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.
npx skills add CarbeneAI/Forge --skill guardgit clone --depth 1 https://github.com/CarbeneAI/ForgeWrote 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.
[](https://agentmods.dev/skills/carbeneai/forge/guard)<a href="https://agentmods.dev/skills/carbeneai/forge/guard"><img src="https://agentmods.dev/badge/skills/carbeneai/forge/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.
<a href="https://agentmods.dev/skills/carbeneai/forge/guard"><img src="https://agentmods.dev/badge/skills/carbeneai/forge/guard.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00084 | $0.00792 |
| Opus 5 | $0.00042 | $0.00396 |
| Sonnet 5 | $0.00017 | $0.00158 |
| Haiku 4.5 | $0.00008 | $0.00079 |
Grade C, and why
guard scanned grade C with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 6d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Recursive force deletehighDestructive command
rm -rf with a variable or a broad path is one typo away from removing the wrong tree.
Combines /careful (warns before rm -rf, DROP TABLE, force-push, etc.) with This is a copy
94% identical to guard — 9 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 83 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/guard — Full Safety Mode
Activates both destructive command warnings and directory-scoped edit restrictions.
This is the combination of /careful + /freeze in a single command.
Dependency note: This skill references hook scripts from the sibling /careful
and /freeze skill directories. Both must be installed (they are installed together
by the gstack setup script).
mkdir -p ~/.gstack/analytics
echo '{"skill":"guard","ts":"'$(date -u +%Y-%m-%dT%H:%M:%SZ)'","repo":"'$(basename "$(git rev-parse --show-toplevel 2>/dev/null)" 2>/dev/null || echo "unknown")'"}' >> ~/.gstack/analytics/skill-usage.jsonl 2>/dev/null || true
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:
- Resolve it to an absolute path:
FREEZE_DIR=$(cd "<user-provided-path>" 2>/dev/null && pwd)
echo "$FREEZE_DIR"
- Ensure trailing slash and save to the freeze state file:
FREEZE_DIR="${FREEZE_DIR%/}/"
STATE_DIR="${CLAUDE_PLUGIN_DATA:-$HOME/.gstack}"
mkdir -p "$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.
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 6d ago First seen · 83 lines · 84 tokens per session scan C 6e6f38220c53
guard is a skill published in the GitHub repository CarbeneAI/Forge (9 stars, last pushed 1mo ago), licensed MIT. It adds 84 tokens to every session and 792 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it C with 1 finding (recursive force delete). It is 94% identical to guard, differing in 9 lines, and is treated as a copy.
Other skills, from other repositories
anti-debug-bypass
Detect and neutralize anti-debug / anti-VM checks — IsDebuggerPresent, ptrace, NtGlobalFlag, timing, hardware-breakpoint detection.
malware-triage
Fast malware triage workflow — static (PE/Mach-O/ELF format, strings, imports, signatures, entropy/packed indicators), dynamic (sandbox with INetSim, Wireshark, Process Monitor, Procmon, time-shift), unpack (Scylla/PE-sieve), then full RE with Ghidra/IDA. Designed for ≤15 min initial verdict.
packer-unpacking
Identify and unpack common binary packers — UPX, ASPack, Themida, VMProtect, MPRESS, PECompact, Enigma.
test-and-fix
Run unit tests and automatically fix code failures, regression bugs, or test mismatches. Use when tests are failing, after implementing new features, or to repair "broken" tests.
ghidra
Deep binary analysis via Ghidra — headless analyzeHeadless or live MCP bridge with 245 tools. Decompilation, xrefs, function listing, batch operations, P-code emulation, convention enforcement.
build-and-fix
Build the project and automatically fix any build errors, compilation failures, or type mismatches. Use when the project fails to build, shows "broken" states, or after making significant changes.