.md
Original file line number Diff line number Diff line change
Expand Up @@ -24,7 +24,7 @@ Remaining triggers:
- Nontrivial multi-step → write the throughput checkpoint (Feature step 3).
- Any prose surface, your reply to the user included → the **unslop** skill. Write the reply per **Writing the reply**. Agent-facing prose also follows the Authoring or modifying a skill playbook (`playbooks/authoring-a-skill.md`).
- Docs, RFCs, readmes, PR descriptions, or commit messages → the **technical-writing** skill (`/pstack:technical-writing`).
- Before commit → the `deslop` skill (`/deslop`).
- Before commit → the `deslop` skill (`/pstack:deslop`).
- Before review → the **no-comments** skill (`/pstack:no-comments`).
- Shipping UI / IDE / CLI → the matching control skill. pstack includes `control-cli` (CLIs and TUIs) and `control-ui` (browser / Electron / web UIs). For bug fixes, reproduce first on the same surface yourself. Hand to the user only under the narrow Bug fix step 1 exception.
- Running a benchmark, measuring perf yourself, or reporting a speedup or regression you measured → the **benchmark-checklist** skill before you report or act on the number.
Expand Down
4 changes: 2 additions & 2 deletions skills/poteto-mode/playbooks/autopilot-full.md
Original file line number Diff line number Diff line change
Expand Up @@ -5,9 +5,9 @@
A verdict covers one patch and green CI covers one head. Step 4 runs a full swarm once, and again only for a major change. The patch-id rule in `playbooks/shipping.md` can carry a lane's result, and every new head needs its own green CI.

1. **The operator's gates come first.** The grant covers only the queue's items, so items the operator names as theirs and PRs outside the queue stop at merge-ready. A request to state the plan is not a go.
2. **Spawn one owner per PR, and keep its work where a replacement can find it.** Resolve the forge once for the program. GitHub CLI (`gh`) is the default. If `command -v origin` succeeds and Origin can resolve the repository, use `origin pr` for every PR operation. Otherwise stay on `gh` and record the fallback. Never require Graphite (`gt`). Each owner is a cloud Devin session (`devin --cloud -p "<brief>"`) that builds, opens its PR per `playbooks/opening-a-pr.md`, proves the change on the real artifact, babysits to green per `playbooks/babysit.md`, and merges once steps 4 and 5 clear it.
2. **Spawn one owner per PR, and keep its work where a replacement can find it.** Resolve the forge once for the program. GitHub CLI (`gh`) is the default. If `command -v origin` succeeds and Origin can resolve the repository, use `origin pr` for every PR operation. Otherwise stay on `gh` and record the fallback. Never require Graphite (`gt`). Each owner is its own shell session (`devin --cloud -- "<brief>"`; `run_subagent` has no cloud option) that builds, opens its PR per `playbooks/opening-a-pr.md`, proves the change on the real artifact, babysits to green per `playbooks/babysit.md`, and merges once steps 4 and 5 clear it.

Open the PR early so CI and bots run alongside the work. The code is ready only after the slop-strip (the `deslop` skill (`/deslop`)) and the `/pstack:no-comments` pass, so the full swarm runs on finished code. Then rebase onto current trunk and report the code-ready head before self-proof, so verification runs on the base the patch lands on. Report every later head, and merge-ready once self-proof, CI, and babysit are done. Fix rounds stay on that base unless trunk conflicts, breaks CI, or lands a known concurrent change to the same files, because each rebase restarts CI. Run the repo's checks for the touched paths on the committed head before the code-ready push and before a later push that needs a verifier.
Open the PR early so CI and bots run alongside the work. The code is ready only after the slop-strip (the `deslop` skill (`/pstack:deslop`)) and the `/pstack:no-comments` pass, so the full swarm runs on finished code. Then rebase onto current trunk and report the code-ready head before self-proof, so verification runs on the base the patch lands on. Report every later head, and merge-ready once self-proof, CI, and babysit are done. Fix rounds stay on that base unless trunk conflicts, breaks CI, or lands a known concurrent change to the same files, because each rebase restarts CI. Run the repo's checks for the touched paths on the committed head before the code-ready push and before a later push that needs a verifier.

