Borrowing it
Nothing to install: this file belongs to cedricarlos07/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/cedricarlos07/meta-ads-mcp/main/.github/pre-deploy-guard/SKILL.mdgit clone --depth 1 https://github.com/cedricarlos07/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/cedricarlos07/meta-ads-mcp/pre-deploy-guard)<a href="https://agentmods.dev/skills/cedricarlos07/meta-ads-mcp/pre-deploy-guard"><img src="https://agentmods.dev/badge/skills/cedricarlos07/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/cedricarlos07/meta-ads-mcp/pre-deploy-guard"><img src="https://agentmods.dev/badge/skills/cedricarlos07/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` | This is a copy
100% identical to pre-deploy-guard — 0 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
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 cedricarlos07/meta-ads-mcp (0 stars, last pushed 17d ago), 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). It is 100% identical to pre-deploy-guard, differing in 0 lines, and is treated as a copy.
Other skills, from other repositories
agent-release-swarm
Agent skill for release-swarm - invoke with $agent-release-swarm.
release-announcement
Write a release announcement — changelog, blog post, in-app note, or social post — that leads with user impact, names the audience, and includes upgrade/migration steps without filler.
multi-agent-release-manager
Cleans up the workspace, formats code, runs presubmit checks, and uploads CLs to Gerrit.
release-notes
Generate user-facing release notes from tickets, PRDs, or changelogs. Creates clear, engaging summaries organized by category (new features, improvements, fixes). Use when writing release notes, creating changelogs, announcing product updates, or summarizing what shipped.
pack-submit
Package one of this agent's own skills as a standalone community pack and submit it to the aeon registry as a PR.
updater_guide
Guidance for checking for and installing Row-Bot updates.