AC token-optimizer
Reduce token usage in AI agent systems (Claude Code, OpenClaw, GPT Codex, Cursor, Windsurf, Aider, etc.) by applying context compression, selective loading, prompt deduplication, caching strategies, and efficient tool definitions. Use when: (1) the user wants to cut AI costs or token burn, (2) optimizing CLAUDE.md, AGENTS.md, system prompts, or skill files for size, (3) designing token-efficient agent architectures, (4) auditing a project or config for context bloat, (5) building skills or prompts that minimize context window usage, (6) asking about context engineering, prompt compression, LLMLingua, compaction, or sub-agent patterns for token savings. Triggers on: "reduce tokens", "optimize tokens", "token usage", "context bloat", "prompt compression", "context engineering", "token audit", "cut costs", "token-efficient", "compact context".
As a process C 56/100 · Has gaps — weak spots: result and completion, inputs and preconditions, consistency
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: 3. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
✓ No remarks against the Agent Skills spec
Process rating: all ten parameters 56/100
- 0Result and completion. Does not say what the result is
- 0Inputs and preconditions. Does not say what the process needs to start
- 30Running it twice. 3 mutating operations with no state check
- 40Consistency. Frontmatter name (token-optimizer) differs from the folder (lean-context)
- 60Tools and files. Uses tools (bash) that frontmatter does not declare
- 60Failures and branches. 2 branches
- 100Steps. 50 steps
- 100When it triggers. States when to use and when not to
- 100Execution cost. Instruction body is 2320 tokens
- 100Progress reporting. Reports progress
- low 12 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
- +4Description does not say when NOT to use the skill (false activations)
- +3Description length 852: 120–800 characters recommended
- +3Output format is not stated: the model decides each time
- +1No license
- +2Single-language instructions
- +5Description quotes 10 example trigger phrases
- +4Structure: 16 headings
- +3Step-by-step instructions: 50 items
- +4Has examples (9 code blocks)
- +4Reference files are cited in the instructions (1 of 1)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 90.