Assume the VM dies. Soon after starting, push and start a decision trail in the root agent's store (path in the system prompt) per the **show-me-your-work** skill, then push each finished unit before you start the next. Whoever spawns a subagent records its id, state, and a stuck-after runtime from past runs of its kind in that store, so the root can probe it if the parent dies. Force-push only your own branch, with `--force-with-lease` pinned to the SHA you last pushed or took over, and on any push you did not make, stop and report to the root.
3. **Run owners in parallel off trunk, never stacked,** so each PR lands on its own.
Expand Down
4 changes: 2 additions & 2 deletions skills/poteto-mode/playbooks/multi-phase-plan.md
Original file line number Diff line number Diff line change
Expand Up @@ -56,7 +56,7 @@ Tests alone are not sufficient verification. A PR is verified only when its unit
- [ ] Resolve the forge once. Default to `gh`; if `command -v origin` succeeds and Origin can resolve the repository, use `origin pr` for every PR operation. Record any fallback to `gh`. Never require `gt`.
- [ ] Open the PR ready, never draft, per **Opening a PR**. Use the run's built-in PR tool when it has one, else `origin pr create --status open --base <base-branch>` or `gh pr create --base <base-branch>` according to the resolved forge. A stack child targets its parent branch.
- [ ] Run the repo's lint and typecheck once before the PR-facing push. Push with hooks on.
- [ ] Run `/deslop` before each commit and `/pstack:no-comments` before review.
- [ ] Run `/pstack:deslop` before each commit and `/pstack:no-comments` before review.
- [ ] Triage every Bugbot and security-reviewer comment per `../references/bugbot-triage.md`.
- [ ] Rebase onto current trunk before the code-ready report and babysit. Keep that merge base in fix rounds. Rebase again only at merge prep, on a `git merge-tree` conflict with trunk, on a CI failure that comes from a change on trunk, or when a known concurrent change to the same files lands.

Expand All @@ -68,7 +68,7 @@ Tests alone are not sufficient verification. A PR is verified only when its unit

### Boot recipe, for every live lane

Each live lane runs on its own cloud VM (a `devin --cloud -p` session) or worktree at the PR head. Drive through `control-ui` or `control-cli`.
Each live lane runs on its own cloud VM (`devin --cloud -- "<brief>"` in its own shell session) or worktree at the PR head. Drive through `control-ui` or `control-cli`.

- [ ] `git fetch origin <head-branch> && git checkout <head SHA>`.
- [ ] <Start the backend and the surface. Wait for ready.>
Expand Down
4 changes: 2 additions & 2 deletions skills/poteto-mode/playbooks/opening-a-pr.md
Original file line number Diff line number Diff line change
Expand Up @@ -6,7 +6,7 @@ Invoked at the end of every other playbook.

**Commits.** Commit liberally. Rebase into small, ordered commits before opening PRs. Each commit is a future PR: landable, ordered to tell the story. Amend when the fix belongs in a just-made commit. New commit when separable. Commit bodies don't restate the subject.

**PRs.** Run `/deslop` over the diff before commit and `/pstack:no-comments` before review. Write every PR title, description, and commit body with `/pstack:technical-writing` (every layer except Diátaxis, and apply the STE vocabulary rules: one word per action, keep articles, a plain verb over `-ing` where one works), then apply `/pstack:unslop`.
**PRs.** Run `/pstack:deslop` over the diff before commit and `/pstack:no-comments` before review. Write every PR title, description, and commit body with `/pstack:technical-writing` (every layer except Diátaxis, and apply the STE vocabulary rules: one word per action, keep articles, a plain verb over `-ing` where one works), then apply `/pstack:unslop`.

**Titles.** Conventional Commits `type(scope): subject`, no trailing period. Type such as `feat`, `fix`, `docs`, `refactor`, `test`, `chore`, or `perf`. Scope is the area, such as `pstack` or `poteto-mode`. Subject is short, imperative, and names a real symbol when one carries the change, for example `fix(pstack): retarget opening-a-pr babysit trigger`.

Expand All @@ -31,4 +31,4 @@ After the sections, attach videos or screenshots when they prove a claim. Full S

**Babysit.** Opening a PR does not start a babysit. Post the URL and keep building. Finish the phase or stack first. Run a separate babysit pass only when the user asks for one after the whole stack exists. A babysit for each new PR stalls the build and spends checks on commits later waves restart. Push back when feedback drifts from intent.

