Cap verbs (the 24-token cloud)

The payoff of a closed verb vocabulary is a load-time guarantee: because every skill, script, and capability must carry a verb from a fixed set, the runtime can check each one is wired to the right kind of executor before your agent ever runs — a mis-declared building block fails at config load, not in the middle of a workflow.

flowgate has three closed-vocabulary verb clouds. They’re disjoint by design:

• Cognitive verbs (10) — govern skills. Verbs that name what the LLM does. See Cognitive verbs.
• Script verbs (12) — govern scripts: entries. Verbs that name what a deterministic script does. See Script verbs.
• Cap verbs (24) — govern cap.* workflow declarations. Verbs that name the role the capability plays in composition. The subject of this page.

Different audience, different rules. Skills name how an LLM thinks. Scripts name deterministic action. Cap verbs name the role of a typed sub-workflow.

The 24-token cloud

Cognitive (10) — LLM is the actor

Verb	Subject root	Examples
triage	cap.triage.*	classify-severity, route-component
diagnose	cap.diagnose.*	parse-error, reproduce, localize
plan	cap.plan.*	draft, vet, fix, track-gaps
implement	cap.implement.*	tdd-loop, scope-bounded
review	cap.review.*	adversarial, final-approval
refactor	cap.refactor.*	draft, extract-module
explain	cap.explain.*	summarize-change, walk-architecture
compose	cap.compose.*	integrate-plans, merge-reports
research	cap.research.*	context-assemble, tool-inventory, lexicon-lookup
summarize	cap.summarize.*	session-delta, lexicon-define

Deterministic (12) — script or MCP tool is the actor

Verb	Subject root	Examples
build	cap.build.*	cargo-release
test	cap.test.*	baseline-snapshot, compare-baseline
deploy	cap.deploy.*	cargo-install
format	cap.format.*	rust-check
lint	cap.lint.*	rust-clippy-strict
install	cap.install.*	npm-ci
verify	cap.verify.*	workspace-green, regression-tests, check-config
run	cap.run.*	cargo-bench
inspect	cap.inspect.*	dependency-tree
search	cap.search.*	codebase-ripgrep
fetch	cap.fetch.*	docs-pull
audit	cap.audit.*	security-scan, mine-transitions

Coordination (2) — neither cognitive nor pure deterministic

Verb	Subject root	Description
gate	cap.gate.*	Awaits a permission signal: HITL approval, evidence quorum, manual acknowledgment.
coordinate	cap.coordinate.*	Side effect to an external system: open a PR, create issues, post a comment.

V6 — primary-executor verb-shape

At config load, the runtime checks each capability’s primary executor — the executor on the transition leaving the capability’s initial state. The check is per-capability, primary-executor only (TRIZ Local Quality resolution): narrow enough to keep the runtime cost negligible, broad enough to catch gross verb misuse.

Verb category	Primary executor must satisfy
Cognitive (10)	kind: mcp OR kind: noop (the noop typically surfaces a skills: ref)
Deterministic (12)	kind: script OR kind: mcp
gate	At least one initial-state transition has actor: human OR purpose: ask
coordinate	kind: mcp (the current check enforces only the kind half; spec §4.1’s external: true connection flag is future work)

Mismatches are config-load errors with the rule code V6 named in the message:

INVALID_PRIMARY_EXECUTOR: capability 'cognitive/cap.plan.draft' (verb 'plan', category
Cognitive) has initial-state transitions whose primary executor kinds are ["script"];
expected kind: mcp OR kind: noop (skill-surfacing) (SPEC §4.1, V6)

The error names the cap, the declared verb, the resolved category, the actual primary kinds, and the expected set. Operators paste-fix without spelunking.

Picking the right verb

The cap verbs and skill verbs share names by design (plan, review, implement, etc.) but they carry different semantics:

• A skill named review.code.adversarial is a guidance fragment the LLM reads.
• A cap named cap.review.adversarial is a sub-workflow whose body invokes the LLM (via kind: noop + skills: [review.code.adversarial]).

The cap binds the skill. The cap verb says “this composition surface is a review-shaped step.” The skill verb says “this guidance is review-shaped advice.” They line up most of the time — cap.review.adversarial references the review.code.adversarial skill — but they’re independent vocabularies.

For deterministic and coordination verbs there’s no skill equivalent. cap.verify.workspace-green is a script invocation. cap.coordinate.pr-open is an MCP call. No LLM guidance needed; the cap is the script body or the MCP tool selection.

Closed enums and amendments

The 24-token cloud is closed. Adding a new verb requires a spec amendment in docs/superpowers/specs/2026-05-26-capability-orchestrator-design.md §4. The closed enum is what makes verb-aware search useful (flowgate.query({kind:"capability", query:"review"}) returns a deterministic set) and what makes V6 surface verb drift loudly at load.

The criterion for a new verb: it has to name a category that’s structurally distinct from every existing verb’s category. “Better word for implement” is not a new verb. “There’s a class of caps that does X and no existing verb describes X without bending the semantics” might be.

Tier discrimination via the cap. prefix

The runtime decides whether to apply cap-verb rules to a workflow by reading its id prefix:

• cap.<verb>.<name> → capability tier; V1–V6, V10, V12, V13, V17, V18 apply.
• flow.<name> → orchestrator tier; V7–V9, V11, V13, V14, V15, V16 apply.
• Anything else → plain workflow (no cap/flow tier); no cap/flow rules apply.

This is the tier check at V2 and V7. The namespace prefix from multi-repo loading is stripped before the check, so cognitive/cap.plan.draft correctly tier-detects as Cap.

What this is not

These aren’t categories of LLM thinking, the way the 10 cognitive verbs are. They’re roles in composition. cap.fetch.docs-pull and cap.research.context-assemble both gather information; the verb difference says “the fetch one is a script call to a known endpoint; the research one is LLM-driven open-ended exploration.” That tier difference shapes the primary executor (V6) and surfaces in the workflow’s audit trail.

For the LLM-thinking taxonomy, see Cognitive verbs. For deterministic action verbs, see Script verbs.