Codecast

Stream coding agent sessions (Claude Code, Codex, Gemini CLI, etc.) to a Discord channel in real-time via webhook. Use when invoking coding agents and wantin...

Security Scan

The skill largely does what it claims (stream agent output to Discord) but asks for and performs actions that aren't fully declared or proportionate (undocumented credentials, instructions to bypass model permissions, ability to write to /proc and kill processes, and to post file contents to remote webhooks).

Purpose & Capability

The name/description (stream coding sessions to Discord) matches the shipped scripts, but the skill requires additional runtime capabilities not declared in the registry metadata: Discord bot token usage, webhook storage, GH/gh CLI access (for PR review), and macOS keychain access are referenced in docs/scripts but not listed as required env vars. PR review mode clones repos and runs arbitrary code — coherent with a review feature but raises extra privileges that a user should expect to be explicitly requested.

Instruction Scope

Runtime instructions and scripts go beyond just relaying stdout: they advise creating ~/.claude/settings.json to 'bypassPermissions' and use --dangerously-skip-permissions (disabling agent permission checks), clone remote repos and run agents against them, read and post file contents to Discord (potentially leaking secrets), write session breadcrumbs in /tmp, and create/consume named pipes or /proc/<pid>/fd/0 to forward input. These steps can enable exfiltration and remote-driven command execution and are not limited to benign streaming.

Install Mechanism

There is no install spec (instruction-only), and all code is included in the bundle (shell + Python). That lowers remote-install risk, but some runtime dependencies are implied (python3, unbuffer, curl, gh, websocket-client) yet not centrally declared. No external download URLs are used, which is good; however missing dependency declarations mean operators might run the skill without realizing required packages and capabilities.

Credentials

Registry metadata lists no required env vars, but SKILL.md and scripts expect/optionally use several secrets and env vars: WEBHOOK_URL/.webhook-url, CODECAST_BOT_TOKEN (or .bot-token), BRIDGE_CHANNEL_ID, BRIDGE_ALLOWED_USERS, CODECAST_RATE_LIMIT, and optional keychain access. The skill also relies on gh CLI authentication for PR review mode. Secrets and credential access are not declared up-front, which is disproportionate to a simple 'stream to Discord' description and hides the credential blast radius.

Persistence & Privilege

always:false (no forced persistence) and user-invocable:false are appropriate. The skill does create /tmp/dev-relay-sessions entries, writes stream.jsonl and breadcrumb files, and the bridge can send signals (os.kill) and write to /proc/<pid>/fd/0 or a named pipe to inject stdin into other processes. Those are powerful runtime privileges (process control and inter-process I/O) — coherent with an interactive relay but worth caution. No evidence the skill modifies other skills or global agent configs beyond its own files.

What to consider before installing

This skill will post live agent activity (including file reads/edits, command outputs, and potentially file contents) to a Discord webhook or channel. Before installing: 1) Review all included scripts (they are shipped with the skill) and understand they can clone repos and run code (PR review mode) and can inject input into/kill agent processes. 2) Do NOT enable the suggested Claude 'bypassPermissions' setting or use --dangerously-skip-permissions unless you fully understand the security impact — it disables model-level protections. 3) Treat any bot token or webhook as sensitive: prefer one-way webhook posting (no BOT token) if you only need relay output; restrict allowed Discord users and channels when using the bridge. 4) Run the skill in a sandbox/container or isolated account, and avoid mounting host secrets into the working directories. 5) If you plan to use PR review or parallel modes, ensure gh/git access is limited and consider running those features on a throwaway runner. 6) The registry metadata omitted several env/credential requirements — expect to supply CODECAST_BOT_TOKEN / .bot-token, a webhook URL file, and gh CLI credentials; only proceed if you accept that scope and have audited the scripts.

Live-stream coding agent sessions to Discord. Zero AI tokens burned.

Setup

First-time setup: see references/setup.md for webhook creation, unbuffer install, bot token, and smoke test.

Invocation

Launch with exec background:true. Background exec sessions survive agent turns and OpenClaw fires notifyOnExit automatically when the process ends.

exec background:true command:"{baseDir}/scripts/dev-relay.sh -w ~/projects/myapp -- claude -p --dangerously-skip-permissions --output-format stream-json --verbose 'Your task here'"

Note the session ID from the response — use it to monitor via process.

Options

Flag	Description	Default
-w <dir>	Working directory	Current dir
-t <sec>	Timeout	1800
-h <sec>	Hang threshold	120
-n <name>	Agent display name	Auto-detected
-r <n>	Rate limit (posts/60s)	25
--thread	Post into a Discord thread	Off
--skip-reads	Hide Read tool events	Off
--review <url>	PR review mode	—
--parallel <file>	Parallel tasks mode	—
--resume <dir>	Replay session	—

For PR review, parallel tasks, Discord bridge, and Codex structured output: see references/advanced-modes.md.

Agent Launch Checklist

1. Start background session → note session ID and PID from response
2. Post to dev channel → announce agent name, workdir, task
3. Write breadcrumb for completion routing:

   echo '{"channel":"<invoking-channel-id>","relayDir":"<relay-dir>","pid":<PID>}' > /tmp/codecast-pending-<PID>.json
   

4. Log to daily memory → session ID, relay dir, invoking channel

The breadcrumb file tells the heartbeat precheck where to post results when the session completes. It auto-detects completion by checking if the PID is still alive.

That's it. When the process ends, OpenClaw's notifyOnExit fires a system event + heartbeat request. The heartbeat handler reads the result from the relay dir's stream.jsonl and posts to the invoking channel.

Completion Detection

OpenClaw handles this natively:

• tools.exec.notifyOnExit: true (default) — system event + heartbeat on process exit
• Heartbeat precheck script detects completed sessions via /tmp/dev-relay-sessions/
• No cron watcher needed

Backup: Append this to the inner agent's prompt for an additional signal:

When completely finished, run: openclaw system event --text "Done: <brief summary>" --mode now

Monitoring

process poll sessionId:<id>        # Check status
process log sessionId:<id>         # View recent output
process kill sessionId:<id>        # Stop session

Agent Support

Agent	Output Mode	Status
Claude Code	stream-json	Full support
Codex	--json JSONL	Full support
Any CLI	Raw ANSI	Basic support

Session Tracking

• Active sessions: /tmp/dev-relay-sessions/<PID>.json (auto-removed on end)
• Event logs: /tmp/dev-relay.XXXXXX/stream.jsonl (7-day auto-cleanup)
• Interactive input: process submit sessionId:<id> data:"message"

Reference Docs

• Setup guide — first-time install, webhook, bot token
• Advanced modes — PR review, parallel tasks, Discord bridge, Codex
• Discord output — message formats, architecture, env vars, troubleshooting