Loading...
Loading...
Fact-forcing gate that blocks Edit/Write/Bash (including MultiEdit) and demands concrete investigation (importers, data schemas, user instruction) before allowing the action. Measurably improves output quality by +2.25 points vs ungated agents.
npx skill4agent add affaan-m/everything-claude-code gateguard1. DENY — block the first Edit/Write/Bash attempt
2. FORCE — tell the model exactly which facts to gather
3. ALLOW — permit retry after facts are presented| Task | Gated | Ungated | Gap |
|---|---|---|---|
| Analytics module | 8.0/10 | 6.5/10 | +1.5 |
| Webhook validator | 10.0/10 | 7.0/10 | +3.0 |
| Average | 9.0 | 6.75 | +2.25 |
Before editing {file_path}, present these facts:
1. List ALL files that import/require this file (use Grep)
2. List the public functions/classes affected by this change
3. If this file reads/writes data files, show field names, structure,
and date format (use redacted or synthetic values, not raw production data)
4. Quote the user's current instruction verbatimBefore creating {file_path}, present these facts:
1. Name the file(s) and line(s) that will call this new file
2. Confirm no existing file serves the same purpose (use Glob)
3. If this file reads/writes data files, show field names, structure,
and date format (use redacted or synthetic values, not raw production data)
4. Quote the user's current instruction verbatimrm -rfgit reset --hardgit push --forcedrop table1. List all files/data this command will modify or delete
2. Write a one-line rollback procedure
3. Quote the user's current instruction verbatimQuote the user's current instruction verbatim.scripts/hooks/gateguard-fact-force.jspip install gateguard-ai
gateguard init.gateguard.yml%Y/%m/%d %H:%M.gateguard.yml.venv/node_modules/.git/safety-guardcode-reviewer