deep-security-scan — Claude Code skill: what it does, how to install
deep-security-scan is a Claude Code skill that runs deep, multi-pass repository security audits, combining findings until consecutive scans reveal nothing new.
Apache-2.0 127 installs ★ 14,254 updated 2026-10-25
npx skills add openai/codex-security --skill deep-security-scan -a claude-codeWhat deep-security-scan does
Workers in the same scan exchange investigation leads and verify each other's evidence, while max_discovery_runs limits total standard scans. The workflow stops when the time limit is reached or findings stop accumulating.
The process resolves targets, inspects setup configurations, and handles concurrent deep scans by checking resource impact on CPU, memory, and tokens. A final report compiles accepted audits into report.md alongside canonical artifacts and usage data.
What it helps with
- run deep multi-pass repository security audits
- merge findings from multiple sequential scans
- inspect active concurrent security processes
- generate a comprehensive security report with artifacts
Example prompts for the agent
- Run a deep security audit on this repository
- Execute a multi-pass vulnerability scan for the project
- Perform an exhaustive security check of the scoped path
How to install deep-security-scan
1Skills CLI (Vercel)
npx skills add openai/codex-security --skill deep-security-scan -a claude-code2Manually: put the files in place
~/.claude/skills/deep-security-scan/SKILL.mdCopy the whole skill folder; for one project use .claude/skills/deep-security-scan/
1Skills CLI (Vercel)
npx skills add openai/codex-security --skill deep-security-scan -a codex2Manually: put the files in place
.agents/skills/deep-security-scan/SKILL.mdFor all projects use ~/.agents/skills/
1Skills CLI (Vercel)
npx skills add openai/codex-security --skill deep-security-scan -a cursor2Manually: put the files in place
.cursor/skills/deep-security-scan/SKILL.mdCursor also reads .agents/skills/ and .claude/skills/
1GitHub CLI
gh skill install openai/codex-security plugins/codex-security/skills/deep-security-scan2Manually: put the files in place
.github/skills/deep-security-scan/SKILL.md1Skills CLI (Vercel)
npx skills add openai/codex-security --skill deep-security-scan -a gemini-cli2Platform CLI
gemini skills install https://github.com/openai/codex-security --path plugins/codex-security/skills/deep-security-scanManually: put the files in place
.devin/skills/deep-security-scan/SKILL.mdThe legacy .windsurf/skills/ path still works
Skills CLI (Vercel)
npx skills add openai/codex-security --skill deep-security-scan -a opencodeClaude.ai
Zip the folder and upload it in Settings → Capabilities → Skills
Step by step, with commands for each platform: How to install skills in Claude Code: five ways
Questions about deep-security-scan
How to install deep-security-scan in Claude Code?
Run npx skills add openai/codex-security --skill deep-security-scan -a claude-code, then check ~/.claude/skills/deep-security-scan/SKILL.md.
What does deep-security-scan do?
It executes repeated security scans on a repository or scoped path, merges findings across passes, and stops when subsequent audits yield no new results.
How does it handle running scans?
It checks for active background tasks, displays their parameters and resource usage impact, and prompts the user for confirmation before proceeding.
Source text
SKILL.md · Apache-2.0
---
name: deep-security-scan
description: Run repeated Standard security scans of a repository or scoped path when the user requests a deep, exhaustive, or multi-pass audit. For changes to a PR, commit, branch or working tree, use security-diff-scan.
---
# Deep Security Scan
The host runs Standard audits and merges their findings. Workers in the same scan can exchange investigation leads and verify each other’s evidence. Later passes receive the titles and locations already reported. The host stops when consecutive audits add nothing new or the configured scan or time limit is reached. Its final report includes every accepted audit.
1. Resolve the authorized target and scope. For a scoped directory use that directory as `targetPath` and `scope: "."`. For a continuation, call `get_codex_security_scan_context` with its `scanId` and supplied `handoffClaimToken`. Use its saved identity and scope. If its mode is Standard or diff, continue with the corresponding scan skill. Follow `../../references/scan-prologue.md` for source access and context updates.
2. For a new target, call `inspect_codex_security_setup({ targetPath, scope: ".", mode: "deep", projectConfigPath? })`. Show the effective settings and their sources. `max_discovery_runs` caps the total number of Standard scans, including when several run together. Pass a project file only when the user selected it. Existing scans use their saved configuration.
3. For a newly launched native scan with a supplied scan ID, inspect `otherRunningDeepScans` in the result of `get_codex_security_scan_context` once. Target-based setup previews have no scan ID. If another Deep scan is active, show its target, phase and human-friendly start time. Explain the additional CPU, memory and token use. Offer **Cancel (Recommended)** and **Continue** using `request_user_input`, then `request_codex_security_user_input` or plain chat if unavailable. Wait for an explicit choice. A dismissed dialog is not a cancellation. Cancel only the new scan if requested.
4. Follow `../../references/access-advisory.md`, then call `start_codex_security_deep_scan({ scanId, handoffClaimToken? })` for an existing scan or `start_codex_security_deep_scan({ targetPath, scope: ".", userContext?, projectConfigPath? })` for a new target. Reuse the project file selected at setup. Await the tool. If the tool runner returns a running cell ID, wait on that cell until it returns the scan result. If the connection closes, rejoin with the same arguments. Report a terminal failure with its saved results. For a policy refusal, identify the worker from its saved error when available. On explicit cancellation call `cancel_codex_security_scan({ scanId })` from the owning thread.
5. For an SDK-owned scan, return the host's scan ID and manifest path so the SDK can finalize it. When the tool returns `completion`, link its generated `report.md` and canonical artifacts. Use `completion.scan.usage` and any separate cost estimate to report usage per `../../references/final-report.md`. Distinguish a completed audit with zero findings from a deadline reached before any audit completed.
© openai · Apache-2.0 · openai/codex-security