BD agent-optimizer
CLI tool that audits Claude Code, OpenClaw, and Hermes Agent config files for misconfigurations, token waste, security issues, and stale auth. Reads local JSON/Markdown config files only. No data leaves the machine unless you explicitly enroll in optional daily monitoring (summary counts only — see Data & Network Disclosure). No API keys required. Other network calls: one-time license activation and npm update check.
As a process D 43/100 · Unfinished process — 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.
- 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: 2. 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") - note
frontmatter-keyunknown frontmatter key "install"
Process rating: all ten parameters 43/100
- 0Result and completion. Does not say what the result is
- 0Inputs and preconditions. Does not say what the process needs to start
- 20When it triggers. No condition that starts the skill
- 30Running it twice. 8 mutating operations with no state check
- 40Consistency. Frontmatter name (agent-optimizer) differs from the folder (drakon-agent-optimizer)
- 50Failures and branches. 0 branches, has a failure section
- 60Tools and files. Uses tools (bash, web) that frontmatter does not declare
- 85Steps. 22 steps, 1 vague phrases
- 100Execution cost. Instruction body is 2720 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
- +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
- +2Single-language instructions
- +3Description length 420: enough signal without eating the budget
- +4Structure: 9 headings
- +3Step-by-step instructions: 22 items
- +4Has examples (5 code blocks)
- +1License stated
Quality base 70; lint remarks subtract, signals add up to 100. Result: 72.