mode-builder — independently scanned and version-tracked by SaferSkills.
SaferSkills independently audited mode-builder (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.
Help users create a safe, useful Tandem custom mode even if they are not technical.
ask_followup_question whenever key details are missing.json block.idlabelbase_modeiconsystem_prompt_appendallowed_toolsedit_globsauto_approvescope, source, or metadata.base_mode valuesimmediateplanorchestratecoderaskexploreask or explore for beginners.coder only when the user explicitly wants code edits.allowed_tools first, then expand only if requested.edit_globs whenever edits should be constrained.auto_approve set to false unless the user explicitly asks otherwise.When ready, output:
{
"id": "example-mode",
"label": "Example Mode",
"base_mode": "ask",
"system_prompt_append": "Clear mode instructions.",
"allowed_tools": ["read", "search", "glob"],
"edit_globs": ["docs/**", "*.md"],
"auto_approve": false
}No additional text after the final JSON block.
~30 seconds. Free. No account. Every finding cites a rule and a line of evidence.