¿Qué hace build?
This skill is the entry point for engineering work in code. It takes the place of pstack's poteto-mode. It picks a playbook or a reference. The reference holds the steps.
Before a routed task
- Read
references/poteto-mode/SKILL.ref.mdin full. It is the rulebook. Its Non-negotiables, Principles, Autonomy, Subagents, Writing the reply, and Comments sections apply to every route below. - Where this file and the rulebook differ, follow this file. Follow the user's own instructions (CLAUDE.md, AGENTS.md, the request) over both.
- Before you apply a principle, read its file,
references/principle-<title>/SKILL.ref.md.
Skip the playbook for a small task: a contained one-file change with an obvious test, a short question, or a one-line edit. Verify it on the real artifact all the same.
Routes
Use the first row that fits. Copy the playbook steps into the todo list, as the rulebook says. A bare .md name is a playbook in references/poteto-mode/playbooks/.
| Request | Read |
|---|---|
| "how does X work", a walkthrough, "where should this live" | references/how/SKILL.ref.md, run inside investigation.md |
| "why is X like this", history, where a regression came from | references/why/SKILL.ref.md, run inside investigation.md |
| "are we sure", "X or Y", another read-only question | investigation.md |
| a bug with an unknown cause, "debug this" | bug-fix.md, with references/diagnosing-bugs/SKILL.ref.md (see Choices) |
| a bug with a cheap local test, "write a failing test first" | references/tdd/SKILL.ref.md |
| slow code, a perf regression | perf-issue.md |
| "make this number better" over many attempts | hillclimb.md |
| a live leak, spin, or glitch to diagnose | runtime-forensics.md |
| a captured profile, trace, spindump, or heap snapshot | trace-forensics.md |
| new or changed behavior | feature.md |
| rename, extract, dedupe, or move, with no behavior change | refactoring.md |
| types, signatures, or module shape before code | references/architect/SKILL.ref.md |
| module depth, seams, testability, "deepen this" | references/codebase-design/SKILL.ref.md |
| domain terms, a glossary, an ADR while you design | references/domain-modeling/SKILL.ref.md |
| a fork that a run can settle, "prototype it", "sketch it" | prototype.md |
| pixel-exact parity between two UIs | visual-parity.md |
| review, audit, critique, cleanup, "is this safe to ship" | references/audit.md |
| "interrogate", "tear this apart", adversarial review | references/interrogate/SKILL.ref.md |
| "what could this break", a brief that asserts a fact about code | references/blast-radius/SKILL.ref.md |
| AI slop in a diff | references/deslop/SKILL.ref.md |
| comments to cut | references/no-comments/SKILL.ref.md |
| parallel coverage, a race, a gauntlet | references/swarm/SKILL.ref.md |
| a large or cross-cutting change, or work the user reviews later | references/figure-it-out/SKILL.ref.md |
| "run until done", "loop until X" | autonomous-run.md |
| a plan across phases or stacked PRs | multi-phase-plan.md |
| a queue of PRs to drive with full autonomy | autopilot-full.md, or autopilot-stack.md when the PRs build on each other |
| a multi-day program for one coordinator chat | orchestrate.md |
| resume or take over earlier work | session-pickup.md |
| stop cleanly so that work can resume | pause-safely.md |
| free disk from worktrees and simulators | worktree-cleanup.md |
| a decision trail for long or unattended work | references/show-me-your-work/SKILL.ref.md |
Other h00man skills
-
ship: commit, branch, PR, babysit, CI, merge conflicts, and landing. When a playbook says "Run Opening a PR", or names the Babysit or Shipping playbook, useship. -
verification: a driver or verify skill, formal verification, and the vetting of a benchmark or a measured number. -
writing: docs, PR and commit text, and skill authoring (the Authoring a skill playbook). -
ui: the look of an interface. -
motion: animation and gestures. The model cannot start a command, so tell the user to type it: -
/arenafor a bakeoff, a model or skill benchmark, or the Eval playbook. -
/planto grill an idea into a PRD. -
/variantsfor UI variants that the user can switch between. -
/retrofor a repeated mistake. -
/ambitiousto sharpen a prompt. -
/bruhto restate something in plain words.
Name map
h00man is standalone. Never load a skill or agent from another source, even when the session has one with the same name. Read each name in the references as follows. A name that is not here is not in the stack: do the step with the files in this skill set, and tell the user the gap so that the set can add it.
