poteto-mode

Files (49)

• SKILL.md
• authoring-a-skill.md · playbooks/
• autonomous-run.md · playbooks/
• autopilot-full.md · playbooks/
• autopilot-stack.md · playbooks/
• babysit.md · playbooks/
• bug-fix.md · playbooks/
• eval.md · playbooks/
• feature.md · playbooks/
• hillclimb.md · playbooks/
• investigation.md · playbooks/
• multi-phase-plan.md · playbooks/
• opening-a-pr.md · playbooks/
• orchestrate.md · playbooks/
• pause-safely.md · playbooks/
• perf-issue.md · playbooks/
• prototype.md · playbooks/
• refactoring.md · playbooks/
• runtime-forensics.md · playbooks/
• session-pickup.md · playbooks/
• shipping.md · playbooks/
• trace-forensics.md · playbooks/
• visual-parity.md · playbooks/
• worktree-cleanup.md · playbooks/
• bugbot-triage.md · references/
• bootstrap.test.ts · scripts/
• bootstrap.ts · scripts/
• bun.lock · scripts/
• check-plan.mjs · scripts/
• check-plan.test.ts · scripts/
• orch.test.ts · scripts/orch/
• orch.ts · scripts/orch/
• store.ts · scripts/orch/
• package.json · scripts/
• cli.test.ts · scripts/watch-pr/
• cli.ts · scripts/watch-pr/
• deadline.test.ts · scripts/watch-pr/
• fakes.test-helper.ts · scripts/watch-pr/
• github.test.ts · scripts/watch-pr/
• github.ts · scripts/watch-pr/
• policy.test.ts · scripts/watch-pr/
• policy.ts · scripts/watch-pr/
• render.ts · scripts/watch-pr/
• tsconfig.json · scripts/watch-pr/
• types.compile.ts · scripts/watch-pr/
• types.ts · scripts/watch-pr/
• watch-pr · scripts/watch-pr/
• worktree-audit.py · scripts/
• worktree-audit.sh · scripts/

SKILL.md (first lines)

# Poteto mode

## Portable activation and boot

Explicit invocation by poteto, /poteto-mode, or a request for this style activates this workflow subject to [workflow ownership](../../references/workflow-ownership.md). Retain the active controller for unqualified follow-ups. Do not replace another controller or run two controllers over one assignment. If both are explicitly requested, clarify ownership before dispatch or writes.

Before any work, read this entire mode, including the Principles index, and the selected playbook in full. Read each applied principle leaf in full this session. A summary does not satisfy these reads. If a required mode, playbook or applied leaf is unavailable, report the exact missing dependency and stop dependent work. Preserve the source metadata and aliases as invocation guidance; they do not register a host mode, icon or custom agent.

Discover operations using [session capabilities](../../references/host-capabilities.md). Follow [assignment and integration](../../references/orchestration-contract.md), [model roles](../../references/model-roles.md) and the [poteto role prompt](../../references/agent-prompts/poteto-agent.md). Observed bindings and user permissions govern execution. Bundled helpers and playbooks supply instructions, not executable host capability. Never install or configure a companion implicitly.

Bundled skills live at `../<name>/SKILL.md` from this file. Give every poteto-role delegate this file's exact absolute path and the full role prompt. The receiving chat owns the selected playbook, checklist and every worker assignment. Never delegate the playbook controller itself.

## Non-negotiables

The Principles section below grounds every trigger. In your reply, name each principle that shaped a decision and the specific choice it changed. Cite only principles whose leaf SKILL.md you read this session.

Remaining triggers:

- At the start of a task, restate the user's goal, the problem and the smallest intended change in your own words. Proceed within authorization without waiting for confirmation. Carry the goal into worker briefs, PR rationale and the final report. When evidence rules out the requested change, show it before proceeding.

- For a nontrivial change, architecture decision, or "are we sure?", use the **how** skill.
- Before using the host's user-question operation on a "which approach", "how should I", or "what should this do" fork, classify it before you ask.

  If the answer is a fact you could observe by running something (behavior, timing, layout, output, perf, even whether an eval separates), it is not the human's to answer.

  Sketch it via the Prototype playbook (`playbooks/prototype.md`) and let the result decide.

  If the task is a read-only Investigation whose deliverable is a cited answer, stay in it and answer from the evidence rather than building a sketch.

  Reserve the question for a genuine product or preference call no experiment can settle.

  Under a full-autonomy grant, decide a call that the grant covers, act on it, and report it, with no reply word and no offer.

  Under the grant, apply a default for a call that only the operator can make.

  Report the default with a full explanation, and say in plain words what the operator could tell you to do instead.

  The operator answers in their own words.

  Never give a shorthand token to type back.

  Gates that the operator named and the Always-pause list in Autonomy still need the operator.
- For any code, name the data shape first, and choose its organizing structure per **principle-model-the-domain**.
- For code crossing a function boundary, use the **architect** skill, parallel design exploration before implementing.
- For parallel fan-out, use the **swarm** skill for coverage matrices, races, gauntlets, and exploration partitions. Use **arena** for design or code bakeoffs with base selection and grafting.
- For contested design, use the **interrogate** skill (multi-model adversarial) before shipping.
- For nontrivial multi-step work, write the throughput checkpoint (Feature step 3).
- For any prose surface, use the **unslop** skill. Your reply is a prose surface. Write it per **Writing the reply**. Agent-facing prose also follows the **create-skill** authoring guidance when that companion is exposed. If unavailable, declare the missing companion and use the bundled Authoring or modifying a skill playbook only as an explicit reduced fallback. Do not claim the absent companion ran.
- For docs, RFCs, readmes, PR descriptions, or commit messages, use the **technical-writing** skill (`/technical-writing`).
- Before commit, use the `deslop` companion from `cursor-team-kit` (`/deslop`) if available. If absent, report the missing gate and obtain an authorized replacement review before claiming it satisfied. Do not install it implicitly.
- Before review, use the **no-comments** companion (`/no-comments`) if available. If absent, disclose the missing gate; this mode's Comments rules remain applicable but do not prove that companion ran.
- When shipping UI / IDE / CLI, use the matching control skill. `cursor-team-kit` publishes `control-cli` for CLIs and TUIs and `control-ui` for browser, Electron and web UIs.

  Discover their availability and the actual exposed control tools.

  Missing tools or companions leave the matching verification blocked; an authorized reduced check must name the surface and its limits.

  For bug fixes, reproduce first on the same surface yourself.

  Hand to the user only under the narrow Bug fix step 1 exception.
- When running a benchmark, measuring perf yourself, or reporting a speedup or regression you measured, use the **benchmark-checklist** skill before you report or act on the number.
- For any PR-status request, use the **Babysit** playbook (`playbooks/babysit.md`).

  Use the bundled routing even if a host companion has a matching description.

  That includes "babysit this", "get it green", "address the bugbot comments", and the commonest phrasing, "check on PR X" / "anything outstanding on X".

  Never triggered by merely opening a PR.

  Declare its mode before polling.

  The playbook's step 1 owns the request-to-mode mapping.

  Reaching for `drive` inside a phase agent stops that agent finishing its turn.
- When asked to land or ship a green stack, use the **Shipping** playbook (`playbooks/shipping.md`). Green is not safe. Nothing gets armed before an independent per-PR verdict, and only the contiguous verified run from the root lands.
- When Bugbot or the agentic security review comments, assess it skeptically. They catch real bugs and also file non-issues and nitpicks, so assess each on its merits and dismiss noise with a concrete reason instead of churning code. Triage fix / dismiss / ask per `references/bugbot-triage.md`.
- Broken skill mid-task, fix it separately within authorized scope and prepare its own PR when PR creation is authorized. Continue independent work. Stop dependent work and disclose the broken contract instead of silently working around it.
- For long, autonomous, or multi-phase work, or any task the user steps away from to review later ("going to bed", "trust it when i'm back", "/loop until X"), keep a decision trail via the **show-me-your-work** skill. Commit it when stakes need an auditable record. Keep it local otherwise.

## Principles

Read the leaf skill in full for any principle you apply. Each entry names when it applies.

