# Guard

> Full safety mode. Combines /careful (destructive command warnings) with file scope restriction. Prevents editing files outside a specified directory.

- **Type:** Skill
- **Install:** `agentstack add skill-fagemx-gstack-game-guard`
- **Verified:** Yes — security-reviewed for prompt injection and unsafe behavior
- **Seller:** [fagemx](https://agentstack.voostack.com/s/fagemx)
- **Installs:** 0
- **Category:** [Agent Skills](https://agentstack.voostack.com/c/agent-skills)
- **Latest version:** 0.1.0
- **License:** MIT
- **Upstream author:** [fagemx](https://github.com/fagemx)
- **Source:** https://github.com/fagemx/gstack-game/tree/main/skills/guard

## Install

```sh
agentstack add skill-fagemx-gstack-game-guard
```

Requires the [AgentStack CLI](https://agentstack.voostack.com/docs/cli). Works with Claude Code, Cursor, and any MCP-compatible agent.

## About

## Preamble (run first)

```bash
setopt +o nomatch 2>/dev/null || true  # zsh compat
_GD_VERSION="0.5.0"
# Find gstack-game bin directory (installed in project or standalone)
_GG_BIN=""
for _p in ".claude/skills/gstack-game/bin" ".claude/skills/game-review/../../gstack-game/bin" "$(dirname "$(readlink -f .claude/skills/game-review/SKILL.md 2>/dev/null)" 2>/dev/null)/../../bin"; do
  [ -f "$_p/gstack-config" ] && _GG_BIN="$_p" && break
done
[ -z "$_GG_BIN" ] && echo "WARN: gstack-game bin/ not found, some features disabled"

# Project identification
_SLUG=$(basename "$(git rev-parse --show-toplevel 2>/dev/null || pwd)")
_BRANCH=$(git branch --show-current 2>/dev/null || echo "unknown")
_USER=$(whoami 2>/dev/null || echo "unknown")

# Session tracking
mkdir -p ~/.gstack/sessions
touch ~/.gstack/sessions/"$PPID"
_PROACTIVE=$([ -n "$_GG_BIN" ] && "$_GG_BIN/gstack-config" get proactive 2>/dev/null || echo "true")
_TEL_START=$(date +%s)
_SESSION_ID="$-$(date +%s)"

# Shared artifact storage (cross-skill, cross-session)
mkdir -p ~/.gstack/projects/$_SLUG
_PROJECTS_DIR=~/.gstack/projects/$_SLUG

# Telemetry (sanitize inputs before JSON interpolation)
mkdir -p ~/.gstack/analytics
_SLUG_SAFE=$(printf '%s' "$_SLUG" | tr -d '"\\\n\r\t')
_BRANCH_SAFE=$(printf '%s' "$_BRANCH" | tr -d '"\\\n\r\t')
echo '{"skill":"guard","ts":"'$(date -u +%Y-%m-%dT%H:%M:%SZ)'","repo":"'"$_SLUG_SAFE"'","branch":"'"$_BRANCH_SAFE"'"}'  >> ~/.gstack/analytics/skill-usage.jsonl 2>/dev/null || true

echo "SLUG: $_SLUG"
echo "BRANCH: $_BRANCH"
echo "PROACTIVE: $_PROACTIVE"
echo "PROJECTS_DIR: $_PROJECTS_DIR"
echo "GD_VERSION: $_GD_VERSION"

# Artifact summary
_ARTIFACT_COUNT=$(ls "$_PROJECTS_DIR"/*.md 2>/dev/null | wc -l | tr -d ' ')
[ "$_ARTIFACT_COUNT" -gt 0 ] && echo "Artifacts: $_ARTIFACT_COUNT files in $_PROJECTS_DIR" && ls -t "$_PROJECTS_DIR"/*.md 2>/dev/null | head -5 | while read f; do echo "  $(basename "$f")"; done
```

**Shared artifact directory:** `$_PROJECTS_DIR` (`~/.gstack/projects/{slug}/`) stores all skill outputs:
- Design docs from `/game-ideation`
- Review reports from `/game-review`, `/balance-review`, etc.
- Player journey maps from `/player-experience`

All skills read from this directory on startup to find prior work. All skills write their output here for downstream consumption.

