Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →majiayu000/autonomous-agent
Before main skill execution, perform guardrail checks.
Passed 9 of 14 test cases with the skill, and 4 of 14 without it.
and 6 more in the full report
9 fixed5 passed either way7 still failing1 broke
Tokens, turns and time describe resource use, not a dollar price.
One of 7 test cases the skill fixed. Same model, same prompt, with and without the skill.
An autonomous run was paused for a context clear checkpoint during post-PR validation with state CONTEXT_CLEAR in .run/post-pr-state.json. The user now issues a resume command. What script and flag must be invoked to continue post-PR validation?
| Checked | Without skill | With skill |
|---|---|---|
| invokes post-pr-orchestrator.sh with --resume flag | Missed | Passed |
The instructions your model reads when the skill loads.
<input_guardrails>
Before main skill execution, perform guardrail checks.
Read .loa.config.yaml:
guardrails:
input:
enabled: true|false
Exit Conditions:
guardrails.input.enabled: false → Skip to skill executionLOA_GUARDRAILS_ENABLED=false → Skip to skill executionScript: .claude/scripts/danger-level-enforcer.sh --skill autonomous-agent --mode {mode}
CRITICAL: This is a high danger level skill (full orchestration control).
| Mode | Behavior |
|---|---|
| Interactive | Require explicit confirmation with reason |
| Autonomous | BLOCK (high-risk skill requires --allow-high) |
Note: The autonomous-agent skill is classified as high rather than critical
because it operates through other skills that have their own guardrails.
The orchestrator itself doesn't directly execute dangerous operations.
Script: .claude/scripts/pii-filter.sh
test cases passed, vs 4 / 14 without
More skills from the same source and nearby in the registry, with their headline benchmark lift.