co-scientist-doctor-f240a0 — independently scanned and version-tracked by SaferSkills.
SaferSkills independently audited co-scientist-doctor-f240a0 (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.
Goal:
Expected input:
Execution steps:
python -m tools.host.claude_project_cli doctoror, when machine-readable output is needed:
python -m tools.host.claude_project_cli doctor --format jsonnode, pnpm)budget, iteration-policy, iteration-band, stop-policy, and human-checkpoint divide responsibilityinspect_state or validation blocked means operationally pnpm --dir apps/dashboard install
pnpm --dir apps/dashboard buildstart, run, and resume commands try a background dashboard bootstrappython -m tools.host.claude_project_cli dashboard <run-dir> resolves the ready dashboard URLruns/<run_id>/dashboard/LINKS.md is the human-readable dashboard receiptbudget controls per-round intensity, while iteration-policy controls semantic vs capped stoppinghuman-checkpoint=auto means completion-driven runs should not pause after every evolution roundinspect_state means review/ranking/evolution artifacts disagree and need repair before resume or overview powershell -File tools/install/install_co_scientist.ps1Rules:
conda run -n <env> python ... over conda activate when the user is running commands through Claude Code shells.fail.~30 seconds. Free. No account. Every finding cites a rule and a line of evidence.