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 ash1794/vibe-engineering --skill vibe-publication-leak-guardgit clone --depth 1 https://github.com/ash1794/vibe-engineeringWrote 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/ash1794/vibe-engineering/vibe-publication-leak-guard)<a href="https://agentmods.dev/skills/ash1794/vibe-engineering/vibe-publication-leak-guard"><img src="https://agentmods.dev/badge/skills/ash1794/vibe-engineering/vibe-publication-leak-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/ash1794/vibe-engineering/vibe-publication-leak-guard"><img src="https://agentmods.dev/badge/skills/ash1794/vibe-engineering/vibe-publication-leak-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 | $0.00109 | $0.01004 |
| Opus 5.5 | $0.00044 | $0.00402 |
| Sonnet 5.5 | $0.00022 | $0.00201 |
| Haiku 4.5 | $0.00011 | $0.00100 |
Grade A, and why
vibe-publication-leak-guard 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 1mo 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 — 60 lines — stays where its author put it; the contents beside it link to each section on GitHub.
vibe-publication-leak-guard
A source-diff scan catches a secret in a commit. It doesn't catch a private field that a server component serializes into the client payload, a draft line that ships in a static JSON route, or a file in public/ that never went through the build. Agents that work from private notes, or draft text in someone's voice, need a guard on what actually ships, plus a way to keep drafts visible for review without ever publishing them.
When to Use This Skill
- Content comes from private sources (notes, journals, internal documents, exports)
- Agents draft copy in the owner's voice, or quote material that needs the owner's sign-off
- Setting up a preview build that shows drafts and a production build that must not
- Before the first production deploy of a content site
When NOT to Use This Skill
- Secret scanning of staged code (use
vibe-pre-commit-audit) - A site with no private inputs and no draft content
- Access control for authenticated content (that's an authorization problem, not a build scan)
Steps
-
Keep raw private context out of git. Raw notes and exports live in a gitignored directory; only distilled, public-safe facts enter the repo. A force-push doesn't purge old commits from a hosted PR, so if something private was ever pushed, plan a squash-merge or a history purge.
-
Gate drafts with a flag, not a comment. Give every item that needs sign-off a stable id and a
needsOk-style flag in the content data. Preview builds render it with a visible WIP marker; production builds drop it. A missing input becomes a pending id, not a blocker. A code comment saying "approved" is not approval, and the guard should fail on it. -
The human owns the approval ledger. Approvals live in a sign-off sheet or file the human edits, with one record per item id. Agents read it before copy work and never write approval states, even when the human says yes in chat. In that case, tell them which item id to mark, and keep the content gated until they do.
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.
- 1mo ago First seen · 60 lines · 109 tokens per session scan A e538aee38bff
vibe-publication-leak-guard is a skill published in the GitHub repository ash1794/vibe-engineering (165 stars, last pushed 22d ago), licensed MIT. It adds 109 tokens to every session and 1,004 once invoked, about $0.0004 per session on Opus 5.5. 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 2026-09-29.
Other skills, from other repositories
feature-verify
Feature verification (READ-ONLY, P0-P5). Use when: verifying feature behavior after deployment, validating API responses, diagnosing production issues, post-deploy smoke test. Not for: modifying data (use feature-dev), code review (use codex-review-fast), writing tests (use codex-test-gen), security audit (use…
post-dev-test
Post-development test completion. Use when: checking test coverage after feature-dev, writing missing integration/e2e tests. Not for: unit test generation (use codex-test-gen), test review (use test-review). Output: test files + coverage report.
test-health
Holistic test coverage measurement. Use when: assessing test health, measuring coverage trends, quantitative + qualitative test audit. Not for: running tests (use verify), reviewing test sufficiency only (use codex-test-review), generating tests (use codex-test-gen). Output: multi-dimensional dashboard with coverage…
test-review
Test coverage review via Codex exec. Use when: reviewing test sufficiency, identifying coverage gaps, test quality audit. Not for: generating tests (use codex-test-gen), code review (use codex-code-review). Output: coverage analysis + gap report.
pre-pr-audit
Pre-PR confidence audit with 5-dimension scoring. Use when: final check before commit/push/PR, evaluating PR readiness, assessing test quality + risk + coverage holistically. Triggers: pre-pr, readiness check, confidence audit, final verification, ready to PR, how confident. Not for: code review (use…
precommit
Pre-commit checks — lint:fix -> build -> test.