guard
Full safety mode: destructive command warnings + directory-scoped edits.
Skill by LaPaGaYo
Chalk Labs
Need help deploying guard?
Chalk Labs sets up agents like this inside real teams: connected to your tools, tested on your data, with a human in the loop where it matters.
Install
Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.
npx agentmarket install skill/lapagayo-guard
Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.
Get the weekly diff
The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.
About
Reviews
Write a reviewNo reviews yet. Installed it? Reviews come from verified installers only. How reviews work
Permissions
What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.
- Tools
- No tools found
- Secrets
- None asked for
- Install scripts
- None found
Network hosts it talks to 1
codeload.github.com· found in install command
Files it touches
~/.claude/skills/guard
What's inside
- Skill name
guard- Description
- Full safety mode: destructive command warnings + directory-scoped edits. Combines /careful (warns before rm -rf, DROP TABLE, force-push, etc.) with /freeze (blocks edits outside a specified directory). Use for maximum safety when touching prod or debugging live systems. Use when asked to "guard mode", "full safety", "lock it down", or "maximum safety". (Nexus)
- License
- MIT
- Instructions
- 70 lines in SKILL.md · view on GitHub
Agent Skills spec issues
- allowed-tools: must be a space-separated string
Files (3)
- SKILL.md
- SKILL.md.tmpl
- nexus.skill.yaml
SKILL.md (first lines)
<!-- AUTO-GENERATED from SKILL.md.tmpl — do not edit directly -->
<!-- Regenerate: bun run gen:skill-docs -->
# /guard — Full Safety Mode
Activates both destructive command warnings and directory-scoped edit restrictions.
This is the combination of `/careful` + `/freeze` in a single command.
**Dependency note:** This skill references hook scripts from the sibling `/careful`
and `/freeze` skill directories. Both must be installed (they are installed together
by the Nexus setup script).
## Setup
Ask the user which directory to restrict edits to. Use AskUserQuestion:
- Question: "Guard mode: which directory should edits be restricted to? Destructive command warnings are always on. Files outside the chosen path will be blocked from editing."
- Text input (not multiple choice) — the user types a path.
Once the user provides a directory path:
1. Resolve it to an absolute path:
```bash
FREEZE_DIR=$(cd "<user-provided-path>" 2>/dev/null && pwd)
echo "$FREEZE_DIR"
```
2. Ensure trailing slash and save to the freeze state file:
```bash
FREEZE_DIR="${FREEZE_DIR%/}/"
STATE_DIR="${CLAUDE_PLUGIN_DATA:-$HOME/.nexus}"
mkdir -p "$STATE_DIR"
echo "$FREEZE_DIR" > "$STATE_DIR/freeze-dir.txt"
echo "Freeze boundary set: $FREEZE_DIR"
```
Tell the user:
- "**Guard mode active.** Two protections are now running:"
- "1. **Destructive command warnings** — rm -rf, DROP TABLE, force-push, etc. will warn before executing (you can override)"
- "2. **Edit boundary** — file edits restricted to `<path>/`. Edits outside this directory are blocked."
- "To remove the edit boundary, run `/unfreeze`. To deactivate everything, end the session."
## What's protected
See `/careful` for the full list of destructive command patterns and safe exceptions.
See `/freeze` for how edit boundary enforcement works.
## Output Contract
Report both protections and their current state:
- Destructive Bash command warnings are active through the `/careful` hook.
- Edit and Write operations are restricted to the absolute freeze boundary path.
- `/unfreeze` clears only the edit boundary; ending the session clears all hook state.
Do not claim guard mode is active unless the freeze boundary was written and the
destructive-command hook is part of this skill configuration.
## Verification Evidence
After setup, verify the boundary state file:
```bash
STATE_DIR="${CLAUDE_PLUGIN_DATA:-$HOME/.nexus}"
cat "$STATE_DIR/freeze-dir.txt"
```
The final response must include the saved absolute boundary path and confirm that
Bash commands will still be checked for destructive patterns.From LaPaGaYo/nexus, MIT.
