hermes-herdr-loop
Skill0 starsChanged 48 days agoMITView on GitHub
Hand work from the interactive desk to Hermes, with Herdr responsible for watch and recover. Overnight enrichment, multi-hour research sweeps, or any agent run that should outlive a Claude Code session.
In this repository12 other files it gives its agents.
- AGENTS.mdAGENTS.md
- CLAUDE.mdCLAUDE.md
- clay-table-designSkill
- competitor-teardownSkill
- deploy-surface-checkSkill
- fde-handoff-packSkill
- icp-scorecardSkill
- jev-typesafe-briefSkill
- n8n-flow-scaffoldSkill
- signal-to-sequenceSkill
- trigger-job-patternSkill
- weekly-pipeline-pulseSkill
The file
We split this skill into the rules it gives an agent
3 rules. About 0 are common, 1 is distinctive, and 2 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈1
Distinctive · estimate
This author's own choices. Worth a look.
2
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 11
Write a Jev / TypeSafe brief (jev-typesafe-brief) with schema, slug, goals, stop conditions.
- Very specific: line 14
Start the run; record run id in ops/<slug>/SESSION.md.
- Distinctive: line 21
No timeout / no artifact path (runs that vanish)
≈ “Common” is an estimate: at least 1 in 5 of the 364,980 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Skill: hermes-herdr-loop
Hand work from the interactive desk to Hermes, with Herdr responsible for watch and recover.
When to use
Overnight enrichment, multi-hour research sweeps, or any agent run that should outlive a Claude Code session.
Steps
- Write a Jev / TypeSafe brief (
jev-typesafe-brief) with schema, slug, goals, stop conditions. - Define Hermes run config: model/runtime hint, timeout, max steps, artifact output path under
ops/<slug>/agents/. - Define Herdr watch: poll interval, failure threshold, who to notify (human), replay policy.
- Start the run; record run id in
ops/<slug>/SESSION.md. - On completion or failure, Herdr writes a status note; desk operator reviews before any outbound.
- Close the loop by folding results into signal board or enrichment QA, then
/desk-closeif the session ends.
Anti-patterns
- Letting Hermes clear the send fence
- No timeout / no artifact path (runs that vanish)
- Skipping Herdr and "just hoping" overnight jobs finish
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