**Core**

- **Laziness Protocol** (**principle-laziness-protocol**). Refactoring, sizing a diff, or tempted to add abstractions, layers, or signal threading. Bias to deletion and the smallest change that solves the problem.
- **Foundational Thinking** (**principle-foundational-thinking**). Before writing logic: core types and data structures, scaffold-vs-feature sequencing, what concurrent actors share.
- **Redesign from First Principles** (**principle-redesign-from-first-principles**). Integrating a new requirement into an existing design. Redesign as if it had been foundational from day one.
- **Attack the Premise** (**principle-attack-the-premise**). Two or more fixes that share one premise have failed the same gate. Write the premise down and test it directly before writing another fix that assumes it.
- **Subtract Before You Add** (**principle-subtract-before-you-add**). Sequencing an addition, refactor, or rewrite. Remove dead weight first, then build on the simpler base.
- **Minimize Reader Load** (**principle-minimize-reader-load**). Reviewing or shaping code that's hard to trace. Count layers and hidden state, collapse one-caller wrappers, shrink mutable scope.
- **Outcome-Oriented Execution** (**principle-outcome-oriented-execution**). Planned rewrites and migrations with explicit phase boundaries. Converge on the target architecture, don't preserve throwaway compatibility states.
- **Experience First** (**principle-experience-first**). Product, UX, or feature-scope tradeoffs. Choose user delight over implementation convenience.
- **Exhaust the Design Space** (**principle-exhaust-the-design-space**). A novel interaction or architectural decision with no precedent. Build 2-3 competing prototypes and compare before committing.
- **Build the Lever** (**principle-build-the-lever**). Any non-trivial work. Build the tool that does or proves it (codemod, script, generator), not by hand. The tool is the artifact a reviewer reruns.

**Architecture**

- **Model the Domain** (**principle-model-the-domain**). Writing stateful logic, or code that branches a lot or repeats a shape assumption across files. Encode the domain in a structure (state machine, typed model, table or registry, reducer, boundary, the right collection) instead of scattered conditionals.
- **Boundary Discipline** (**principle-boundary-discipline**). Wiring validation, error handling, or framework adapters. Guards at system boundaries, trust internal types, keep business logic pure.
- **Type System Discipline** (**principle-type-system-discipline**). Designing types or a signature in any typed language. Make illegal states unrepresentable, brand primitives, parse external data at boundaries.
- **Make Operations Idempotent** (**principle-make-operations-idempotent**). Designing commands, lifecycle steps, or loops that run amid crashes and retries. Converge to the same end state.
- **Migrate Callers Then Delete Legacy APIs** (**principle-migrate-callers-then-delete-legacy-apis**). Introducing a new internal API while old callers exist. Migrate and delete in one wave.
- **Separate Before Serializing Shared State** (**principle-separate-before-serializing-shared-state**). Concurrent actors might write the same file, branch, key, or object. Eliminate the sharing first.

**Verification**

- **Prove It Works** (**principle-prove-it-works**). After a task, before declaring done. Verify against the real artifact, not a proxy or "it compiles".
- **Fix Root Causes** (**principle-fix-root-causes**). Debugging. Trace each symptom back to the first place the system went wrong and fix it there. A guard is a fix only when the state it handles is legitimate.
- **Sequence Work into Verifiable Units** (**principle-sequence-verifiable-units**). Multi-step work (sweeps, migrations, runs of similar edits) and how you stack commits and PRs. Break work into small units that each end in a check, verify each before the next, and order delivery so the sequence proves itself.
- **Test Behavior, Not Implementation** (**principle-test-behavior-not-implementation**). Writing, changing, or keeping a test. Assert what the code's users can observe, so the test fails when that behavior breaks and keeps passing when only the internals change.
- **Explain the Number** (**principle-explain-the-number**). Before you trust, report, or act on a number you measured (a speedup, a regression, a throughput, a latency, or an eval result). Find what limits it, and rule out that it measured something other than the work you think.

**Delegation**

- **Guard the Context Window** (**principle-guard-the-context-window**). Context fills up: large outputs, long files, repeated reads, fan-out planning. Route bulk to subagents, keep summaries in the main thread.
- **Never Block on the Human** (**principle-never-block-on-the-human**). Tempted to ask "should I do X?" on reversible work. Proceed, present the result, let the human course-correct.

**Meta**

From yabasha/pstack-openai, MIT.

More from yabasha/pstack-openai