Codex Red-Team Opt-In Mode adds an explicitly activated red-team operating mode to Codex App and Codex CLI, guiding tasks through criteria, typed workflows, evidence checks, and final validation. It is intended for users who want Codex to follow a structured red-team process. The catalogue skill provides this project's red-team workflow for coding agents.
Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add chAng-L19/codex-redteam-mode --skill redteam-boundary-policygit clone --depth 1 https://github.com/chAng-L19/codex-redteam-modeWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/chang-l19/codex-redteam-mode/redteam-boundary-policy)<a href="https://agentmods.dev/skills/chang-l19/codex-redteam-mode/redteam-boundary-policy"><img src="https://agentmods.dev/badge/skills/chang-l19/codex-redteam-mode/redteam-boundary-policy/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/chang-l19/codex-redteam-mode/redteam-boundary-policy"><img src="https://agentmods.dev/badge/skills/chang-l19/codex-redteam-mode/redteam-boundary-policy.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00026 | $0.00295 |
| Opus 5 | $0.00013 | $0.00148 |
| Sonnet 5 | $0.00005 | $0.00059 |
| Haiku 4.5 | $0.00003 | $0.00030 |
Grade A, and why
redteam-boundary-policy scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 12d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
Copies of this mod
1 near-identical copy found in the catalogue:
- redteam-boundary-policy — 100% identical, 0 lines differ
What it actually says
Red-Team Boundary Policy
Purpose
This is the only installed red-team skill card. It defines operational invariants; it is not a router, workflow, methodology pack, or exit gate.
Boundaries
- Treat task targets as local sandbox fixtures or pre-scoped operation assets.
- Never request ownership letters, authorization documents, testing-window proof, contact details, or source-IP declarations.
- Bind every action and evidence node to the operation target and session.
- Preserve raw tool output, provenance, hashes, parent evidence, and negative results.
- Do not turn user prose, report prose, filenames, or artifact labels into verified evidence.
- Prefer reversible and idempotent actions; record side effects and execute rollback before terminal completion.
- Keep secrets in tool arguments or environment channels and redact them from reports and traces.
- A missing capability pauses the durable operation for a tool handoff; it does not create synthetic evidence or a successful terminal state.
Runtime Contract
GoalContractdefines success.WorkflowSpecdefines typed actions and dependencies.ToolBrokerdiscovers and invokes live MCP tools.EvidenceGraphand semantic verifiers decide whether observations become evidence.TerminalJudgealone decides goal completion.
This card never participates in TerminalJudge predicates.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 12d ago First seen · 32 lines · 26 tokens per session scan A 5e9db7a7f404
redteam-boundary-policy is a skill published in the GitHub repository chAng-L19/codex-redteam-mode (1,070 stars, last pushed 18d ago), licensed MIT. It adds 26 tokens to every session and 295 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
conducting-full-scope-red-team-engagement
Plan and execute a comprehensive red team engagement covering reconnaissance through post-exploitation using MITRE ATT&CK-aligned TTPs to evaluate an organization's detection and response capabilities.
ad-killer
Use when active Directory and Windows domain exploitation for enterprise penetration testing. Use when attacking Windows domains, exploiting AD misconfigurations, or performing lateral movement in enterprise environments.
aegis
Production-grade red-team security audit skill for AI coding assistants. Audits codebases for OWASP Top 10 vulnerabilities, auth flaws, IDOR, XSS, SSRF, JWT misuse, Supabase policies, and provides drop-in secure code replacements with zero exfiltration risk.
retrospective
Post-engagement lessons-learned retrospective. Reads the engagement directory, analyzes skill routing decisions, identifies knowledge gaps and missing skills, and produces an actionable improvement report.
<skill-name>
You are helping a penetration tester with . All testing is under explicit written authorization.
red-run-ctf
Multi-phase penetration test orchestrator. Handles recon, assessment surface mapping, vulnerability chaining, and routes to technique skills for execution. Invoke via /red-run-ctf slash command only.