oracle-codex — independently scanned and version-tracked by SaferSkills.
SaferSkills independently audited oracle-codex (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.
Use OpenAI Codex CLI as a read-only oracle — planning, review, and analysis only. Codex provides its perspective; you synthesize and present results to the user.
Sandbox is always `read-only`. Codex must never implement changes.
Parse $ARGUMENTS for:
--reasoning <level> — override reasoning effort (low, medium, high, xhigh). Optional; default is xhigh.Run the check script before any Codex invocation:
scripts/check-codex.shIf it exits non-zero, display the error and stop. Use the wrapper for all codex exec calls:
scripts/run-codex-exec.sh| Setting | Default | Override |
|---|---|---|
| Model | gpt-5.5 | Allowlist only (see references/codex-flags.md) |
| Reasoning | xhigh | --reasoning <level> or user prose |
| Sandbox | read-only | Not overridable |
| Complexity | Effort | Timeout | Criteria |
|---|---|---|---|
| Simple | low | 300000ms | \<3 files, quick question |
| Moderate | medium | 300000ms | 3–10 files, focused analysis |
| Complex | high | 600000ms | Multi-module, architectural thinking |
| Maximum | xhigh | 600000ms | Full codebase, critical decisions |
For xhigh tasks that may exceed 10 minutes, use run_in_background: true on the Bash tool and set CODEX_OUTPUT so you can read the output later.
See references/codex-flags.md for full flag documentation.
$ARGUMENTS for query and --reasoningscripts/check-codex.sh — abort on failurexhigh reasoning effort unless --reasoning overrides itBuild a focused prompt from the user's query and any relevant context (diffs, file contents, prior conversation). Keep it direct — state what you want Codex to analyze and what kind of output you need. Do not implement; request analysis and recommendations only.
Invoke via the wrapper with HEREDOC. Set the Bash tool timeout per the reasoning effort table above.
EFFORT="<effort>" \
CODEX_OUTPUT="/tmp/codex-${RANDOM}${RANDOM}.txt" \
scripts/run-codex-exec.sh <<'EOF'
[constructed prompt]
EOFFor xhigh, consider run_in_background: true on the Bash tool call, then read CODEX_OUTPUT when done.
Read the output file and present with attribution:
## Codex Analysis
[Codex output — summarize if >200 lines]
---
Model: gpt-5.5 | Reasoning: [effort level]Synthesize key insights and actionable items for the user.
~30 seconds. Free. No account. Every finding cites a rule and a line of evidence.