Workflow

workflow — multi-phase JS orchestration over provider subagents

Wrong lane? A flat one-shot fan-out of independent tasks → /cc-fleet:subagent; interactive collaboration you message back and forth → /cc-fleet:team; arbitration in cc-fleet-shared/routing.md.

When this skill cites cc-fleet-shared/<file>.md, OPEN it with the Read tool at ../cc-fleet-shared/<file>.md relative to this SKILL.md — the cited content is load-bearing, not optional background.

Execution environment — check before running anything. Confirm your shell tool executes on the host where cc-fleet is installed. In sandboxed or remote agent sessions, a tool named Bash may run on an isolated machine with a different filesystem, PATH, processes, and tmux server — command not found, a healthy-looking doctor whose leaves can't reach your files, or a wrong working directory should prompt you to verify whether you are in a sandbox shell, not conclude that cc-fleet is broken. If so, route commands through a host-executing bridge tool (for example, desktop-commander) and pass host paths for any files you reference; do not retry the same Bash call expecting different results. If no host-executing tool is available, stop and explain that cc-fleet must run on its installation host.

A workflow is a JavaScript script that fans out provider cc-fleet subagent leaves and runs in a cc-fleet process, OFF the main session's context. You write the script; cc-fleet workflow run executes it. The orchestration plan lives in script variables (CPU, ~0 of your tokens) — you are invoked only when authoring the script, not on every scheduling decision. The API mirrors the native Claude Code Workflow tool — write the script exactly as you would a native workflow; the only addition is the provider option on agent().

When to use it

• Multi-phase or dynamic orchestration over many provider subagents: fan-out + barrier, per-item pipeline, loop-until-dry, branch-on-result, with a board run-tree.
• A single flat batch of independent one-shots is not a workflow — that's /cc-fleet:subagent. Don't write a script for it.

The provider ask ladder (ask at most once per task)

1. The user named a provider or model → use it.
2. Else run cc-fleet default --json: if it returns a provider (source "configured" or "auto"), use it and STATE it in your kickoff line (e.g. "using glm (default)").
3. Else (several providers, none default) ask the user ONCE which to use — list the enabled providers from cc-fleet list --json (name + default_model + the one-line note in cc-fleet-shared/providers.md). After they pick, run cc-fleet default <chosen> so you never ask again. (cc-fleet default <p> is user-layer; only run it to FILL a blank default, never with --force.)
4. A mid-task provider failure (insufficient balance / rate limit / auth) → STOP, tell the user what happened, propose the next provider, and WAIT for their confirmation. Never switch providers silently.

Model tier within a provider: fan-out / leaf work → omit --model (or --model fast); judge / synthesis / sustained work → --model strong. The provider's roster decides the actual model — see cc-fleet-shared/providers.md.

In a script, agent()'s opts.provider is optional: omitted, the leaf uses the run's default provider, resolved ONCE at launch and recorded with the run — so --resume stays stable even if the default changes later. A script meant to be shared or reproducible should still pin provider explicitly.

The script API (mirrors the native Workflow tool)