If `PROACTIVE` is `"false"`, do not proactively suggest gstack-game skills.

## User Sovereignty

AI models recommend. You decide. When this skill finds issues, proposes changes, or
a cross-model second opinion challenges a premise — the finding is presented to you,
not auto-applied. Cross-model agreement is a strong signal, not a mandate. Your
direction is the default unless you explicitly change it.

## Public Output Redaction Lite

Before writing or sharing public/semi-public output, scan the exact text when
`$_GG_BIN/gstack-game-redact` exists:

```bash
printf '%s' "$OUTPUT_TEXT" | "$_GG_BIN/gstack-game-redact" --json
```

Use this for PR bodies, patch notes, Steam/App Store/Google Play submission text,
publisher updates, imported GDD excerpts, release docs, playtest summaries, and
game-autoplan artifacts that leave the repo.

HIGH findings block the output until removed and, for credentials, rotated.
MEDIUM findings require explicit user review or safe redaction before publishing.
Game-specific MEDIUM examples: player email/phone, platform NDA wording,
publisher-confidential notes, unreleased platform dates, and named community
member reports.

## Completion Status Protocol

DONE / DONE_WITH_CONCERNS / BLOCKED / NEEDS_CONTEXT.
Escalation after 3 failed attempts.

## Telemetry (run last)

```bash
_TEL_END=$(date +%s)
_TEL_DUR=$(( _TEL_END - _TEL_START ))
[ -n "$_GG_BIN" ] && "$_GG_BIN/gstack-telemetry-log" \
  --skill "guard" --duration "$_TEL_DUR" --outcome "OUTCOME" \
  --used-browse "false" --session-id "$_SESSION_ID" 2>/dev/null &
```

# /guard: Full Safety Mode

Activates BOTH destructive command safety (/careful) AND file edit scope restriction.

## Activation

AskUserQuestion: What directory should I restrict edits to?
- A) Current feature directory (auto-detect from recent git changes)
- B) Specific path: [user provides path]
- C) Only files in current PR/branch diff

## Scope Restriction

When active, before any Edit/Write tool call:

1. Check if target file is within the allowed scope
2. If outside scope:

> 🛡️ **GUARD MODE**: This file is outside the allowed scope.
> Scope: [allowed directory]
> Target: [file being edited]
>
> This edit is BLOCKED. To proceed, either:
> A) Expand scope to include this file
> B) Temporarily bypass for this one edit
> C) Deactivate guard mode

## Careful Mode (included)

All /careful protections are also active. See `/careful` for destructive command warnings.

## Use Cases

- **During a focused bug fix:** Guard to only the affected module
- **During asset work:** Guard to only asset directories (don't accidentally change code)
- **During balance tuning:** Guard to only data/config files (don't change game logic)

## Deactivation

Say "turn off guard mode" or start a new session.

## Review Log

```bash
[ -n "$_GG_BIN" ] && "$_GG_BIN/gstack-review-log" '{"skill":"guard","timestamp":"TIMESTAMP","status":"ACTIVATED","scope":"SCOPE","commit":"COMMIT"}' 2>/dev/null || true
```

## Source & license

This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.

- **Author:** [fagemx](https://github.com/fagemx)
- **Source:** [fagemx/gstack-game](https://github.com/fagemx/gstack-game)
- **License:** MIT

Install and usage instructions live in the source repository linked above.

## Pricing

- **Free** — Free

## Security capabilities

Automated source analysis of v0.1.0 — what this tool can access:

- **Network access:** no
- **Filesystem access:** no
- **Shell / process execution:** no
- **Environment & secrets:** no
- **Dynamic code execution:** no

*"Yes" means the capability is present in the source — more access means more to trust, not that it is unsafe.*


## Versions

- **0.1.0** — security scan: passed — Imported from the upstream source.

## Links

- Listing page: https://agentstack.voostack.com/l/skill-fagemx-gstack-game-guard
- Seller: https://agentstack.voostack.com/s/fagemx
- Browse the marketplace: https://agentstack.voostack.com/browse

---
Listed on AgentStack — the marketplace for AI agent skills and MCP servers. Every listing is security-reviewed. Creators keep 70%.