Extract content to check from tool input based on tool type.

Filter out pre-existing content from diff files. When a file is fully rewritten (Write tool replaces entire content), git shows all lines

Generate complete benchmark.json from run results.

Generate human-readable benchmark.md from benchmark data.

Get the content of a file at the baseline SHA. Returns None if unavailable. Decode the file content as UTF-8 with errors="replace" rather than us

Get session-specific lock file path.

PostToolUse handler for Bash — reviews git commits for security issues. Runs as asyncRewake: detects `git commit` in the Bash command, parses

Review the just-pushed range as one diff, advancing the base past the contiguous prefix of already-per-commit-reviewed shas. Spec: review `gi

Handle the Stop hook — final security check using git diff. Diffs against the baseline SHA captured at UserPromptSubmit to review only co

Handle UserPromptSubmit — capture git baseline SHA. Called on every user prompt. Updates the baseline so the stop hook only reviews chang

Gate for the commit-review PostToolUse[Bash] hook. Commit review is enabled by default; ENABLE_COMMIT_REVIEW=0 remains the unconditional kill

Gate for the push-sweep PostToolUse[Bash] hook. Enabled by default. ENABLE_COMMIT_REVIEW=0 remains the unconditional kill switch (push-sweep

Load the git baseline SHA from state.

Load previous iteration's feedback and outputs. Returns a map of run_id -> {"feedback": str, "outputs": list[dict]}.

Load a single rule file. Returns: Rule object or None if file is invalid.

Load all run results from a benchmark directory. Returns dict keyed by config name (e.g. "with_skill"/"without_skill", or "new_skill"/"o

Run the bootstrap. Returns (outcome, err_phase, err_kind). err_phase / err_kind are non-empty only on BUILD_FAILED — they let telemetry split

Main hook function.

Main entry point for PostToolUse hook.

Main entry point for PreToolUse hook.

Main entry point for UserPromptSubmit hook.

Main entry point for Stop hook.

Package a skill folder into a .skill file. Args: skill_path: Path to the skill folder output_dir: Optional output directory

Mark file:rule pairs as pending for the Stop-hook outcome sweep.

Append a file path to the touched_paths list (deduped, capped at 200). Stop is the consumer and clears under the same lock it reads with; UPS

Run the eval + improvement loop.

Check if a path should be excluded from packaging.

Split eval set into train and test sets, stratified by should_trigger.

Return the absolute path of the plugin's state directory. Resolution precedence (highest first): 1. SECURITY_WARNINGS_STATE_DIR — plugin-sp

Stop-hook final sweep. Re-read every file in pending_warnings, re-check patterns, and return (fixed, unresolved, unresolved_mask). Clears sta

Initialize rule engine.

Run a higher-level security concerns analysis on files/diffs. Identifies AREAS OF CONCERN that the main model should investigate. Returns

Atomically check if a counter has reached its limit and increment if not. Returns True if the counter is below max_count (should proceed),

Extract file paths from unified diff output (without content). Only includes files with source code extensions. Returns a list of file pa

Medium-included is the validated default; the model's investigate-stage severity is conservative and dropping mediums before self-refute filters