Borrowing it
Nothing to install: this file belongs to byadsco/meta-ads-mcp. 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/byadsco/meta-ads-mcp/main/.github/pre-deploy-guard/SKILL.mdgit clone --depth 1 https://github.com/byadsco/meta-ads-mcpWrote 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/byadsco/meta-ads-mcp/pre-deploy-guard)<a href="https://agentmods.dev/skills/byadsco/meta-ads-mcp/pre-deploy-guard"><img src="https://agentmods.dev/badge/skills/byadsco/meta-ads-mcp/pre-deploy-guard/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/byadsco/meta-ads-mcp/pre-deploy-guard"><img src="https://agentmods.dev/badge/skills/byadsco/meta-ads-mcp/pre-deploy-guard.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 | $0.00144 | $0.02311 |
| Opus 5 | $0.00072 | $0.01156 |
| Sonnet 5 | $0.00029 | $0.00462 |
| Haiku 4.5 | $0.00014 | $0.00231 |
Grade B, and why
pre-deploy-guard scanned grade B 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 10d 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.
Reads agent configuration directoriesmediumAgent snooping
.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.
| Hook (`hook-gate.sh`) | PreToolUse hook that *blocks* offending Bash calls | `~/.claude/settings.json` | Copies of this mod
1 near-identical copy found in the catalogue:
- pre-deploy-guard — 100% identical, 0 lines differ
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.
Pre-deploy Guard
This skill protects public open-source repositories from two preventable disasters:
- Secret leakage — once a token, API key or credential is pushed to a public branch, treat it as compromised forever. Rotation is mandatory; deletion of history is best-effort.
- Broken main — for
meta-ads-mcpspecifically, a push tomaintriggers a Cloud Run deploy. There is no PR gate by default, so a broken commit ships to production.
The skill works in concert with three other pieces; understand the picture before touching them:
| Layer | What it does | Where it lives |
|---|---|---|
CLAUDE.md rule |
Stating the policy so any agent reading the repo follows it | committed in repo root |
| This skill | The playbook for how to validate when about to commit/push/deploy | ~/.claude/skills/pre-deploy-guard/ |
pre-deploy-guard agent |
A subagent that runs the same audit and returns a structured report | ~/.claude/agents/pre-deploy-guard.md |
Hook (hook-gate.sh) |
PreToolUse hook that blocks offending Bash calls | ~/.claude/settings.json |
ci.yml workflow |
Server-side defense that runs on every PR/push | .github/workflows/ci.yml |
When to activate
Activate this skill before Claude executes any of the following Bash patterns:
git commit -m …,git commit -am …,git commit --message …git push …(any remote)gcloud run deploy …,gcloud run services replace …docker push …npm publish,pnpm publish,yarn publishgh pr merge …(publishing the work)
The hook will also try to block these calls automatically — but the skill exists so Claude understands why the block happened, what to do, and how to handle false positives without bypassing safety.
If the user says things like "commit and push", "ship it", "deploy", "release", "merge to main": activate this skill before you start running git/deploy commands.
Two modes
| Mode | When | Script | What it runs |
|---|---|---|---|
| quick | before git commit -m |
scripts/quick-checks.sh |
file guard, custom regex secret scan, gitleaks --staged, typecheck. Target <10s. |
| full | before git push, gcloud run deploy, docker push, npm publish |
scripts/run-checks.sh |
quick checks plus lint, full test suite, build. Can take 1-5 min. |
What ships with it
7 files 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.
- 10d ago First seen · 137 lines · 144 tokens per session scan B 26892ae894ae
pre-deploy-guard is a skill published in the GitHub repository byadsco/meta-ads-mcp (14 stars, last pushed today), licensed MIT. It adds 144 tokens to every session and 2,311 once invoked, about $0.0007 per session on Opus 5. A static security scan graded it B with 1 finding (reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
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…
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…
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…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…