Agent skill

Vibe Publication Leak Guard

by ash1794 in ash1794/vibe-engineering

Keeps private and unapproved material out of a public build.

MITAuto-check passed

Install Vibe Publication Leak Guard

skills CLI
$ npx skills add ash1794/vibe-engineering --skill vibe-publication-leak-guard -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install ash1794/vibe-engineering vibe-publication-leak-guard --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/ash1794/vibe-engineering.git skills-src && mkdir -p .claude/skills && cp -r skills-src/plugins/vibe-engineering/skills/vibe-publication-leak-guard .claude/skills/vibe-publication-leak-guard && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
vibe-publication-leak-guard
GitHub stars
163
Token cost
~1.1k tokens
SKILL.md length
604 words
Files
1
Skills in repo
33
Repo updated
First seen
Licence
MIT

At a glance

Keeps private and unapproved material out of a public build.

  • Works in 8 steps: Keep raw private context out of git. Raw… → Gate drafts with a flag, not a comment.… → The human owns the approval ledger.… → …
  • App publishes content that agents drafted
  • SKILL.md covers When to Use This Skill, When NOT to Use This Skill, Steps and Output Format
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Vibe Publication Leak Guard is an agent skill from ash1794/vibe-engineering. Keeps private and unapproved material out of a public build. Scans the built output (HTML, serialized component payloads, client JS and CSS chunks, static data routes, public files) against a private tier that always applies and a draft tier that applies in production. Gates work-in-progress so it shows in preview and is absent from production, and keeps sign-off in a ledger only the human writes. Use when a site or app publishes content that agents drafted or that came from private sources.

Its SKILL.md is about 1.1k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

The repository describes itself as: 33 engineering discipline skills for Claude Code, OpenAI Codex & Gemini CLI + a CLI for CI/CD enforcement. Extracted from real-world multi-agent system development. Born from… The licence is MIT.

When your agent uses it

  • App publishes content that agents drafted
  • That came from private sources

Example prompts

  • “Use the vibe-publication-leak-guard skill to keep private and unapproved material out of a public build”
  • “/vibe-publication-leak-guard”

Workflow steps

8 steps, taken from the first numbered list in SKILL.md.

  1. Keep raw private context out of git. Raw notes and exports live in a gitignored directory; only distilled, public-safe facts enter the…
  2. 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…
  3. 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…
  4. Build the guard over emitted output. After the production build, scan every artifact the server or CDN can serve
  5. Use two tiers.
  6. Hold the denylist outside the repo. Read it from a CI secret plus an untracked local file. Warn locally when it's missing, and fail in CI…
  7. Test the guard. A self-test plants a known leak in each artifact type, plus a known false positive. The guard must catch the first and…
  8. Run it in CI on every push, after the build and before any deploy step. A leak fails the job. Never allowlist a finding to get to green…

What it can do on your machine

Read from SKILL.md and the folder at commit 8f1d71b. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    No scripts in the folder and no shell commands in SKILL.md.

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Vibe Publication Leak Guard loads about 1.1k tokens when it runs. Until then it costs about 131 tokens; SKILL.md has 604 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~131
When it runs · the whole SKILL.md, loaded when a task matches
~1.1k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from ash1794/vibe-engineering at commit 8f1d71b, republished under its MIT licence (© ash1794). 604 words, ~1,108 tokens.

Download SKILL.mdSave it as .claude/skills/vibe-publication-leak-guard/SKILL.md (or your agent's skills folder).
name
vibe-publication-leak-guard
description
Keeps private and unapproved material out of a public build. Scans the built output (HTML, serialized component payloads, client JS and CSS chunks, static data routes, public files) against a private tier that always applies and a draft tier that applies in production. Gates work-in-progress so it shows in preview and is absent from production, and keeps sign-off in a ledger only the human writes. Use when a site or app publishes content that agents drafted or that came from private sources.
user-invocable
true

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

  1. 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.

  2. 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.

  3. 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.

  4. Build the guard over emitted output. After the production build, scan every artifact the server or CDN can serve:

    • rendered HTML and serialized component payloads, including segment files
    • feeds, sitemaps, robots files, and static data routes
    • first-party JS and CSS chunks
    • everything in the public or static directory, which ships verbatim
  5. Use two tiers.

