[omh] Hermes Loop workflow: agentic interviewer -> planner -> researcher -> builder -> reviewer cycles until a real gate.
SkillScore91Maintained
Automatic
◆Project Management pack
Last verified 8/27/2026
What it changes
Passed 21 of 23 test cases with the skill, and 6 of 23 without it.
Without skill26%
With skill91%
Checks it passed that the model alone missed
Provides small_loop_guidance in the response.
Includes failure_mode_summary in the response.
Records the situation as an external wait state.
and 22 more in the full report
15 fixed6 passed either way2 still failing0 broke
Pass-rate lift
+65 pp
Tokens
+155%
Agent turns
0%
Response time
-22%
Model gemini-3.6-flashMeasured 8/27/2026v321 of 23 cases passed with skill
Tokens, turns and time describe resource use, not a dollar price.
See it in action
One of 15 test cases the skill fixed. Same model, same prompt, with and without the skill.
1 of 15
Prompt
After native goal activation in Hermes, what command must be executed to ingest metadata-only activation and contiguous turn evidence into loop_cycle/v1 state?
What was checked, without and with the skill
Checked
Without skill
With skill
Specifies `omh loop goal-driver-observe` to ingest host evidence.
Missed
Passed
Stores host observation evidence in loop_goal_driver_observation/v1.
Missed
Passed
case-20 · gemini-3.6-flash · 8/27/2026 · answers are capped and redacted
What's inside
The instructions your model reads when the skill loads.
SKILL.md199 lines3 files
Loop
This is a Hermes-native loop workflow skill.
Why This Exists
loop exists for goals whose correct implementation cannot be known upfront but can be discovered through bounded cycles of definition, action, verification, and revision without confusing planned cycles with observed progress.
Do Not Use When
The user asks for one bounded delivery cycle; use ultrawork's delivery-boundary capability instead.
Scope and milestones are already known and only durable checkpoint/resume tracking is needed; use ultrawork's durable-checkpoint capability.
The user gives only a north-star outcome such as revenue, stars, or adoption and has not accepted a bounded first loop goal.
The goal is too vague to name an observable problem, next artifact, verification signal, or stop condition.
The goal depends mainly on external waiting, adoption, revenue, or community response without observable local next actions.
The permission profile does not allow repeated research, handoff, queue, or feedback cycles.
Examples
Good example:
Prompt: ./loop make OMH a credible Hermes workflow pack with install, docs, QA, and feedback cycles.
Expected behavior: Start a permission-scoped loop, maintain loop_cycle/v1 state, choose the next concrete task, and keep external outcomes as waiting states.
Why: The request is long-horizon and needs repeated discovery, verification, feedback, and resume decisions.
Bad example:
Prompt: ./loop merge this already reviewed one-line README fix.
Expected behavior: Use a direct delivery or PR workflow instead of starting a persistent loop.
Why: The task is bounded and should stop after merge evidence rather than create ongoing cycles.
Completion Checklist
The request is classified as task, project, north-star ambition, external-wait, or unclear before a loop starts.
The current loop_status_card/v1 names the queue item, tick status, verification_plan, and next action.
failure_mode_summary checks verification_gap, comprehension_debt, and cognitive_surrender before progress advances.
Completion is backed by linked goal/runtime evidence; queued loop ticks alone are not observed work.
Native /goal activation and continuation are backed by loop_goal_driver_observation/v1, and each observed role advance is backed by loop_phase_transition/v1.