BB agent-kill-switch-plan
Prepare, before you need it, the runbook for stopping a proactive agent that is misbehaving: how to pause it in seconds, which connections to revoke in what order, how to check what it did, who to tell, and how to restart safely. Use when asked what to do if my agent goes wrong, make a kill switch plan for Duet, how do I stop my AI agent, my agent sent something it should not have, or prepare an emergency plan for an always-on agent. Produces a one-page runbook with the pause step, the revoke order per connected app, the activity check, message templates for anyone affected, and the restart checklist.
Prepare, before you need it, the runbook for stopping a proactive agent that is misbehaving: how to pause it in seconds, which connections to revoke in what…
As a process B 75/100 · Nearly there — weak spots: when it triggers, running it twice
How to improve
- Your own cases (evals/evals.json, 4–6 real requests with expected answers): the full check would then run those instead of a model-drafted suite.
- A spec.yaml with trigger phrases and assertions — a behaviour contract for CI; `skilltest init` writes a template.
Guard findings · 0
✓ No critical or high findings
Files scanned: 1. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- note
frontmatter-keyunknown frontmatter key "duet"
Process rating: all ten parameters 75/100
- 20When it triggers. No condition that starts the skill
- 30Running it twice. 6 mutating operations with no state check
- 60Result and completion. Output format stated, no completion criterion
- 60Failures and branches. 2 branches
- 70Inputs and preconditions. Inputs and preconditions are listed
- 100Tools and files. No external tools needed
- 100Steps. 24 steps
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 1093 tokens
- 100Progress reporting. Reports progress
- high The skill tells the model to perform an irreversible action with no human approval
Everything here is measured from the skill text rather than judged by a model, so the numbers are checkable. A parameter weighs more when it is a more common reason for the process to stall.
Quality signals
- +5Description has no quoted example phrases that should trigger the skill
- +4Description does not say when NOT to use the skill (false activations)
- +1No license
- +2Single-language instructions
- +3Description length 608: enough signal without eating the budget
- +4Structure: 9 headings
- +3Step-by-step instructions: 24 items
- +3Output format is stated explicitly
- +4Has examples (0 code blocks)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 86.