    • Private (always, including preview): private source paths, denylist terms, hashes of sentences the owner rejected.
    • Draft (production only): WIP markers, prompt leftovers, placeholder slots, and every string from items still flagged needsOk.
  6. Hold the denylist outside the repo. Read it from a CI secret plus an untracked local file. Warn locally when it's missing, and fail in CI on the release branch. Suggest categories to fill it with (names, internal program terms, private places, hostnames), because "what goes in the denylist?" is hard to answer cold.

  7. Test the guard. A self-test plants a known leak in each artifact type, plus a known false positive. The guard must catch the first and pass the second.

  8. Run it in CI on every push, after the build and before any deploy step. A leak fails the job. Never allowlist a finding to get to green without writing down why.

Show full SKILL.md (57 more words)Show less

Output Format

Leak Guard Report

Build: [sha] · Mode: production | preview · Denylist: present (N terms) | missing

TierArtifactMatchSource itemAction
draftabout.rscWIP markerq.about.introkeep gated; awaiting sign-off
privatechunks/123.jsdenylist term #4content/people.tsremove field from client props

Pending sign-off: [item ids the human needs to mark] Result: PASS | FAIL (N private, M draft)

© ash1794, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

Just SKILL.md in plugins/vibe-engineering/skills/vibe-publication-leak-guard of ash1794/vibe-engineering.

Open the folder on GitHubat commit 8f1d71b

Compare with similar skills

Vibe Publication Leak Guard next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Vibe Publication Leak Guard compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Vibe Publication Leak Guard this skillash1794/vibe-engineering163—~1.1kAutomated safety check: PassMIT
Scanwshobson/agents40k—~2.2kAutomated safety check: PassMIT
Repo Scanaffaan-m/ECC276k—~1.5kAutomated safety check: PassMIT
Repo Scanaffaan-m/ECC276k—~1.3kAutomated safety check: PassMIT
Safety Guardaffaan-m/ECC277k2 repos~554Automated safety check: NotesMIT
Vulnerability Scanningsickn33/agentic-awesome-skills47k1 repos~2.8kAutomated safety check: PassMIT

Similar skills

  • Scan

    wshobson/agents

    Scans the codebase to generate project-doc.md and AGENTS.md.

    40k GitHub stars~2.2k tokensUpdated 6 days ago
    Agent WorkflowsAuto-check passed
  • Repo Scan

    affaan-m/ECC

    固定されレビュー可能なコミットから外部の repo-scan スキルをインストールするブートストラップ用ポインター。クロススタックのソースコード資産監査を実行する前に repo-scan のインストールが必要な場合に使用する。この ECC ポインター自体は監査を実行しない。

    276k GitHub stars~1.5k tokensUpdated yesterday
    Auto-check passed
  • Repo Scan

    affaan-m/ECC

    用于从固定且可审查的提交安装外部 repo-scan 技能的引导指针。在运行跨栈源代码资产审计前需要安装 repo-scan 时使用;此 ECC 指针本身不执行审计。

    276k GitHub stars~1.3k tokensUpdated yesterday
    Auto-check passed
  • Safety Guard

    affaan-m/ECC

    Guard against destructive operations with three modes: Careful intercepts dangerous commands (rm -rf, git push --force, DROP TABLE) for confirmation, Freeze locks writes to one directory, and Guard…

    277k GitHub starsUsed in 2 repos~554 tokens
    DevelopmentAuto-check: notes
  • Vulnerability Scanning

    sickn33/agentic-awesome-skills

    Scan systems and dependencies for CVEs and security vulnerabilities.

    47k GitHub starsUsed in 1 repo~2.8k tokens
    SecurityAuto-check passed
  • Repo Scan

    affaan-m/ECC

    Bootstrap pointer that installs the external repo-scan skill from a pinned, reviewable commit.

