BC model-inventory
Scan the machine for installed AI coding CLIs (claude, codex, gemini, copilot, opencode, ollama), detect whether each account is actually active and which models are usable, and cache the result to ~/.claude/model-inventory.json with role→model routing chains (planner/coder/scout/reviewer/fixer) that goal-runner and autopilot consume to pick the best available model per sub-agent while staying cost-efficient. Three evidence tiers — installed (binary found), likely-authenticated (zero-token credential heuristics), verified (a live one-line probe per model, the only ground truth for "account active and model on the plan"). Use this skill whenever the user says "scan available models", "which models can I use", "what AI CLIs are installed", "refresh the model inventory", "is fable available", "check my model access", or "/model-inventory" — even if they don't name the skill. Not for picking a model mid-task (consumers read the cached file, they don't rescan).
Scan the machine for installed AI coding CLIs (claude, codex, gemini, copilot, opencode, ollama), detect whether each account is actually active and which…
As a process C 58/100 · Has gaps — weak spots: result and completion, inputs and preconditions, running it twice
What is at stake
The skill contains fragments that, in the wrong hands, cost money or data. Below: what the installer risks and what the author should do.
The skill tells the agent to hide things from you: not to show errors, not to mention actions, to report differently from what was done. You lose the ability to see what the agent really did.
Transparency beats a smooth answer. If the goal is to hide technical noise, ask the agent to "summarise briefly", not to "not mention".
How to improve
- Address the high-severity findings: each costs 18 safety points. If one is a false positive, add the rule id to guard.allow in spec.yaml.
- 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 · 1
-
high Concealment
en-hide-from-userSKILL.md:78Instruction to hide actions from the user- ❌ Recording a probe timeout as `unavailable` — a flaky network would silently delete your best model from every chain. Timeout = `unknown`, chain keeps the alias.
Files scanned: 4. 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 58/100
- 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
- 30Running it twice. 3 mutating operations with no state check
- 50Failures and branches. 0 branches, has a failure section
- 60Tools and files. Uses tools (bash) that frontmatter does not declare
- 100Steps. 22 steps
- 100When it triggers. States when to use and when not to
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 1998 tokens
- 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
- +3Description length 970: 120–800 characters recommended
- +3Output format is not stated: the model decides each time
- +1No license
- +2Single-language instructions
- +5Description quotes 8 example trigger phrases
- +4Description says when NOT to use the skill
- +4Structure: 11 headings
- +3Step-by-step instructions: 22 items
- +4Has examples (1 code blocks)
- +4Reference files are cited in the instructions (1 of 1)
- +3All 1 scripts are documented
Quality base 70; lint remarks subtract, signals add up to 100. Result: 97.