AF rl-runtime-guard
Soft, opt-in runtime guardrails for AI agents — advisory reminders injected before each request, never blocking or modifying tool output. Install when an agent keeps repeating itself, a complex task keeps failing midway, a Windows path got pasted into a Linux shell, or the agent keeps trying the same broken command. Easy to disable globally or per-session. Catches 82.5% of common agent errors. Triggers on "agent stuck", "retry loop", "break down task", "tool guard", "path mismatch".
Soft, opt-in runtime guardrails for AI agents — advisory reminders injected before each request, never blocking or modifying tool output.
As a process F 46/100 · Will not run — References files that are not bundled: templates/handler.esm.mjs
How to improve
- The text references files that are not there: add them or drop the references.
- 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: 12. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
missing-refreference to a missing file: templates/handler.esm.mjs - note
frontmatter-keyunknown frontmatter key "triggers"
Process rating: all ten parameters 46/100
- 0Tools and files. 1 referenced file(s) missing: templates/handler.esm.mjs
- 0Result and completion. Does not say what the result is
- 0Inputs and preconditions. Does not say what the process needs to start
- 30Running it twice. 6 mutating operations with no state check
- 50Failures and branches. 0 branches, has a failure section
- 70When it triggers. States when to use, but not when not to
- 100Steps. 21 steps
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 1224 tokens
- 100Progress reporting. Reports progress
- medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
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
- +4Description does not say when NOT to use the skill (false activations)
- +3Output format is not stated: the model decides each time
- +2Single-language instructions
- +5Description quotes 5 example trigger phrases
- +3Description length 487: enough signal without eating the budget
- +4Structure: 10 headings
- +3Step-by-step instructions: 21 items
- +4Has examples (3 code blocks)
- +4Reference files are cited in the instructions (3 of 3)
- +1License stated
Quality base 70; lint remarks subtract, signals add up to 100. Result: 87.