    277k GitHub starsUsed in 1 repo~1.8k tokens
    DevelopmentAuto-check passed

More from ash1794/vibe-engineering

All 33 skills in this repo
  • Vibe Concurrent Test Safety

    ash1794/vibe-engineering

    Audits tests for concurrency safety — race conditions, shared mock state, cleanup ordering.

    163 GitHub stars~665 tokensUpdated 3 days ago
    Auto-check passed
  • Vibe Fuzz Parser Inputs

    ash1794/vibe-engineering

    Generates fuzz test scaffolding for parsers handling external input (YAML, JSON, config files, user input).

    163 GitHub stars~722 tokensUpdated 3 days ago
    Auto-check passed
  • Vibe Golden File Testing

    ash1794/vibe-engineering

    Implements snapshot/golden file tests with temporal normalization so tests don't break daily.

    163 GitHub stars~669 tokensUpdated 3 days ago
    Auto-check passed
  • Vibe Parallel Task Decomposition

    ash1794/vibe-engineering

    Analyzes large tasks for independent subtasks that can be safely parallelized.

    163 GitHub stars~717 tokensUpdated 3 days ago
    Auto-check passed
  • Vibe Slop Filter

    ash1794/vibe-engineering

    Strips AI-generation "smell" from prose before it ships (READMEs, docs, release notes, PR descriptions, posts, emails).

    163 GitHub stars~2.3k tokensUpdated 3 days ago
    Auto-check passed
  • Vibe Spec Sync

    ash1794/vibe-engineering

    Keeps specification documents and code in agreement. An agent skill from ash1794/vibe-engineering.

    163 GitHub stars~2.2k tokensUpdated 3 days ago
    Auto-check passed

Questions about Vibe Publication Leak Guard

What does Vibe Publication Leak Guard do?

Keeps private and unapproved material out of a public build. Vibe Publication Leak Guard is an agent skill from ash1794/vibe-engineering. Keeps private and unapproved material out of a public build.

When should I use Vibe Publication Leak Guard?

Vibe Publication Leak Guard fits situations like: app publishes content that agents drafted; that came from private sources.

How do I install Vibe Publication Leak Guard in Claude Code?

Run `npx skills add ash1794/vibe-engineering --skill vibe-publication-leak-guard -a claude-code`. Or copy the skill folder (plugins/vibe-engineering/skills/vibe-publication-leak-guard in ash1794/vibe-engineering) into .claude/skills/vibe-publication-leak-guard in your project. Claude Code loads it when a task matches its description.

How do I install Vibe Publication Leak Guard in Codex?

Run `npx skills add ash1794/vibe-engineering --skill vibe-publication-leak-guard -a codex`. Or copy the skill folder (plugins/vibe-engineering/skills/vibe-publication-leak-guard in ash1794/vibe-engineering) into .agents/skills/vibe-publication-leak-guard in your project. Codex loads it when a task matches its description.

Can I use Vibe Publication Leak Guard in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add ash1794/vibe-engineering --skill vibe-publication-leak-guard -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/vibe-publication-leak-guard, .gemini/skills/vibe-publication-leak-guard, .github/skills/vibe-publication-leak-guard and .opencode/skills/vibe-publication-leak-guard in your project.

What does Vibe Publication Leak Guard need to run?

SKILL.md names no scripts, command-line tools or credentials: Vibe Publication Leak Guard is instructions for the agent only.

Does Vibe Publication Leak Guard access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Vibe Publication Leak Guard safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Vibe Publication Leak Guard use?

Vibe Publication Leak Guard is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Vibe Publication Leak Guard use?

About 1.1k tokens (SKILL.md is roughly 4.4k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Vibe Publication Leak Guard?

Skills that share tags, products or a category with Vibe Publication Leak Guard: Scan (wshobson/agents, 40k stars), Repo Scan (affaan-m/ECC, 276k stars), Repo Scan (affaan-m/ECC, 276k stars) and Safety Guard (affaan-m/ECC, 277k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Vibe Publication Leak Guard?

ash1794 (a GitHub user) maintains it in ash1794/vibe-engineering, which has 163 GitHub stars. The repository holds 33 skills in this directory. The repository was last updated on October 7, 2026.

Source: ash1794/vibe-engineering on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.