ai-agentic-coding-template_unified: Skill for Claude Code

.ai/adapters/claude-code/skills/repo-guard/SKILL.md

repo-guard is a skill for Claude Code from Zenobia0000/ai-agentic-coding-template_unified. It costs 19 tokens per session (527 once invoked), scanned C, a copy of repo-guard, MIT.

A repository safety guard that checks for dangerous commands, exposed secrets, risky files, and direct changes to protected branches.

In plain words
What is it for?
Use it while editing files, running shell commands, or using Git to detect secrets, block destructive operations, protect branches, and warn about large or generated files.
Why use it?
It helps prevent accidental data loss, credential leaks, unsafe permissions, and changes made directly to main, master, or production branches.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter. Also seen: mentions Claude Code; mentions Gemini CLI.

This is Zenobia0000/ai-agentic-coding-template_unified's own configuration. It tells Claude Code how to work on ai-agentic-coding-template_unified itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything ai-agentic-coding-template_unified configures →

Reuse

Borrowing it

Nothing to install: this file belongs to Zenobia0000/ai-agentic-coding-template_unified. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/Zenobia0000/ai-agentic-coding-template_unified/main/.ai/adapters/claude-code/skills/repo-guard/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/Zenobia0000/ai-agentic-coding-template_unified

Made for: Claude Code.

Wrote 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.

agentmods badge for repo-guard

README.md
[![agentmods](https://agentmods.dev/badge/skills/zenobia0000/ai-agentic-coding-template_unified/repo-guard/github.svg)](https://agentmods.dev/skills/zenobia0000/ai-agentic-coding-template_unified/repo-guard)
Your own site
<a href="https://agentmods.dev/skills/zenobia0000/ai-agentic-coding-template_unified/repo-guard"><img src="https://agentmods.dev/badge/skills/zenobia0000/ai-agentic-coding-template_unified/repo-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.

agentmods 80×15 button for repo-guard

Your own site · 80×15
<a href="https://agentmods.dev/skills/zenobia0000/ai-agentic-coding-template_unified/repo-guard"><img src="https://agentmods.dev/badge/skills/zenobia0000/ai-agentic-coding-template_unified/repo-guard.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 19 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 527 The whole file, excluding the scripts and references it only reads on demand.
Security scan C 1 finding. A grade says what 26 rules found in the file — not that it is safe.
Origin 100% copy Near-identical to another mod in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00019 $0.00527
Opus 5 $0.00010 $0.00264
Sonnet 5 $0.00004 $0.00105
Haiku 4.5 $0.00002 $0.00053

Measured 10d ago against content hash cc0e0eb47746, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade C, and why

repo-guard 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 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.

Recursive force deletehighDestructive command

rm -rf with a variable or a broad path is one typo away from removing the wrong tree.

rm -rf /
Origin

This is a copy

100% identical to repo-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.

.ai/adapters/claude-code/skills/repo-guard/SKILL.md · 112 lines

What it actually says

Repo Guard Skill

Purpose

Proactively protect the repository from common mistakes and security issues.

Trigger Conditions

This skill activates automatically when:

  • File write/edit operations are about to occur
  • Bash commands are being executed
  • Git operations are being performed

Protection Rules

1. Secret Detection

Detect and block commits containing:

  • API keys and tokens
  • Passwords and credentials
  • Private keys
  • Environment secrets

Patterns to watch:

- .env files
- *_KEY, *_SECRET, *_TOKEN patterns
- BEGIN PRIVATE KEY
- password=, passwd=, pwd=
- Bearer tokens
- AWS credentials

Action: Block and suggest using environment variables or secret managers.

2. Destructive Command Prevention

Block or require confirmation for:

rm -rf /
rm -rf *
rm -rf .
mkfs.*
dd if=
> /dev/sd*
chmod -R 777

Action: Block immediately with warning, suggest safer alternatives.

3. Main Branch Protection

Prevent direct modifications to:

  • main branch
  • master branch
  • production branch

Action: Suggest creating feature branch first.

4. Large File Prevention

Warn about:

  • Binary files > 10MB
  • Generated files (node_modules, dist, build)
  • Media files without LFS

Action: Warn and suggest .gitignore or Git LFS.

Response Behavior

When Detecting Issues

**Repo Guard Alert**

**Issue Detected**: [Type of issue]
**Location**: [File or command]
**Severity**: [Critical/Warning/Info]

**Details**:
[Explanation of the issue]

**Recommended Action**:
[What to do instead]

**To proceed anyway** (not recommended):
[Explicit override instructions]

Safe Operations

No output - allow operation to proceed silently.

Integration

Claude Code

Automatically invoked before:

  • Write tool calls
  • Edit tool calls
  • Bash tool calls with git/rm/chmod

Cursor

Referenced in rules for file modification warnings.

Gemini CLI

Included in system prompt for command validation.

Changes

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.

  1. 10d ago First seen · 112 lines · 19 tokens per session scan C cc0e0eb47746

Subscribe to this mod's changes

repo-guard is a skill published in the GitHub repository Zenobia0000/ai-agentic-coding-template_unified (4 stars, last pushed 4mo ago), licensed MIT. It adds 19 tokens to every session and 527 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it C with 1 finding (recursive force delete). It is 100% identical to repo-guard, differing in 0 lines, and is treated as a copy.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

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…

microsoft/ai-agents-for-beginners · 200 tokens

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…

vercel/next.js · 95 tokens

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…

vercel/next.js · 83 tokens

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…

vercel/next.js · 170 tokens

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…

vercel/next.js · 103 tokens