egc-guardian

validate_command({ command: string, cwd?: string })

Validates a shell command before execution. Blocks shell injection patterns (semicolons, pipes to bash, backtick execution), known dangerous binaries, inline eval even when the flag is glued to its value, grep pattern files pointed at protected paths, paths smuggled inside flag=value forms, and commands targeting protected paths. Secret redaction also covers Google-style API keys.

Returns: { allowed: boolean, reason?: string }

validate_write({ path: string, content?: string })

Validates a file write operation. Blocks writes to sensitive system paths (~/.ssh/, /etc/, /usr/, /bin/) and paths outside the project directory.

Returns: { allowed: boolean, reason?: string }

reduce_context({ content: string, max_tokens?: number })

Deduplicates and trims a Markdown payload to reduce token count. Removes repeated headers, collapses whitespace, and truncates to the token limit if specified.

Returns: Trimmed Markdown string.

orchestrate_task({ prompt: string, context?: string })

Analyzes a prompt and returns a routing suggestion: which agents, skills, and commands are most relevant. Does not execute anything. Returns a plan for the AI to follow.

Returns: Object with suggested agents, skills, and commands.

auto_learn({ project_path: string, target_file?: string, limit?: number })

Mines recent tool failures from session history and writes actionable recommendations to all AI tool config files found in the project (CLAUDE.md, GEMINI.md, AGENTS.md, Cursor rules, Copilot instructions, Windsurf rules, and others). Only writes to files that already exist. Safe to call at any time; skips gracefully if no failures are found.

Returns: Object with patterns_found, recommendations_written, target_file, propagated_to (list of files written), and skipped.