Harness adapters

Use this skill when a pstack workflow names a delegation action, worklist, question, loop, transcript, or portable resource.

pstack tool names describe intent. Satisfy that intent with the live session's capabilities. Your tool inventory and CLI help are authoritative. Never invent a tool. Report the mechanism when it affects execution or evidence. For worklists, report item state rather than the carrier.

Select the action

Read each selected reference in full before its action. Select only the actions the next step needs. Combine their files when a step needs several actions. Read a link inside a reference only when its described operation applies. Do not read every reference.

Runtime adapters

For spawn or transcript, read only the current runtime column for that action. Other actions need no runtime adapter.

Resolve portable resources

Read the portable resource path contract selected above. Resolve only the roots that the next command needs. Keep the exact command forms in generated plans and restore the recorded roots across owners, delegates, wake-ups, and later ticks.

Preserve roles across handoffs

Read the role resolution and handoffs reference selected above before a role handoff or recovery.

Spawn a role

Read the spawn references and current runtime adapter selected above before resolving or dispatching a role. Keep the caller's role and panel arm count.

The primitives

Use the action table above for spawning, parallelism, read-only execution, structured questions, worklists, loops, and transcripts.

Universal rules

• Use named sibling skills yourself. "Use the architect skill" tells you to load the pstack skill architect and follow it. The name is a sibling directory under the installed skills root, the directory that holds this skill's own directory. Any other pstack mention of a skill by name, such as "the leaf skill", names one the same way. On Claude Code, call the Skill tool with the bare name, such as architect. The call works when the listing shows the name only, with no description, and a name-only listing never means the skill is missing. On Codex, Grok Build, Hermes, and any other harness, read <installed skills root>/<name>/SKILL.md in full, then read the files it references when its steps need them. Never ask the user to type a skill that a pstack skill names. Never edit a skill's files or the listing settings to change how it loads.
• Load only skills that someone named. Never read or load a pstack skill that you found by listing or searching a skills directory, unless the user or a loaded skill named it. A skill that the harness lists with its description can still load from that description.
• Tool names in skill text describe intent, never a required tool. Task, Glob, Grep, Read, a worklist, and Cursor-era parameters like readonly name capabilities: realize each with whatever your session provides (a search tool, a shell command, a read-only brief). Capability selection follows live descriptions, not recalled names. A missing optional tool never cancels the step and needs no announcement. A subagent_type in skill text names a persona or none, and Spawn a role turns it into the concrete type.