GateGuard: Fact-Forcing Pre-Action Gate

A PreToolUse hook that forces Claude to investigate before editing. Instead of self-evaluation ("are you sure?"), it demands concrete facts. The act of investigation creates awareness that self-evaluation never did.

When to Activate

• Working on any codebase where file edits affect multiple modules
• Projects with data files that have specific schemas or date formats
• Teams where AI-generated code must match existing patterns
• Any workflow where Claude tends to guess instead of investigating

Core Concept

LLM self-evaluation doesn't work. Ask "did you violate any policies?" and the answer is always "no." This is verified experimentally.

But asking "list every file that imports this module" forces the LLM to run Grep and Read. The investigation itself creates context that changes the output.

Three-stage gate:

1. 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

No competitor does all three. Most stop at deny.

Evidence

Two independent A/B tests, identical agents, same task:

Both agents produce code that runs and passes tests. The difference is design depth.

Gate Types

Edit / MultiEdit Gate (first edit per file)

MultiEdit is handled identically, each file in the batch is gated individually.

Before editing {file_path}, present these facts:

1. List ALL files that import/require this file (search the tree: Glob/Grep, or find/grep via Bash)
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 verbatim

Write Gate (first new file creation)

Before 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 (search the tree: Glob/Grep, or find/grep via Bash)
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 verbatim

Destructive Bash Gate (every destructive command)

Triggers on: rm -rf, git reset --hard, git push --force, drop table, etc.

1. List all files/data this command will modify or delete
2. Write a one-line rollback procedure
3. Quote the user's current instruction verbatim

Routine Bash Gate (once per session)

1. The current user request in one sentence
2. What this specific command verifies or produces

Quick Start

Option A: Use the ECC hook (NOT available in this collection)

Adapted 2026-09-03. Upstream ships an implementation at scripts/hooks/gateguard-fact-force.js inside the ECC plugin. That file was not imported, so this skill arrives as the design (gate stages, fact lists, tuning surface) and not as a runnable hook. Two ways to actually run it:

1. Install the upstream package (Option B below), which is self-contained.
2. Port the three gates into onboard-repo/library/hooks/ as a Python PreToolUse hook alongside protect-paths.py and block-destructive.py, following the same fail-open discipline (exit 0 on unparseable input, and on valid JSON of the wrong shape). The three-stage DENY / FORCE / ALLOW contract and the per-gate fact lists above are the spec for that port.

Everything below documents upstream's ECC_* environment surface. Those variables do nothing here until one of the two options above is done; they are kept because they are the best statement of which knobs a gate like this needs.

If GateGuard blocks setup or repair work, start the session with ECC_GATEGUARD=off. For hook-level control, keep using ECC_DISABLED_HOOKS with the GateGuard hook ID.

In long sessions, only the first GATEGUARD_FACT_FORCE_FULL_DENIALS fact-force denials (default 3) emit the full four-fact block; later denials are condensed to a single line carrying the denial ordinal, so near-identical blocks cannot accumulate in the context window and amplify model repetition loops (#2142). Retrying the same file or command after presenting facts never re-triggers the gate.

Graduated controls

ECC_GATEGUARD=off (or GATEGUARD_DISABLED=1) turns the gate off entirely. The variables in this table do not: each narrows one behaviour while the load-bearing destructive-Bash checks keep running:

GATEGUARD_BASH_ROUTINE_DISABLED accepts 1, true, on, enabled, enable, or yes (case- and whitespace-insensitive); any other value leaves the gate on.

Turning the gate off completely

For hook-level control, keep using ECC_DISABLED_HOOKS with the GateGuard hook ID.

Glob semantics for GATEGUARD_EXEMPT_GLOBS

Patterns are matched, unanchored, against the target path with backslashes normalized to / and the whole string lowercased, the path exactly as the hook receives it, which for Claude Code tool payloads is absolute. * matches within a path segment, ** across segments, ? a single character. Matching is fail-open: a malformed pattern is dropped rather than raising.

Note that a leading **/ compiles to .*/, so it requires at least one preceding separator: **/tests/** exempts /repo/tests/foo.js but would not match a bare relative tests/foo.js. Add the separator-free form too if you pass relative paths:

{
  "env": {
    "GATEGUARD_BASH_ROUTINE_DISABLED": "1",
    "GATEGUARD_EXEMPT_GLOBS": "**/tests/**,tests/**,**/*.test.*,**/docs/**,**/dist/**"
  }
}

Option B: Full package with config

pip install gateguard-ai
gateguard init

This adds .gateguard.yml for per-project configuration (custom messages, ignore paths, gate toggles).

Anti-Patterns

• Don't use self-evaluation instead. "Are you sure?" always gets "yes." This is experimentally verified.
• Don't skip the data schema check. Both A/B test agents assumed ISO-8601 dates when real data used %Y/%m/%d %H:%M. Checking data structure (with redacted values) prevents this entire class of bugs.
• Don't gate every single Bash command. Routine bash gates once per session. Destructive bash gates every time. This balance avoids slowdown while catching real risks.

Best Practices

• Let the gate fire naturally. Don't try to pre-answer the gate questions, the investigation itself is what improves quality.
• Customize gate messages for your domain. If your project has specific conventions, add them to the gate prompts.
• Use .gateguard.yml to ignore paths like .venv/, node_modules/, .git/.