Dynamic Workflow

Dynamic Workflow Skill

Runs large fan-out work as a workflow: the plan, the loop and every intermediate result live in a script and on disk, so the parent's context holds only verified results. Covers one-shot fan-outs, adversarial convergence (attempts + refuters), and multi-wave campaigns that integrate dozens of worker branches. It does not make delegate_task durable across restarts; that is the kanban swarm's job.

When to Use

Reach for it when the unit of work is clear (a file, an endpoint, a record) and there are more units than one context can hold. Skip it for under ~10 units or for serial chains. For a refactor or fix campaign on hermes-agent itself, load hermes-agent (the dev workflow) alongside; this skill owns the fan-out shape.

Prerequisites

• delegate_task available and delegation.max_concurrent_children sized for the wave (default 10; the runtime rejects a tasks=[] larger than that with a clear error rather than queueing). delegation.max_spawn_depth >= 2 only if children must fan out themselves.

<!-- no-tmp: ok — explains why a literal /tmp is wrong -->

• A writable run directory resolved from the terminal environment's temp dir ($TMPDIR, else the platform temp dir). Never a literal /tmp: Termux has no such directory and native Windows breaks on it. Use <tmp>/wf_<name>_<uuid>/, unique per run, so an interrupted earlier run cannot leave stale outputs to be misread.
• execute_code for the deterministic layer (only web_search, web_extract, read_file, write_file, search_files, terminal, patch exist inside it).

How to Run

Two layers, split by a real capability boundary:

Do the deterministic part in Layer A first, fan out only the irreducibly-LLM step in Layer B, synthesize on the parent.

Background-first: results re-enter as messages

A top-level delegate_task returns immediately with one handle per task; each child's result re-enters the conversation as a new message when it finishes. You cannot read out_*.csv on the line after the call. Finish whatever does not depend on the children, give a one-line status, and END YOUR TURN; act on each result message as it lands. An ordinary follow-up user message does not cancel children; /stop, /new and process exit do. Only a delegation issued by an orchestrator subagent (depth > 0) is synchronous.

Quick Reference

• Unit must be answerable without sibling output, else it is serial.
• Manifest: one unit per line in <run>/manifest.jsonl; print count + run dir.
• Per child: ~8-12 mechanical edits, or ~2-3k lines of reading, or ~50-70 KB of corpus; size by the LARGEST unit. Structured output goes to files, never the summary field (it truncates under load); delimiter-separated lines over JSON.
• Parent verifies file count and per-run freshness before merging.
• A "stalled" child usually completed its write; check the filesystem first.
• Scoped slice first (one directory, 20 records), report token cost, then scale.

Procedure

One-shot fan-out

1. Decompose into independent units.
2. Layer A pre-pass writes the manifest.
3. Size chunks against the limits above; for more tasks than max_concurrent_children, issue bounded waves yourself.
4. Layer B: one delegate_task(tasks=[...]); each task reads its slice, writes <run>/out_<i>.csv, prints a status word, stops.
5. End the turn. As result messages arrive, read the files, verify, merge; the cross-cutting synthesis stays on the parent.

Adversarial convergence (finding-quality work)

1. Independent attempts: the SAME question to N children (2-4) with DIFFERENT framings in each context, each writing one claim per line to <run>/attempt_<i>.md. Located, individually falsifiable claims only ("POST /api/users/:id/role in src/routes/users.ts:142 has no role check"); a refuter cannot break "the auth layer has problems".
2. Merge and dedupe on the parent; note the agreement count per claim.
3. Refuters: a second batch told to BREAK each claim with counter-evidence, emitting claim_idx|survives|counter_evidence. Give them the sources, not the attempts' reasoning.
4. Surface only survivors; drop refuted claims with a one-line reason.
5. Feed new claims from round 2 through one more refutation; stop when a round adds no survivors, cap at 3 rounds.

The same mechanic protects the parent from its own wrong premises: when you hand children a heuristic ("every patch target on a facade is a dead seam"), tell them to refute it with evidence before acting on it. Four squads doing so turned a 647-site blanket rewrite into 59 real fixes and saved 130+ green tests.