[omh] Policy overlay for terminal commands - add cwd, environment, safety, and result-evidence gates after preferring native shell tools for ordinary CLI, package-manager, and test runs.
SkillScore100Maintained
Automatic
◆DevOps & SRE pack
Last verified 8/18/2026
What it changes
Passed 22 of 22 test cases with the skill, and 3 of 22 without it.
Without skill14%
With skill100%
Checks it passed that the model alone missed
States exit code is not observed
Defines explicit execution timeout
Includes explicit timeout parameter
and 58 more in the full report
19 fixed3 passed either way0 still failing0 broke
Pass-rate lift
+86 pp
Tokens
+55%
Agent turns
0%
Response time
-12%
Model gemini-3.6-flashMeasured 8/18/2026v222 of 22 cases passed with skill
Tokens, turns and time describe resource use, not a dollar price.
See it in action
One of 19 test cases the skill fixed. Same model, same prompt, with and without the skill.
1 of 19
Prompt
Can you prepare a shell command workflow to execute `pnpm test` in `/apps/web`? Give me the structured command task card that defines the command scope, checks if any destructive or network safety gates apply, and specifies the next action without claiming the tests have already run.
What was checked, without and with the skill
Checked
Without skill
With skill
Includes the command_task_card/v1 metadata-only wrapper
Missed
Passed
Includes the command_scope/v1 structure with timeout and stop condition
Missed
Passed
Includes the command_safety_gate/v1 artifact categorizing execution risk
Missed
Passed
Explicitly marks execution output as not observed
Missed
Passed
case-02 · gemini-3.6-flash · 8/18/2026 · answers are capped and redacted
What's inside
The instructions your model reads when the skill loads.
SKILL.md114 linessingle file
Command Operator
This is a Hermes-native command-operator workflow skill.
Why This Exists
command-operator exists so Hermes users can ask for this workflow in chat and receive a structured, evidence-bounded OMH operating surface instead of ad hoc narration.
Do Not Use When
The request is already handled by a narrower explicit skill with stronger evidence.
The user asks OMH to secretly run external platforms, connectors, schedulers, file exports, or runtime agents.
The only safe answer is to ask for missing authority, credentials, target, or observed evidence first.
Examples
Good example:
Prompt: command-operator run npm test in the project terminal and summarize the output.
Expected behavior: Produce prepare_command_operator_card with required context, wrapper actions, and not-evidence boundaries.
Why: The prompt names a real workflow surface that Hermes can orchestrate without hiding execution.
Bad example:
Prompt: command-operator run rm -rf without cwd, confirmation, or observation gates.
Expected behavior: Report the missing observed evidence or authority instead of claiming the external step happened.
Why: Prepared OMH guidance is not platform, runtime, connector, file, memory, or delivery evidence.
Completion Checklist
Command text, working directory, environment assumptions, timeout, safety level, and stop condition are explicit.
Destructive, credential, network, filesystem mutation, install, deploy, and production commands are gated or marked missing.
Exit codes, stdout/stderr, test results, package-manager effects, and filesystem mutations are reported only from observed command evidence.
Recovery Notes
If command text or working directory is missing, ask for the smallest missing scope needed before preparing the command task.
If the command is destructive, credentialed, networked, install/deploy-oriented, or production-affecting, require an explicit confirmation gate.
If the user supplied failed command output and asks for root cause, route to build-failure-triage or agent-debug instead of preparing a fresh command.