poteto-mode: this skill. Its rulebook isreferences/poteto-mode/SKILL.ref.md.how,why,architect,tdd,interrogate,swarm,figure-it-out,show-me-your-work,blast-radius,deslop,no-comments,diagnosing-bugs,codebase-design,domain-modeling,in-your-own-words,ketchup,recall,teach,thermos,thermo-nuclear-review,thermo-nuclear-code-quality-review,typescript-best-practices:references/<name>/SKILL.ref.md. A slash form such as/howor/deslopis the same file.arenaas a step of another workflow (architect Phase B, interrogate, Feature step 4, blast-radius step 6): followreferences/arena/SKILL.ref.mdyourself. Send a user who asks for a bakeoff to/arena.- A principle skill (
principle-<title>, or "the principle skill"):references/principle-<title>/SKILL.ref.md. GLOSSARY.mdin domain-modeling: the project's existing glossary. If the project has none, usedocs/CONTEXT.md./planuses the same file.unslop,technical-writing,plugin-dev:skill-development, andautomate-me, with or without a slash: thewritingskill. Forautomate-me, write the habit as an h00man skill with the Authoring a skill playbook.babysit,fix-ci,fix-merge-conflicts, the Opening a PR, Babysit, and Shipping playbooks, and review-bot triage: theshipskill.- The driver skill,
verify,create-verification-skill,maintain-verification-skill,create-formal-verification-skill,maintain-formal-verification-skill,statechart, andbenchmark-checklist(also the link../benchmark-checklist/SKILL.md): theverificationskill. Claude Code's built-inrunstays the fallback driver. correct,reflect, andretro:/retro.sharpen:/ambitious.broand the link../bro/SKILL.md:../bruh/references/pstack-bro.md.setup-pstack: not in the stack. Edit the model sheet by hand (see Models).- A deploy platform's own skill (Railway, Fly, Vercel, and the like): not in the stack. Read the platform CLI's
--helpand its docs before you run it. loop,/loop, andrun: Claude Code built-ins.- The platform maps (
codex-tools.md,copilot-tools.md,pi-tools.md,muse-tools.md,t3-tools.md) name skills of those apps. Readwriting-skillsas thewritingskill andpr-stackas theshipskill, on every platform. Use only their tool and model names.
Paths and agents
- A path such as
skills/poteto-mode/scripts/..."under the installed plugin" isskills/build/references/poteto-mode/scripts/...in this skill set.<plugin>/skills/reflect/scripts/isskills/build/references/reflect/scripts/. - Relative links between references, such as
../how/SKILL.mdor../poteto-mode/references/codex-tools.md, work as written. The name map covers the three broken links:../setup-pstack/,../benchmark-checklist/, and../bro/. - Each upstream
SKILL.mdinreferences/is namedSKILL.ref.md, so that no harness loads it as a skill. When a reference links to aSKILL.md, read theSKILL.ref.mdin that folder. - The scripts need Node.js. The
orchstore and thewatch-prwatcher also need bun. - Subagent types: use
build-agentwhere a reference sayspstack:poteto-agent,comment-sickowhere it sayspstack:comment-sicko, and the agent of the same name inagents/for each pstack thermo agent (thermo-nuclear-review-subagent, and the code quality one,thermo-nuclear-code-quality-review-subagent). Give each thermo agent the absolute path of its rubric,references/thermo-nuclear-review/SKILL.ref.mdorreferences/thermo-nuclear-code-quality-review/SKILL.ref.mdin this skill. - Give each
build-agentandcomment-sickothe absolute path of this file. The comment-sicko finds the how and why references from it. On every platform, a platform map that gives a child a file inpoteto-mode/references/agents/or a thermo skill to read first, or a scoped agent id such aspstack/comment-sicko, means the agent of that name inagents/(pstack/poteto-agentisbuild-agent). A Muse skill idplugin:pstack:<name>means the file that this map gives for<name>: read thebuildskill and read that file, never the pstack id. Its file is../../agents/comment-sicko.md,../../agents/thermo-nuclear-review-subagent.md, or../../agents/thermo-nuclear-code-quality-review-subagent.mdfrom this file.
Models
- Role models come from the sheet
${CLAUDE_CONFIG_DIR:-~/.claude}/agent-models.md, as each reference's Models section says. Where an upstream file namespstack-models.md, readagent-models.md. - To change a role, edit its line by hand, in the form
bug-fix: opus @high. A role without a line keeps the reference's default. On Codex, read the sheet${CODEX_HOME:-~/.codex}/agent-models.md. The sheet is optional: without it, every role keeps its default.
Routing
These rules turn a sheet value into a running agent in any harness. They replace the reference's own slug handling where the two differ.
- Seats and choices. A comma separates the seats of a panel. A
|separates the choices for one seat, in order:codex/gpt-6.1-sol @high | opus @high. A value without|has one choice. - Pick the first choice that runs. Skip a choice when this harness has no route for it (table below). Skip it when the reference rules it out for that seat, such as the arena cross-judge's rule against the parent's model family. Also skip it after it fails: the model is rejected, the account is out of credits, the run errors, or it times out. Then try the next choice.
- Say so. When a seat runs on any choice but its first, name the choice that ran and why the first did not.
- All choices fail. Drop the seat and say so. If that leaves a single-seat role with no seat, run it on the parent model (
inherit-parent) and say so, unless the reference rules out the parent's family for that seat. Then follow the reference, for example arena skips the judge. - Effort.
@levelgoes to the route's effort field:efforton the Claude CodeAgentcall and on aclaudeAgentdelegate,reasoningEfforton acodexdelegate,-c model_reasoning_effort=<level>oncodex exec, and--effort <level>onclaude -p. In T3 Code, pass an option, the fast-mode option included, only whenorchestrator_capabilitieslists it for that model. Some Claude models, such as Fable, have nofastModeand reject a call that sends it.
