guard

guard is a skill for Claude Code from hamzaPixl/pixl-ai. It costs 45 tokens per session (965 once invoked), scanned A, original, MIT.

A session-level safety tool for marking files or folders as protected, or limiting edits to selected paths. It records these boundaries so they can be checked before changes are made.

In plain words
What is it for?
Use it to protect environment files and schemas, or to restrict an editing session to specific directories.
Why use it?
It reduces the risk of accidentally changing critical files, production settings, or files outside the intended work area.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter.

Part of the pixl-crew plugin — 93 skills, 14 agents, 6 hooks shipped together

Good fit Use it to protect environment files and schemas, or to restrict an editing session to specific directories.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/hamzapixl/pixl-ai/guard
Install

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.

Any agent
npx skills add hamzaPixl/pixl-ai --skill guard
Clone the repo
git clone --depth 1 https://github.com/hamzaPixl/pixl-ai

Made for: Claude Code.

Or install pixl-crew, the plugin that ships this one along with the rest of its 93 skills, 14 agents, 6 hooks.

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 guard

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

Your own site · 80×15
<a href="https://agentmods.dev/skills/hamzapixl/pixl-ai/guard"><img src="https://agentmods.dev/badge/skills/hamzapixl/pixl-ai/guard.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 45 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 965 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found 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 $0.00045 $0.00965
Opus 5.5 $0.00018 $0.00386
Sonnet 5.5 $0.00009 $0.00193
Haiku 4.5 $0.00005 $0.00097

Measured 1mo ago against content hash 41d57dd48c3c, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

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.

packages/crew/skills/guard/SKILL.md · 149 lines

How it starts

The opening of the file, as written. The whole thing — 149 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Overview

Safety guardrail that lets users declare protected paths (no edits allowed) or scoped paths (only edits within scope allowed). Integrates with the session to prevent accidental modifications to critical files.

How this differs from other features:

  • .claude/rules/ — permanent rules. This skill sets session-scoped guards that can be cleared.
  • permissionMode: plan — makes an agent read-only. This skill restricts WHICH files can be edited.

Modes

Protect Mode

Declare files or directories that should NOT be modified:

/guard protect .env prisma/schema.prisma packages/engine/

This creates a guard file that Claude checks before editing:

GUARD_FILE=".context/guard.json"
mkdir -p .context

cat > "$GUARD_FILE" <<EOF
{
  "mode": "protect",
  "protected": [".env", "prisma/schema.prisma", "packages/engine/"],
  "created": "$(date -u +%Y-%m-%dT%H:%M:%SZ)",
  "reason": "User-declared protected paths"
}
EOF

Output:

Guard active — protected paths:
  - .env
  - prisma/schema.prisma
  - packages/engine/**

These paths will be flagged before any edit. Use /guard clear to remove.

Scope Mode

Restrict edits to ONLY the specified directories:

/guard scope src/api/ src/models/
cat > "$GUARD_FILE" <<EOF
{
  "mode": "scope",
  "allowed": ["src/api/", "src/models/"],
  "created": "$(date -u +%Y-%m-%dT%H:%M:%SZ)",
  "reason": "User-declared edit scope"
}
EOF

Output:

Guard active — edits scoped to:
  - src/api/**
  - src/models/**

Files outside this scope will be flagged before any edit. Use /guard clear to remove.

Status Mode

Show current guard state:

/guard status

Read .context/guard.json and display the current guards.

Clear Mode

Remove all guards:

/guard clear
rm -f ".context/guard.json"

How Guards Are Enforced

After creating the guard file, Claude should check it before every file edit:

  1. Before using Edit or Write tools, check if .context/guard.json exists
  2. If mode: "protect" — verify the target file is NOT in the protected list
  3. If mode: "scope" — verify the target file IS within the allowed directories
  4. If a guard would be violated, warn the user and ask for confirmation before proceeding

Read the full file on GitHub · 149 lines

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. 1mo ago First seen · 149 lines · 45 tokens per session scan A 41d57dd48c3c

Subscribe to this mod's changes

guard is a skill published in the GitHub repository hamzaPixl/pixl-ai (2 stars, last pushed 6mo ago), licensed MIT. It adds 45 tokens to every session and 965 once invoked, about $0.0002 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 2026-09-03.

Related

Other skills, from other repositories

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

systematic-debugging

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

obra/superpowers · 21 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

chat-pet-sprite-creation

Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.

microsoft/vscode · 53 tokens

cpu-profile-analysis

Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…

microsoft/vscode · 71 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