AC claw-code
AI Agent Harness Runtime — TypeScript port of Claude Code's harness system. Use when: (1) user asks about claw-code, agent harness, or Claude Code internals; (2) user wants to run claw-code commands or query tool/command registries; (3) routing prompts to commands or tools; (4) bootstrapping agent sessions; (5) parity auditing against original TypeScript archive. Triggers on phrases like "claw-code", "harness runtime", "Claude Code port", "agent harness", "run turn loop", "route prompt".
As a process C 59/100 · Has gaps — weak spots: result and completion, inputs and preconditions, failures and branches
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: 60. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
frontmatter-yamlSKILL.md: the frontmatter is not valid YAML (YAML parse error: Nested mappings are not allowed in compact mappings at line 2, column 14: description: AI Agent Harness Runtime — TypeScript port of Claude Code's harnes… ^ ); fields were read line by line. The usual cause is a colon inside an unquoted value
Process rating: all ten parameters 59/100
- 0Result and completion. Does not say what the result is
- 0Inputs and preconditions. Does not say what the process needs to start
- 0Failures and branches. Linear process with no failure handling
- 0Progress reporting. Says nothing while it works
- 70When it triggers. States when to use, but not when not to
- 100Tools and files. No external tools needed
- 100Steps. 6 steps
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 792 tokens
- 100Running it twice. No mutating operations
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
- -4Absolute local paths (C:\Users, /home/…): not portable
- +1No license
- +2Single-language instructions
- +5Description quotes 6 example trigger phrases
- +3Description length 492: enough signal without eating the budget
- +4Structure: 10 headings
- +3Step-by-step instructions: 6 items
- +4Has examples (8 code blocks)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 75.