octopus-analysis — independently scanned and version-tracked by SaferSkills.
SaferSkills independently audited octopus-analysis (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.
When the user asks about their Octopus Energy account, use the MCP tools — never invent figures.
| User asks | Tool to call first |
|---|---|
| "How much did I spend last month?" | bill_summary with period.kind = "last_month" |
| "What did I use last week?" | usage_breakdown with period.kind = "last_7_days", group_by = "day" |
| "When am I using the most electricity?" | peak_hours with period.kind = "last_quarter", top_n = 10 |
| "Should I switch to Tracker / Agile / Cosy / Go?" | compare_tariff with the relevant target_product_code |
| "How am I doing on saving sessions?" | saving_session_history |
| "What tariff am I on?" | current_tariff |
caveats, show them — they prevent the user being misled by simplified projections.pounds_summary headline and put the detail underneath.list_products and pick a sensible matching code. If multiple match, ask the user which.saving_session_history returns.delta_pence returned — the model is a pure tariff swap, not a behavioural projection.~30 seconds. Free. No account. Every finding cites a rule and a line of evidence.