estimate-ad75fb — independently scanned and version-tracked by SaferSkills.
SaferSkills independently audited estimate-ad75fb (Agent Skill) and scored it 100/100 (green). The audit ran 55 deterministic rules across Security, Supply Chain, Maintenance, Transparency, and Community; it found 0 high-severity and 0 lower-severity findings. The full rule-by-rule trace and per-finding evidence are below. Free, methodology-open.
Findings & checks · 0 flagged
Every scanned point with the score it earned and what moved between them.
First recorded scan — no prior version to compare against.
The primary manifest — the file an agent reads to learn what this artifact does.
The user has asked for a Budgetary estimate. The task description should come from the user's surrounding prompt; if it is missing, ask what they want estimated before doing anything else.
Call the Budgetary `estimate` tool — provided by the bundled budgetary MCP server — passing the task description as the query argument. Show the tool's result to the user verbatim: do not rewrite it, summarize it, or add commentary.
The tool returns a pre-flight token-spend estimate (a token range, a scenario label, and a confidence score) and records the estimate locally. Where there is no firm basis to forecast a particular task it returns no range at all — that abstention IS the result; show it verbatim and do not re-ask with a reworded query, which bills a second estimate. If no API key is configured, the tool returns a short configure-your-key hint instead — show that verbatim too.
Do not call the tool with an empty query, and do not invent a token number yourself: the estimate must come from the tool.
~30 seconds. Free. No account. Every finding cites a rule and a line of evidence.