BC openclaw-token-optimizer
Find potential token waste in OpenClaw or Hermes Agent. Use when asked to reduce AI costs, review model choices, check large instructions or audit recurring tasks. Explain what matters and suggest safe next steps without changing settings.
Find potential token waste in OpenClaw or Hermes Agent.
As a process C 52/100 · 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: 22. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- note
frontmatter-keyunknown frontmatter key "homepage" - note
frontmatter-keyunknown frontmatter key "source" - note
frontmatter-keyunknown frontmatter key "openclaw"
Process rating: all ten parameters 52/100
- 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
- 60Tools and files. Uses tools (python) that frontmatter does not declare
- 70When it triggers. States when to use, but not when not to
- 100Steps. 9 steps
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 1256 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)
- +3Output format is not stated: the model decides each time
- +4No input/output examples
- -38 of 8 scripts are never mentioned in SKILL.md
- +2Single-language instructions
- +3Description length 239: enough signal without eating the budget
- +4Structure: 8 headings
- +3Step-by-step instructions: 9 items
- +4Reference files are cited in the instructions (3 of 3)
- +1License stated
Quality base 70; lint remarks subtract, signals add up to 100. Result: 79.
In the sandbox The scripts kept to themselves
The skill's scripts were run in a throwaway machine: no network, fake keys in the home directory, a tracer watching. We wrote down what they did. Reaching for the network or for secrets caps the technical grade at C; a quiet run adds no points.
Запущено 8 скриптов; каждому дали двадцать секунд, поддельный домашний каталог с ключами и сеть, в которой ничего нет.
Из них 3 не дошли до работы, и об их поведении мы ничего не узнали.
scripts/context_optimizer.py | не запустился: context_optimizer.py context: error: the following arguments are required: files |
scripts/heartbeat_optimizer.py | ничего за пределами своей папки |
scripts/hermes_adapter.py | ничего за пределами своей папки |
scripts/model_router.py | не запустился: model_router.py route: error: the following arguments are required: --policy, --tier |
scripts/optimize.sh | завершился с кодом 2 |
scripts/optimizer_core.py | ничего за пределами своей папки |
scripts/optimizer.py | не запустился: optimizer.py: error: the following arguments are required: command |
scripts/token_tracker.py | ничего за пределами своей папки |
26 Sept 2026