More from LaPaGaYo/nexus
- 0.470score
careful
LaPaGaYo
Safety guardrails for destructive commands.
SkillCFreshness: CClaude Code +9 - 0.470score
freeze
LaPaGaYo
Restrict file edits to a specific directory for the session.
SkillCFreshness: CClaude Code +9 - 0.470score
unfreeze
LaPaGaYo
Clear the freeze boundary set by /freeze, allowing edits to all directories again.
SkillCFreshness: CClaude Code +9 - 0.468score
autoplan
LaPaGaYo
Transitional alias for the canonical Nexus /plan command.
SkillCFreshness: CClaude Code +9 - 0.468score
office-hours
LaPaGaYo
Transitional alias for the canonical Nexus /discover command.
SkillCFreshness: CClaude Code +9 - 0.468score
plan-ceo-review
LaPaGaYo
Transitional alias for the canonical Nexus /frame command.
SkillCFreshness: CClaude Code +9 - 0.468score
plan-eng-review
LaPaGaYo
Transitional alias for the canonical Nexus /frame command.
SkillCFreshness: CClaude Code +9 - 0.464score
nexus
LaPaGaYo
Nexus workflow harness entrypoint.
SkillCFreshness: CClaude Code +9 - 0.462score
review
LaPaGaYo
Canonical Nexus review command.
SkillCFreshness: CClaude Code +9 - 0.462score
ship
LaPaGaYo
Canonical Nexus ship command.
SkillCFreshness: CClaude Code +9 - 0.462score
benchmark
LaPaGaYo
Performance regression detection using the browse daemon.
SkillCFreshness: CClaude Code +9 - 0.462score
build
LaPaGaYo
Canonical Nexus build command.
SkillCFreshness: CClaude Code +9
Signals
- Stars
- 0
- Forks
- 1
- Open issues
- 0
- Last commit (this folder)
- May 6, 2026 (5 months ago)
- Last release
- May 12, 2026 (5 months ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- MIT
- Repository
- github.com/LaPaGaYo/nexus
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
More from LaPaGaYo
- 0.470score
careful
LaPaGaYo
Safety guardrails for destructive commands.
SkillCFreshness: CClaude Code +9 - 0.470score
unfreeze
LaPaGaYo
Clear the freeze boundary set by /freeze, allowing edits to all directories again.
SkillCFreshness: CClaude Code +9 - 0.470score
freeze
LaPaGaYo
Restrict file edits to a specific directory for the session.
SkillCFreshness: CClaude Code +9 - 0.468score
office-hours
LaPaGaYo
Transitional alias for the canonical Nexus /discover command.
SkillCFreshness: CClaude Code +9 - 0.468score
plan-eng-review
LaPaGaYo
Transitional alias for the canonical Nexus /frame command.
SkillCFreshness: CClaude Code +9 - 0.468score
plan-ceo-review
LaPaGaYo
Transitional alias for the canonical Nexus /frame command.
SkillCFreshness: CClaude Code +9
Done for you
Rather not set it up yourself?
Chalk Labs scopes, builds and runs agents for your team: the task audit, the eval harness, the integrations and the weekly ops report. Fixed scope, priced before we start.
See how we build AI agents →Read the case studies
Chalk Labs is a two-founder AI and growth studio. We build AI agents, CRMs and MVPs for Web3 and AI companies, and have shipped 50+ product and token launches.
- launches shipped
- 50+
- launches shipped
- media placements
- 500+
- media placements
- founders on every account
- 2
- founders on every account
Press we've placed: Forbes · CoinDesk · Decrypt · Cointelegraph · The Block
Rahil Jain, Co-founder, Chalk Labs. Ex-Goldman Sachs engineer. You talk to the person who builds it.
Get guard running in your business
Tell us what you want to automate. A founder replies within one working day with a plan, not a pitch deck.
Cite this page
guard skill. Agent Mart. https://agentmart.dev/skills/lapagayo-guard (last updated 2026-10-24)