A T3 Code thread runs on Claude Code or on Codex. Use the column of that harness. In T3, a <provider>/<model> entry always goes through delegate_task.
| Entry | Claude Code (plain or T3) | Codex (plain) | Codex in a T3 thread |
|---|---|---|---|
opus, sonnet, haiku, fable | Agent with model | claude -p --model <alias> | delegate_task to claudeAgent, with the newest model of that family from orchestrator_capabilities |
claudeAgent/<id> | Agent with the alias (claude-fable-5-2 is fable); delegate_task in T3 | claude -p --model <id> | delegate_task |
codex/<id> | codex exec -m <id>; delegate_task in T3 | spawn_agent with model | delegate_task |
inherit-parent, auto | subagent with no model | subagent with no model | subagent with no model |
- CLI routes. Run a review or other read-only seat as
codex exec -m <id> -s read-only -C <repo> -o <file> "<brief>", orclaude -p --model <id> --permission-mode plan "<brief>". A seat that writes code gets-s workspace-writeor the default permission mode, and its own worktree when other seats write too. The brief must stand alone, as for a T3 delegate. Read the result from the output file or stdout. A missing CLI is "no route".
Context budget
Every turn reads the whole context again from the cache, so each item you keep costs again on each later turn. These rules apply to the main session in every route, and they override the rulebook where the two differ. Other h00man skills point here.
- Keep images out of the main session. Send a screenshot, render, or photo comparison to a subagent (
opus @medium). It returns a short text verdict and the image paths, never the pixels. Read an image yourself only when the user asks to see it. - Wait, do not poll. Act on the completion message of a delegate or background task. Do not loop on
task_status,sleep, or a watcher. When a delegate finishes, read its result, not its whole thread. Session pickup still reads the parts of earlier history that it needs. - Cap what a delegate returns. Tell each delegate to return its verdict, the changed files, and the evidence paths in about 20 lines. Long logs go to a file that the delegate names.
- Filter output. Save the full build, test, or log output to a file and keep the command's exit status, for example
cmd > out.log 2>&1; echo "exit $?". Then show only the part you need withtail,grep, orhead. A pipe such ascmd | tailhides a failing exit status. Read a range of a large file, not the whole file. - Orchestrate on a cheaper model. To test a model, run that model as the workers and keep the main session on
opus @medium. Use the strongest model as the main session only for open-ended creative work. - Split a long run into phases. When a run will compact more than once, end each phase with a handoff file: what is done, the evidence, and the next steps. Continue from that file. Start the next phase in a fresh thread only when the user allows new threads; otherwise continue in the current thread and reread the file after each compaction. A handoff file keeps detail that a compaction summary loses.
Choices
- Bug fix. Do bug-fix steps 1 and 2 with diagnosing-bugs Phases 1 to 4: build a repeatable check that fails on the bug, minimize it, rank hypotheses, tag the probes. Then do bug-fix steps 3 to 6. Run the diagnosing-bugs Phase 6 checklist before the commit. Reproduce the bug yourself before you ask the user for anything. Show the ranked hypotheses, but do not wait for an answer.
- Review. Pick by the question. Use
references/audit.mdfor a broad sweep with ranked findings and optional fixes. Use interrogate when each finding needs a run as proof. Use blast-radius for effects outside the diff. A deep audit of a risky diff adds a blast-radius pass on its riskiest change. - Design. Follow architect's flow. Compare its candidates with the codebase-design terms (
depth,seam,adapter,leverage,locality). When the design adds or renames a domain term, update the glossary per domain-modeling. - Hand-off. When the work ships a change, finish with
ship.
Sources
- pstack, by Lauren Tan (poteto), ported to Claude Code by Michael Denyer. Repository: https://github.com/h00mankind/pstack (upstream https://github.com/cursor/plugins/tree/main/pstack). License: MIT. This skill takes the
poteto-moderulebook, its playbooks, references, and scripts; thehow,why,architect,tdd,interrogate,arena,swarm,figure-it-out,show-me-your-work,blast-radius,no-comments,in-your-own-words,ketchup,recall,teach,thermos,thermo-nuclear-review,thermo-nuclear-code-quality-review, andtypescript-best-practicesskills; thereflectscripts; and the 24 principle skills. The hook's trigger rules,build-agent,comment-sicko, and the two thermo-nuclear agents adapt pstack's SessionStart context and itspoteto-agent,comment-sicko, and thermo-nuclear agents. - pstack
deslop, from Cursor's cursor-team-kit (https://github.com/cursor/plugins), MIT, copyright Cursor: the AI-slop cleanup pass. - matt, by Matt Pocock. Repository: https://github.com/mattpocock/skills. License: MIT. This skill takes
diagnosing-bugs(the feedback-loop bug method),codebase-design(deep-module vocabulary), anddomain-modeling(glossary and ADR discipline). - h00man:improve, h00mankind's earlier skill, https://github.com/h00mankind/skills, MIT: the audit areas, modes, checklists, and report format in
references/audit.md.