BC morgana-anti-infinite-loop-v2-en
Lightweight anti-infinite-loop guard for LLM agents — healing > kill, predictive, zero-dep, 9 layers of protection. Standalone package (stdlib + numpy optional), works with any LLM (Claude/GPT/Llama/Mistral), any harness (Hermes/LangChain/AutoGen/custom). v1 had a modest reception; v2.0 is rebuilt for the community. Note: 12.8K refers to our whole kofna3369 ClawHub profile, not to v1 specifically. English release.
Lightweight anti-infinite-loop guard for LLM agents — healing > kill, predictive, zero-dep, 9 layers of protection.
As a process C 52/100 · Has gaps — weak spots: result and completion, when it triggers, inputs and preconditions
How to improve
- Say in the description WHEN to use the skill ("use when…", example requests): that is the agent's main cue.
- The SKILL.md body is over 5,000 tokens: move reference detail into references/ and load it when needed.
- 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: 20. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
description-no-whendescription does not say WHEN to use the skill (no "use when") - warning
body-longSKILL.md body ≈ 5832 tokens (recommended < 5000); move details to references/ - note
frontmatter-keyunknown frontmatter key "status" - note
frontmatter-keyunknown frontmatter key "date" - note
frontmatter-keyunknown frontmatter key "clawhub_id" - note
frontmatter-keyunknown frontmatter key "language" - note
frontmatter-keyunknown frontmatter key "python" - note
frontmatter-keyunknown frontmatter key "dependencies" - note
frontmatter-keyunknown frontmatter key "optional_dependencies"
Process rating: all ten parameters 52/100
- 0Result and completion. Does not say what the result is
- 0Inputs and preconditions. Does not say what the process needs to start
- 0Progress reporting. Says nothing while it works
- 20When it triggers. No condition that starts the skill
- 30Running it twice. 3 mutating operations with no state check
- 60Tools and files. Uses tools (python) that frontmatter does not declare
- 70Execution cost. Instruction body is 5832 tokens
- 100Steps. 67 steps
- 100Failures and branches. 2 branches, has a failure section
- 100Consistency. Name and required fields are in place
- low 19 top-level sections: this looks like several domains in one skill
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)
- +3Output format is not stated: the model decides each time
- -255 emoji in the instructions: noise for the model
- +2Single-language instructions
- +3Description length 417: enough signal without eating the budget
- +4Structure: 47 headings
- +3Step-by-step instructions: 67 items
- +4Has examples (29 code blocks)
- +1License stated
Quality base 70; lint remarks subtract, signals add up to 100. Result: 58.