Borrowing it
Nothing to install: this file belongs to bex-co/bex-security. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/bex-co/bex-security/main/.claude/skills/merge-upstream-main/SKILL.mdgit clone --depth 1 https://github.com/bex-co/bex-securityWrote 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/bex-co/bex-security/merge-upstream-main)<a href="https://agentmods.dev/skills/bex-co/bex-security/merge-upstream-main"><img src="https://agentmods.dev/badge/skills/bex-co/bex-security/merge-upstream-main/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/bex-co/bex-security/merge-upstream-main"><img src="https://agentmods.dev/badge/skills/bex-co/bex-security/merge-upstream-main.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 | $0.00044 | $0.00828 |
| Opus 5 | $0.00022 | $0.00414 |
| Sonnet 5 | $0.00009 | $0.00166 |
| Haiku 4.5 | $0.00004 | $0.00083 |
Grade A, and why
merge-upstream-main 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 9d 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.
How it starts
The opening of the file, as written. The whole thing — 72 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Merge Upstream Main
Sync this fork from https://github.com/openai/codex-security.git with a Git
merge. Do not rebase or rewrite main.
Inspect The Repository
- Confirm the current repository, branch, worktree, and remotes with
git rev-parse --show-toplevel,git branch --show-current,git status --short --branch, andgit remote -v. - Continue only on
mainwith a clean worktree, including no untracked files. Do not switch branches, stash changes, or discard work automatically. Report the state and ask the user how to proceed when either condition is not met. - Read the applicable
AGENTS.mdinstructions before resolving conflicts or running checks.
Identify The Remotes
- The canonical upstream is the remote whose normalized GitHub repository is
openai/codex-security. Reuse an existing matching remote. If none exists, add it asupstreamwith the canonical URL above when that remote name is available. Ifupstreamalready points elsewhere, stop and ask rather than rewriting it. - The fork remote is the remote tracked by local
main, when that remote is not the canonical repository; otherwise prefer a noncanonicalorigin, then the sole remaining noncanonical remote. - Never select the canonical repository as the fork remote. If no fork remote exists, or multiple candidates make the destination ambiguous, stop and ask the user to identify or configure the fork remote. Do not guess a repository URL or rewrite an existing remote.
Show the selected upstream and fork remote names and URLs before fetching. This guards against pushing the fork merge to the canonical repository.
Use task-specific upstream_remote and fork_remote shell variables for the
selected remote names, and quote their expansions in commands.
Merge And Verify
- Fetch both selected remotes with
git fetch "$upstream_remote"andgit fetch "$fork_remote". - Fast-forward local
mainto the fork's remote-trackingmainwithgit merge --ff-only "$fork_remote/main". If local and forkmainhave diverged, stop and report the commits on each side instead of choosing a history strategy. - Merge upstream with
git merge --no-edit "$upstream_remote/main". A fast-forward is acceptable when the fork has no unique commits. - If conflicts occur, inspect each one and reconcile the fork's behavior with
the upstream change. Do not resolve all conflicts with a blanket
oursortheirsstrategy. Continue the merge only after the result is coherent. - Run the repository checks relevant to the merged or conflict-resolved files. A clean, conflict-free upstream merge does not require inventing new tests.
- Push local
mainwithgit push "$fork_remote" main:mainwithout force. - Fetch both remotes again, then verify:
git merge-base --is-ancestor "$upstream_remote/main" mainsucceeds.git rev-list --left-right --count "$fork_remote/main...main"reports0 0.git status --short --branchis clean.
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 9d ago First seen · 72 lines · 44 tokens per session scan A 2cfd0362f27d
merge-upstream-main is a skill published in the GitHub repository bex-co/bex-security (44 stars, last pushed 2d ago), licensed Apache-2.0. It adds 44 tokens to every session and 828 once invoked, about $0.0002 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
apk-redteam-pipeline
End-to-end Android APK red-team pipeline — automated APK acquisition (Play Store + apkpure + apkmirror fallback), jadx decompilation, secret/URL/JWT/Firebase grep, pinned-cert extraction, exported-component enumeration, Frida runtime instrumentation templates, intent-injection probes. Built from an authorized external…
enterprise-vpn-attack
External SSL VPN / remote-access appliance attack matrix — Cisco ASA/AnyConnect, Fortinet FortiGate/FortiOS, Citrix NetScaler/ADC, Palo Alto GlobalProtect, Pulse Secure / Ivanti Connect Secure, SonicWall, F5 Big-IP. Covers version fingerprinting, CVE matrix (2018-2026), AAA backend identification, default credentials…
hunt-api-misconfig
Hunt API security misconfiguration — mass assignment, prototype pollution, HTTP verb tampering. Mass assignment: send {isadmin:true, role:admin, verified:true} on profile/account/reset endpoints — server blindly applies. JWT signature/crypto forging (alg:none, key confusion, kid/jku) is owned by hunt-jwt-crypto; this…
hunt-ato
Hunt account takeover taxonomy — 9 distinct paths to ATO, plus chains. Paths: (1) password reset flaws (host-header injection redirects token, predictable/numeric token, Referer leak, no-expiry/reuse), (2) email change without re-auth, (3) OAuth account-link CSRF, (4) MFA bypass (per hunt-mfa-bypass), (5) session…
cloud-iam-deep
Cloud IAM red-team attack chain across AWS, Azure, GCP — focused on EXTERNAL exploitation paths and post-credential-discovery privilege analysis. Covers IAM enumeration (aws iam, az role, gcloud iam), STS/AssumeRole chaining, Azure Managed Identity abuse (via SSRF/leak), GCP service account JSON abuse, IMDSv1/v2…
integrate-arcjet-guard-claude-agent-sdk
Integrate Arcjet security into a Claude Agent SDK agent using @arcjet/guard — wrap tool() handlers, screen inbound prompts with UserPromptSubmit, and deny unwrapped built-in/MCP tools with PreToolUse. Use when asked to add Arcjet to a Claude Agent SDK or Claude Code agent, rate limit its tools, screen inbound…