pstack-omp
Skill71 starsChanged 27 days agoMITView on GitHub
OMP adapter for poteto-mode. Maps canonical pstack roles and lifecycle protocols to current OMP task agents, batching, isolation, agent:// follow-ups, and durable result resources.
In this repository58 other files it gives its agents.
- architectSkill
- arenaSkill
- automate-meSkill
- benchmark-checklistSkill
- blast-radiusSkill
- broSkill
- correctSkill
- create-formal-verification-skillSkill
- create-verification-skillSkill
- fable-deslopSkill
- figure-it-outSkill
- howSkill
- interrogateSkill
- in-your-own-wordsSkill
- ketchupSkill
- maintain-formal-verification-skillSkill
- maintain-verification-skillSkill
- make-bot-uiSkill
- no-commentsSkill
- orchestrate-ompSkill
- poteto-helpSkill
- poteto-modeSkill
- principle-attack-the-premiseSkill
- principle-boundary-disciplineSkill
- principle-build-the-leverSkill
- principle-encode-lessons-in-structureSkill
- principle-exhaust-the-design-spaceSkill
- principle-experience-firstSkill
- principle-explain-the-numberSkill
- principle-fix-root-causesSkill
- principle-foundational-thinkingSkill
- principle-guard-the-context-windowSkill
- principle-laziness-protocolSkill
- principle-make-operations-idempotentSkill
- principle-migrate-callers-then-delete-legacy-apisSkill
- principle-minimize-reader-loadSkill
- principle-model-the-domainSkill
- principle-never-block-on-the-humanSkill
- principle-outcome-oriented-executionSkill
- principle-prove-it-worksSkill
- principle-redesign-from-first-principlesSkill
- principle-separate-before-serializing-shared-stateSkill
- principle-sequence-verifiable-unitsSkill
- principle-subtract-before-you-addSkill
- principle-test-behavior-not-implementationSkill
- principle-type-system-disciplineSkill
- recallSkill
- reflectSkill
- setup-pstackSkill
- sharpenSkill
- show-me-your-workSkill
- swarmSkill
- tddSkill
- teachSkill
- technical-writingSkill
- typescript-best-practicesSkill
- unslopSkill
- whySkill
The file
Show its rules and text
We split this skill into the rules it gives an agent
22 rules. About 0 are common, 12 are distinctive, and 10 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈12
Distinctive · estimate
This author's own choices. Worth a look.
10
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 14
Use these exact OMP agent names.
- Very specific: line 55
Use security-reviewer for an independent security lane.
- Very specific: line 91
Never put a model field in a task item.
- Very specific: line 93
Keep briefs short and route bulk through local://<name>.md, which parent and children share.
- Distinctive: line 97
Use one batch call for independent participants:
- Distinctive: line 119
Start every participant in one batch before consuming any verdict.
- Very specific: line 127
Read the full result from agent://<id>.
- Very specific: line 128
Read the session transcript from history://<id> when the report is incomplete, ambiguous, or suspicious.
- Very specific: line 132
Call wait only when the root is blocked with nothing else to do.
- Distinctive: line 133
Never steer a reviewer toward a preferred conclusion.
- Distinctive: line 177
Start one task with the mapped agent.
- Very specific: line 180
Read agent://<id>; inspect history://<id> when needed.
- Distinctive: line 190
Start every participant in one batch before consuming any result.
- Distinctive: line 195
Start every independent reviewer in a new batch only after the candidates are frozen.
- Distinctive: line 197
Treat synthesis as advice.
- Distinctive: line 199
Do not mix implementers, reviewers, or synthesizers in one session.
- Very specific: line 203
Start one non-isolated poteto-agent session with the complete owner brief.
- Very specific: line 213
Start one background scout task.
- Distinctive: line 214
Put the exact branch, head SHA, generation, watched predicate, stop predicate, and timebox in the brief.
- Distinctive: line 217
Start a fresh watcher for each new generation.
- Distinctive: line 236
Prefer behavioral proof over type-check-only evidence.
- Very specific: line 245
Do not put a model field in a task item.
≈ “Common” is an estimate: at least 1 in 5 of the 364,980 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
pstack on OMP
poteto-mode is the sole router. It selects the playbook, canonical role, step order, and lifecycle protocol. This adapter translates those choices to OMP only. It never selects a playbook, repeats the playbook index, or changes a playbook gate.
While this skill is active, its role map is the specific pstack execution contract. Generic OMP instructions remain valid outside pstack work.
Canonical role map
Use these exact OMP agent names.
| Canonical role | OMP agent |
explorer | scout |
watcher | scout |
planner | task |
designer | task |
reviewer | reviewer |
researcher | librarian |
synthesizer | reviewer |
implementer | poteto-agent |
owner | poteto-agent |
mechanical | sonic |
Role responsibilities live in skill://poteto-mode. This table only names the agent.
