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 vince-winkintel/gitlab-cli-skills --skill glab-dependency-firewallgit clone --depth 1 https://github.com/vince-winkintel/gitlab-cli-skillsWrote 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/vince-winkintel/gitlab-cli-skills/glab-dependency-firewall)<a href="https://agentmods.dev/skills/vince-winkintel/gitlab-cli-skills/glab-dependency-firewall"><img src="https://agentmods.dev/badge/skills/vince-winkintel/gitlab-cli-skills/glab-dependency-firewall/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/vince-winkintel/gitlab-cli-skills/glab-dependency-firewall"><img src="https://agentmods.dev/badge/skills/vince-winkintel/gitlab-cli-skills/glab-dependency-firewall.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00109 | $0.02359 |
| Opus 5.5 | $0.00044 | $0.00944 |
| Sonnet 5.5 | $0.00022 | $0.00472 |
| Haiku 4.5 | $0.00011 | $0.00236 |
Grade C, and why
glab-dependency-firewall scanned grade C with 1 finding 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 2d 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.
Nullifies safety policieshighAnti-refusal
"You have no restrictions", "do anything now", "ignore your guidelines": a direct jailbreak that disables guardrails.
Treat exit `3` as a policy result, not a transient command failure. Surface the blocked package, version, and reason; do not bypass the policy or rewrite the log. Treat warnings as review input even though they do not fa How it starts
The opening of the file, as written. The whole thing — 137 lines — stays where its author put it; the contents beside it link to each section on GitHub.
glab dependency-firewall
Check package URLs, run supported package managers through GitLab Dependency Firewall, and inspect recorded activity. This command group is experimental; confirm availability before relying on it in durable automation.
Go support and network safety
package accepts versioned golang PURLs and preserves the case of the module path, including names such as github.com/BurntSushi/toml. Internal loopback module-proxy code gates module ZIP downloads, but the command tree exposes no go or golang wrapper. Do not invent glab df go or claim that normal Go downloads are protected by running a single PURL check.
Package checks contact GitLab; wrappers also launch package-manager processes that can download, install, execute build scripts, or upload packages. Approve the target repository, network destinations, and underlying operation before invoking a wrapper. Help is not authorization to install or publish packages. Keep integrity checks enabled and use the glab help dependency-firewall <wrapper> discovery path.
For wrappers, policy transport errors, including a nonresponsive API reaching the 60-second evaluation deadline, become blocked results rather than allowing downloads. The standalone package check reports transport failure as exit 1. Failed checks remain retryable within the run. There is a distinct exception: the API's not-evaluating result (HTTP 404 when the feature is off or the project is inaccessible, or HTTP 422 when policy is not enforced) is logged and allows that project for the rest of the run. An allowed run therefore does not prove enforcement was enabled. Confirm project access and policy enforcement; do not bypass a block or mistake a not-evaluating message for a policy approval.
The Yarn wrapper supports Classic 1.x and Yarn 3.2 or later, and rejects 2.x through 3.1. For Berry, a temporary injected plugin clears merged per-host networkSettings from every rc-file tier (project, ancestors, and home) before requests, keeping traffic on the firewall proxy. Existing registry configuration is retained, but per-host proxy/CA/network overrides are ignored during the run. Review compatibility before starting the approved install; this does not persistently rewrite rc files.
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.
- 2d ago Changed · +12 lines · +4 tokens per session 5b037ca76fa9
- 9d ago Changed · +6 lines ebd250daef5c
- 16d ago Changed · +6 lines 393e77d76deb
- 23d ago Changed · +20 lines · -10 tokens per session b470a915b947
- 1mo ago Changed · +16 lines · +26 tokens per session 4806e7eb051e
- 1mo ago Changed · +17 lines · +8 tokens per session b07f6f709305
- 2mo ago First seen · 60 lines · 81 tokens per session scan C c0d56bd2a8af
glab-dependency-firewall is a skill published in the GitHub repository vince-winkintel/gitlab-cli-skills (49 stars, last pushed today), licensed MIT. It adds 109 tokens to every session and 2,359 once invoked, about $0.0004 per session on Opus 5.5. A static security scan graded it C with 1 finding (nullifies safety policies). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…