Dynamic Workflows
Plan parallel fan-outs in code with adversarial checks and waves.
Install
npx skills add NousResearch/hermes-agent --skill dynamic-workflow -g -a claude-code -y- Repository
- NousResearch/hermes-agent259k
- Category
- AI and agents
- Updated
- 3d ago
- License
- MIT
- Context cost
- Mediumabout 2,516 tokens
- Runs scripts
- No, instructions only
What it does
Plan-in-code fan-outs, adversarial verification, waves.
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_taskavailable anddelegation.max_concurrent_childrensized for the wave (default 10; the runtime rejects atasks=[]larger than that with a clear error rather than queueing).delegation.max_spawn_depth >= 2only if children must fan out themselves.
- 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_codefor the deterministic layer (onlyweb_search,web_extract,read_file,write_file,search_files,terminal,patchexist inside it).
How to Run
Two layers, split by a real capability boundary:

