AC harness-design-patterns
Agent harness 架构设计模式知识库。当设计多阶段任务的上下文传递、选择多 agent 协调方式、或规划 hook 系统架构时使用。纯设计指南，无可执行代码。不用于安装 hook 脚本（用 agent-hooks）或运维监控（用 agent-ops）。
As a process C 62/100 · Has gaps — weak spots: when it triggers, inputs and preconditions, failures and branches
How to improve
For the model run — optional
- 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: 16. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- note
frontmatter-keyunknown frontmatter key "triggers"
Process rating: all ten parameters 62/100
- 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
- 20When it triggers. No condition that starts the skill
- 60Result and completion. Output format stated, no completion criterion
- 100Tools and files. No external tools needed
- 100Steps. 12 steps
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 587 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
- +5Description has no quoted example phrases that should trigger the skill
- +4Description does not say when NOT to use the skill (false activations)
- +4No input/output examples
- +2Single-language instructions
- +3Description length 131: enough signal without eating the budget
- +4Structure: 11 headings
- +3Step-by-step instructions: 12 items
- +3Output format is stated explicitly
- +4Reference files are cited in the instructions (12 of 13)
- +1License stated
Quality base 70; lint remarks subtract, signals add up to 100. Result: 87.
External checks
ClawHub: suspicious
This is mostly a documentation-only design guide, but it includes under-scoped guidance to run agent workflows with permission checks bypassed and hooks that read session data.
LLM: suspicious (medium) · VirusTotal: · 29 May 2026