AB ai-coding-token-optimizer
Make any repository cheap for an AI agent to work in. Measure the instruction file every session loads, cut it to the rules that bind every task, and move reference material behind short task routers (docs/map/ plus a README next to each code area) that agents open only when a task needs them. Use it when asked to adopt, apply or refresh this skill, or to "map", "optimize tokens" or "slim CLAUDE.md/AGENTS.md" in a project. Also offer it when an entry point grows past about 8 KB. For Codex, Claude Code, OpenClaw and any agent with file access. It edits documentation only, never application behaviour.
Make any repository cheap for an AI agent to work in.
As a process B 69/100 · Nearly there — weak spots: result and completion, inputs and preconditions, progress reporting
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: 16. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- note
frontmatter-keyunknown frontmatter key "homepage"
Process rating: all ten parameters 69/100
- 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
- 70When it triggers. States when to use, but not when not to
- 100Tools and files. No external tools needed
- 100Steps. 55 steps
- 100Failures and branches. 1 branches, has a failure section
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 2829 tokens
- 100Running it twice. Mutating operations check current state
- 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 2 example trigger phrases
- +3Description length 606: enough signal without eating the budget
- +4Structure: 14 headings
- +3Step-by-step instructions: 55 items
- +4Has examples (1 code blocks)
- +4Reference files are cited in the instructions (4 of 6)
- +1License stated
Quality base 70; lint remarks subtract, signals add up to 100. Result: 93.