• const meta = {name, description, whenToUse?, model?, phases?: [{title, detail?}]} — a top-level pure literal (no calls/vars/spreads; the native export const meta form is also accepted). name + description are required; model is the default for agents that omit it. Read statically before the run → the board shows the named, phase-skeletoned run immediately.
• agent(prompt, opts) → Promise<string|object> — runs ONE provider subagent leaf. opts.provider is optional (omitted → the run's default provider, above); provider: "claude" runs the official claude CLI on the user's OWN Claude Code login (subscription OAuth) instead of a configured provider — a literal model id (fable/opus/sonnet/a full id, omitted → claude's login default, typically the costliest tier so name one), no roster keywords, no key material. The rest are optional: model, schema, label, phase, timeout (seconds), max_budget_usd, max_turns, isolation: "worktree", profile ("slim" default / "slim-ro" / "full"), tools, skills, mcp. An unknown option key throws (typos fail loudly). On a leaf failure the promise rejects — an un-caught top-level await agent() aborts the run; inside parallel/pipeline a failed element degrades to null. Leaf failures classify like subagent failures — dispatch table in "Leaf failures" below.
  • schema (a plain object) goes to the claude child via --json-schema: claude injects a forced StructuredOutput tool and enforces that it is CALLED (the native mechanism — no JSON instruction is added to the prompt); the promise resolves with the parsed structured payload. The three rules:
    • a validation failure — or a result envelope without a structured payload — FAILS the leaf; there is NO automatic retry;
    • the forced StructuredOutput call costs turns — give a schema'd leaf max_turns ≥ 3 (a budget of 1 starves it);
    • needs claude ≥ 2.1.88 (the slim-profile floor); an older claude fails the leaf with a classified usage error. Client-side validation backstops with a recursive JSON-Schema subset: type (object/array/string/number/integer/boolean/null; integer accepts 5.0), required, nested properties, array items, scalar enum, string pattern (RE2 best-effort — the wire enforces the authoritative ECMA regex) / format (email/uri/uuid/date/date-time), additionalProperties, allOf/anyOf/oneOf, and intra-document $ref (#/… pointers; an external URI is unsupported and fails).
  • isolation: "worktree" runs the leaf with cwd = a fresh git worktree (torn down after), so parallel file-editing leaves don't collide (requires a git repo).
  • profile: "slim" (the default; write-capable) / "slim-ro" (read-only research) / "full" (ONLY to compare against a full session or diagnose a suspected slim regression). Writes files → slim, read-only → slim-ro. tools, skills (default true) and mcp refine a slim leaf, are rejected with profile: "full", and tools REPLACES the whole set, never appends. Tool whitelists / per-profile mcp defaults / the pre-2.1.88 fail-open downgrade: cc-fleet-shared/providers.md. The run journal folds the effective profile + tools, so a --resume re-runs a leaf whose shape changed.
• Background = an unawaited promise. There is no run_in_background/wait(): start a leaf with const p = agent(...), keep working, await p later (Promise.all for a batch). Every leaf — awaited or not — is pool-bounded, journaled at completion, and the run only finalizes after all of them settle. A leaf that rejects with nobody ever handling it fails the run (a silently dropped failure is still a failure); fire-and-forget tolerance is an explicit p.catch(() => null).
• parallel(thunks) → Promise<array> — run each 0-arg thunk concurrently; BARRIER (settles once all finish), null where an element failed: await parallel([() => agent("a", {provider: "glm"}), () => agent("b", {provider: "glm"})]). Concurrent execs stay ~pool size even for a huge list (excess queues).
• pipeline(items, ...stages) → Promise<array> — push each item through all stages independently with NO inter-stage barrier (item A can be in stage 3 while B is in stage 1). Each stage is (prev, item, index) => … (sync or async; its return value is awaited). A failing stage drops that item to null and skips its remaining stages. DEFAULT to pipeline over parallel — only use parallel when a stage genuinely needs ALL prior results together.
• workflow(path, args?) → Promise — run another .js inline on the same engine (shared pool/journal/budget), one level deep only; resolves with the child's top-level return value.
• budget — two parallel cap surfaces. USD: budget.total (the --budget-usd cap in USD, or null), budget.spent(), budget.remaining() (Infinity when uncapped) — USD floats (an Anthropic list-price estimate). Tokens: budget.tokens_total (the --budget-tokens cap, or null), budget.tokens_spent(), budget.tokens_remaining() — ints (input+output, cache-read excluded). agent() throws once either cap is reached; a while (budget.remaining() > N) loop scales depth to the cap. (Native's budget.total is a token target; here it is USD — --budget-usd is the cross-provider cap since providers price tokens differently — and tokens are the separate tokens_* surface.) A provider: "claude" leaf spends the lead session's own subscription window, not a metered provider — use it for one or two synthesis / judgement nodes, never a wide fan-out. Its usage still flows into the run's token / USD surfaces, but the USD is claude's notional list-price (a subscription is not metered per token); max_budget_usd / --budget-usd still gate against that notional figure.
• phase(title, detail?) — name the current phase (tags subsequent agents lacking an explicit phase; the detail shows on the board row). log(msg) — a narrator line (board live log + stderr); console.log/info/warn/error/debug alias onto it (non-strings render as JSON, Errors by message).
• args — the parsed --args-json '<json>' value (or the workflow(child, args) value); undefined when none was given.

What a workflow script can NOT use (determinism — the journal depends on it)

• Date / Math.random() throw; eval / Function / dynamic code are removed; there is no setTimeout / require / fs / ESM import — pass timestamps or randomness in via args.
• Plain script statements only (the body runs inside an async wrapper, so top-level await and return work); async generators (async function*) are not supported.

Running it

RUN=$(cc-fleet workflow run audit.js)        # detached; prints ONLY the bare run id
cc-fleet workflow status "$RUN" --json       # manifest + every tagged leaf (run→phase→agent)
cc-fleet workflow list --json                # all runs, newest first
cc-fleet workflow stop "$RUN"                # reap a running run (engine + in-flight leaves)
cc-fleet workflow stop "$RUN" --leaf <job|label>  # hold ONE agent in place (run keeps going); --phase <title> holds a phase
cc-fleet workflow restart "$RUN" --leaf <job|label>  # re-run a held/running agent in place; --phase <title> a phase;
                                             # on a FINISHED run: keyed re-run (whole run, --leaf, or --phase)
cc-fleet workflow wait "$RUN" --timeout 3m --json  # block silently until the run settles ("Waiting on a run" below)
# or watch the board's Dynamic Workflows view: live log, token/cost columns, prompt/answer drill-in.
# x/r there are level-scoped: run row = the run, Phases pane = the phase, agent pane = the leaf
# (a held agent shows ▶ until you restart it). --foreground runs inline (debug).
# `held` in status output = parked by the control plane: an operator paused it (board
# x, stop --leaf/--phase) or a restart was refused (budget gate); a restart in flight
# may show it briefly. Not an error/retry/backoff — the run waits on it indefinitely.
# If held persists across polls, resume it with restart --leaf/--phase or tell the
# user it is parked; never wait it out.
# --max-concurrency N overrides the default pool (min(16, cores-2));
# --budget-usd N caps total spend; --no-persist-io disables the prompt/answer drill-in.

The run is detached so it outlives this call and your session stays responsive.