The canonical OMP roster is closed:
scout
reviewer
security-reviewer
librarian
task
sonic
poteto-agent
comment-sicko
seanceA canonically routed task item's agent value must be one of those bundled names. Canonical role labels and model aliases are not agent names. task is the default worker, so omit agent for it.
poteto-agent runs implementer and owner work in poteto's style. comment-sicko audits comments for imported skills that name it directly.
Planning and design
The imported warning about a built-in planning subagent describes a source-host mechanism that bypassed the skill contract. This OMP version has no bundled plan agent and no designer agent. Canonical planner and designer work uses task. The brief carries the specialization, such as technical planning or visual and interaction design, and no source-host subagent fields.
Security review
Use security-reviewer for an independent security lane. Keep it read-only and separate from ordinary code review when both are required. A later reviewer session may synthesize frozen reports; it does not replace the primary security review.
Task contract
The root performs every task call. A child never calls task, starts another child, or asks the user directly. Put Do not call task or start subagents under FORBIDDEN in every child brief. task.maxRecursionDepth permits nesting, so the brief is what keeps the tree flat, not the host.
Children start without the parent conversation. Every prompt must stand alone. They receive the configured workspace, context files, skills, and approved plan resources supplied by OMP.
Call shape
One task call is a batch. context is shared immutable background rendered into every child's system prompt; tasks[] carries the participants. A single dispatch is a one-item batch, not a different schema.
{
"context": "Repository root, base SHA, frozen artifacts, constraints, and verification context shared by every item.",
"tasks": [
{
"name": "ParserOverflowFix",
"solutionSpace": "one fix: bounds check in parse_header, call site given",
"task": "GOAL\n...\n\nROLE\n...\n\nSCOPE\n...\n\nCONTEXT\n...\n\nACCEPTANCE\n...\n\nVERIFY\n...\n\nTIMEBOX\n...\n\nFORBIDDEN\n...\n\nREPORT\n...\n\nSTANDING\n..."
}
]
}Required per item: task and solutionSpace. solutionSpace states how open-ended the child's problem is, not how much work it is: whether the fix is given, or which causes and designs remain open. It never mentions sibling items or coordination.
name is CamelCase, at most 32 characters, unique within the call. It becomes the child's agent:// identifier, so choose a name the root can still recognize an hour later.
Optional fields exist only when their setting is on. Check before writing one:
isolatedrequirestask.isolation.enabledand no plan mode. Use it for a writer that needs a dedicated worktree, then verify the patch, branch, or applied change OMP reports. A long-lived owner that must accept follow-ups in the same workspace stays non-isolated.effort(lo,med,hi) requirestask.enableEffort. When it is off, reasoning depth comes from the agent's configured model role, not from the call.outputSchemaandschemaModerequiretask.structured.toolsexposes eval-defined tools to the child.
Never put a model field in a task item. OMP has none.
Keep briefs short and route bulk through local://<name>.md, which parent and children share. Do not paste a large payload inline.
Batched panel
Use one batch call for independent participants:
{
"context": "Shared immutable repository, base SHA, artifacts, constraints, and verification context.",
"tasks": [
{
"name": "CandidateA",
"solutionSpace": "architecture open; candidate A explores the event-sourced shape",
"task": "Standalone brief for architecture candidate A."
},
{
"name": "CandidateB",
"solutionSpace": "architecture open; candidate B explores the state-machine shape",
"task": "Standalone brief for architecture candidate B."
}
]
}Each name is unique. context contains common immutable material. Each item still names its exact role, slice, acceptance criteria, verification, forbidden work, and report contract.
Start every participant in one batch before consuming any verdict. Separate writers with isolated workspaces or disjoint output paths. Freeze candidate artifacts before starting reviewers. Freeze reviewer reports before starting a separate synthesizer session.
task.maxConcurrency caps simultaneous children at 32 by default; a larger batch queues rather than failing.
Background completion and follow-ups
Spawns run as background jobs and their results auto-deliver. Record the returned job and agent identifiers. The delivered preview may be truncated.
- Read the full result from
agent://<id>. Nested children areagent://<parent>.<child>. - Read the session transcript from
history://<id>when the report is incomplete, ambiguous, or suspicious. read proc://lists live jobs andread proc://<id>inspects one without consuming its delivery.write agent://<id>sends one in-scope correction, answer, authorization, or next coupled phase. It revives a parked session.agent://allbroadcasts and is write-only.write proc://<id>/killcancels stale, superseded, or scope-breaching work.- Call
waitonly when the root is blocked with nothing else to do. Never poll. - Never steer a reviewer toward a preferred conclusion.
- Ignore duplicate terminal deliveries and reject stale artifact generations.
A task result is evidence, not completion. The root inspects the artifact and runs verification.
Brief shape
A dispatch is forbidden until its brief contains:
GOAL
One-sentence outcome executable by a stranger.
ROLE
The canonical role, mapped OMP agent, authority, and expected stance.
SCOPE
Writable and non-writable paths, exact slice or race arm, worktree and branch where applicable, and every output path. State the one-writer assignment.