A subagent that opens a PR runs `/deslop` and `/pstack:no-comments`, and posts the URL. It returns to the parent without babysitting, unless it is an Autopilot-full or Autopilot-stack owner. That owner's brief assigns the babysit loop and is the ask `playbooks/babysit.md` waits for. The owner starts the loop after its code-ready report, reports merge-ready, and is exempt from the rules here and in `playbooks/babysit.md` that hold babysitting until a whole stack is built.
A subagent that opens a PR runs `/pstack:deslop` and `/pstack:no-comments`, and posts the URL. It returns to the parent without babysitting, unless it is an Autopilot-full or Autopilot-stack owner. That owner's brief assigns the babysit loop and is the ask `playbooks/babysit.md` waits for. The owner starts the loop after its code-ready report, reports merge-ready, and is exempt from the rules here and in `playbooks/babysit.md` that hold babysitting until a whole stack is built.
4 changes: 2 additions & 2 deletions skills/poteto-mode/playbooks/orchestrate.md
Original file line number Diff line number Diff line change
Expand Up @@ -2,12 +2,12 @@

**You run the program, never the code. Decide which agent does each piece of work, then check what each one produces.** For a standing project handed to one coordinator chat: multi-day, many stacked PRs, dozens to hundreds of subagents, few human turns. One task driven to a predicate is Autonomous run. One ambitious run that needs a bespoke workflow is figure-it-out. Work that one agent could finish inside the session's budget is not a program.

Run it with your own tools. Spawn workers with `run_subagent`. Keep the program's state in the current agent's store (path in the system prompt). Watch each PR with PR and CI event subscriptions when your harness has them. Call no scripts, run no polling loops, and never relay messages or status between agents.
Run it with your own tools. Spawn on-machine workers with `run_subagent`. Keep the program's state in the current agent's store (path in the system prompt). Watch each PR with PR and CI event subscriptions when your harness has them. Call no scripts, run no polling loops, and never relay messages or status between agents.

#### Topology

- **One owner per PR.** The owner is the only writer of its branch and carries the PR from build to merge. Only the owner pushes, rebases, or retargets it. Closing or retargeting a base PR orphans every PR above it, so the owner does that only on your call. You never author or edit code. Conflicted merges, chain rebases, and fixes go to owners.
- **A fresh worker for each independent task.** Its kickoff carries everything it needs, including each upstream report it depends on, pasted in full. Workers can't see their siblings. Run workers as a cloud Devin session (`devin --cloud -p "<brief>"`) unless the work needs this machine: a `control-ui` or `control-cli` runtime check, local session transcripts, a simulator, or auth that exists only here. Cloud sessions load plugin skills but not plugin subagent profiles, so a cloud worker cannot spawn `pstack-*` or `pstack:poteto-agent` delegates. Keep cloud workers leaf-level and run anything that fans out locally. Pick each subagent's reasoning level and fast or standard speed for the job, per the Subagents section.
- **A fresh worker for each independent task.** Its kickoff carries everything it needs, including each upstream report it depends on, pasted in full. Workers can't see their siblings. Run workers as their own shell session (`devin --cloud -- "<brief>"`; `run_subagent` has no cloud option) unless the work needs this machine: a `control-ui` or `control-cli` runtime check, local session transcripts, a simulator, or auth that exists only here. Cloud sessions load plugin skills but not plugin subagent profiles, so a cloud worker cannot spawn `pstack-*` or `pstack:poteto-agent` delegates. Keep cloud workers leaf-level and run anything that fans out locally. Pick each subagent's reasoning level and fast or standard speed for the job, per the Subagents section.
- **A sub-coordinator only when one area has many parallel workers.** It owns that area's workers and kickoffs and sends you one rollup, never raw worker reports. Stop at three levels: you, sub-coordinators, and workers. Keep about ten workers in flight per coordinator, and start the next one as each finishes instead of waiting on a whole batch.
- **Fork when new work needs a worker's built state,** such as its checkout, uncommitted changes, or a running process. Message a worker only for a follow-up on the same work. Never message one to check on it, because a message restarts an idle agent.
- **Each PR gets a verifier that isn't its author,** on a different model family. The owner merges only on that verifier's pass at the current head.
Expand Down
Loading
Loading