claude-print — independently scanned and version-tracked by SaferSkills.
SaferSkills independently audited claude-print (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.
Run a non-interactive Claude Code CLI print-mode call from Codex. This is the Codex edition's low-level Claude bridge for one-shot review and consultation prompts.
Default to read-only review:
claude -p --permission-mode dontAsk --allowedTools="Read,Grep,Glob,Bash(git diff:*),Bash(git log:*),Bash(git show:*),Bash(git status:*),Bash(git rev-parse:*),Bash(git ls-files:*)" "<prompt>" < /dev/nullThe Bash allow-list is restricted to read-only git subcommands so peer review cannot mutate the working tree, branches, or remotes. Use broader permissions only when the user explicitly asks Claude to perform write-capable work.
Keep the prompt compact and explicit:
For large context, write the context to .turbo/claude/<tag>-ctx.txt and pipe it:
mkdir -p .turbo/claude
cat .turbo/claude/<tag>-ctx.txt | claude -p --permission-mode dontAsk --allowedTools="Read,Grep,Glob,Bash(git diff:*),Bash(git log:*),Bash(git show:*),Bash(git status:*),Bash(git rev-parse:*),Bash(git ls-files:*)" "<prompt>"Run Claude as a foreground command and wait for the result. Treat a returned session_id from the Codex shell harness as the still-running foreground command; keep polling that session until Claude exits, reaches a clear error, or has had roughly an hour for normal review work.
Do not background Claude print-mode calls, give up during quiet periods, or classify the run as empty while the shell session is still active. The parent workflow needs the complete output before evaluation.
Treat Claude's output as a review signal, not as an authority. Cross-check actionable findings against the codebase before applying fixes.
Then update or check the active plan and proceed to any remaining task.
--dangerously-skip-permissions for peer review..turbo/claude/ for temporary prompt/context files.< /dev/null for non-piped invocations.~30 seconds. Free. No account. Every finding cites a rule and a line of evidence.