CONTEXT
Repository root, relevant source paths, base SHA, frozen artifacts, active skill and playbook paths, settled assumptions, and known gotchas.
ACCEPTANCE
Checkable observable outcomes, one per line.
VERIFY
Exact commands, fixtures, runtime probes, comparison baselines, environment requirements, and known false-positive or false-negative risks.
TIMEBOX
A rough cap. At the cap, return partial evidence and stop instead of broadening scope.
FORBIDDEN
At minimum: no child task calls; no subagent spawning; no out-of-scope fixes; no unrequested migrations; no shared-path edits outside ownership; no merge; no direct user questions; no completion claim without executed verification.
REPORT
Require PASS | ISSUES | BLOCKED, semantic session name, branch and exact SHAs where applicable, verdict and evidence, changed files or artifacts, actual verification commands and results, deviations, unresolved risks, and parent actions.
STANDING
Copy the active playbook's standing policy text verbatim when it supplies one.
Canonical protocols
Bounded session
- Author one standalone brief.
- Start one task with the mapped agent.
- Record its semantic name, agent ID, job ID, role, scope, isolation mode, base SHA, and expected artifact.
- Consume the async result when delivered.
- Read
agent://<id>; inspecthistory://<id>when needed. - Send one
write agent://<id>correction only within the same unit. - Inspect the artifact and independently run the promised verification.
- Accept the unit only after the parent verifies the reported output.
A role or unit change requires a fresh task.
Panel
- Partition independent slices or race arms with one task item per participant.
- Start every participant in one batch before consuming any result.
- Track participants by semantic name and identifiers, never arrival order.
- Let results auto-deliver;
waitonly when nothing else can proceed, and cancel an abandoned arm explicitly withwrite proc://<id>/kill. - Ignore duplicate terminal delivery.
- Freeze implementation artifacts, branches, head SHAs, reports, and hashes.
- Start every independent reviewer in a new batch only after the candidates are frozen.
- Freeze verdicts before starting a separate
reviewerwhen synthesis is needed. - Treat synthesis as advice. The root selects and verifies.
Do not mix implementers, reviewers, or synthesizers in one session. Do not let reviewers race a moving head.
Long-lived owner
- Start one non-isolated
poteto-agentsession with the complete owner brief. - Record its agent ID and reuse it. Do not start a sibling owner for the same unit.
- The owner works only in its assigned branch and paths and never starts children.
- Send a
write agent://<id>follow-up only for the next coupled phase, an in-scope correction, an answer resolved from evidence, or explicit authorization. - Require a terminal report at each verification boundary.
- Independently verify the boundary before authorizing the next phase.
- Stand down on ownership violation, stale generation, or terminal scope breach.
One-shot watcher
- Start one background
scouttask. - Put the exact branch, head SHA, generation, watched predicate, stop predicate, and timebox in the brief.
- Require one meaningful event and a terminal report.
- Discard a report whose generation no longer matches.
- Start a fresh watcher for each new generation.
- Stand down when the stop predicate is met or the work is superseded.
A watcher observes. It does not fix, merge, authorize, or silently follow a changed head.
Interactions and decisions
Children resolve uncertainty from source, standing policy, frozen evidence, or the brief. Otherwise they use the safest reversible interpretation and report the assumption, or return BLOCKED with the exact missing decision and evidence gathered.
The root resolves a child question and sends the answer with write agent://<id> to the existing agent. Ask the user only for genuine product preference, unavailable authority, or an irreversible action not covered by standing orders.
Ownership and verification
- One writer per branch, worktree, mutable state, and output path.
- Separate sessions own implementation, review, judgment, and synthesis.
- A task stays inside its assigned unit and role.
- Isolate concurrent writers unless their outputs are structurally disjoint.
- A worker's report never verifies its own work.
- Record branch, base SHA, and exact head SHA or artifact generation.
- Prefer behavioral proof over type-check-only evidence.
- A new commit, restack, conflict resolution, or applied patch creates a new generation that voids the prior verdict.
- Judges and synthesizers advise. The root owns selection, user interaction, external writes, merges, deletion, and final truth.
- Claim model independence only from returned resolved-model and fallback metadata.
Model routing
OMP resolves a task agent through its current settings, including modelRoles, task.agentModelOverrides, the agent definition, and normal fallback. Agent selection and model selection are separate decisions.
Do not put a model field in a task item. Do not use a model alias as the agent value. Configure routing with /skill:setup-pstack, which writes both records into the active profile's config.yml after validating every selector against the detected catalog.
/skill:setup-pstack --show prints the live agent-to-role mapping. These are settings, not task payload fields. When a playbook requires model independence, read the resolved model each child reports; if two panel agents resolve to the same model, say so rather than claiming a second opinion.
Writing
Apply unslop (skill://unslop) to every reply, brief, report, review, task dispatch, commit message, and agent-facing edit.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

