Safety-first agentic coding framework. Three-layer safety pipeline (sandbox, YAML policies, human-in-the-loop approval) for AI coding agents. Pluggable runtimes (Claude Code, Codex), autonomous task orchestrator, full audit trail.
Skill Claude CodeCodex
How leashd's core components fit together — buildengine wiring, the Engine message loop, the three-layer safety pipeline (gatekeeper/sandbox/policy/approval), pluggable agent runtimes, the EventBus plugin system, config layering, and two-tier storage. Use when onboarding, planning a change that spans subsystems, or…
Skill Claude CodeCodex
Debug leashd issues by querying SQLite sessions/messages, reading audit.jsonl tool decisions, and parsing logs/app.log application events. Use when something doesn't work as expected, to trace requests, inspect approvals, or diagnose bugs.
Skill Claude CodeCodex
Debug autonomous /task execution — query taskruns state, phase context/costs, trace tool decisions in audit.jsonl, and check app logs for errors. Use when a task fails, gets stuck, escalates, or behaves unexpectedly.
Skill Claude CodeCodex
Run leashd's live tmux+Telegram verification harness in scripts/harness/ — a fake Telegram Bot API plus a real Engine/TmuxAgent/MultiConnector wired like runmulti. Inject messages, slash commands, and inline-button taps and observe the exact outbound streaming/approval/plan/task timeline. Use to reproduce or verify…
Skill Claude CodeCodex
How leashd's default tmux agent runtime works and how to debug it — TmuxAgent/TmuxSessionManager drive a real interactive claude TUI in a tmux pane, bridge every tool call back through the gatekeeper via Claude Code PreToolUse HTTP hooks, tail session JSONL for streaming, and handle turn completion. Use when changing…
Skill Claude CodeCodex
Core agent-browser usage guide. Read this before running any agent-browser commands. Covers the snapshot-and-ref workflow, navigating pages, interacting with elements (click, fill, type, select), extracting text and data, taking screenshots, managing tabs, handling forms and auth, waiting for content, running multiple…
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: