Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add commands/gettalon/talon-plugins/channels-setupgit clone --depth 1 https://github.com/gettalon/talon-pluginsWhat it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00030 | $0.00881 |
| Opus 5 | $0.00015 | $0.00441 |
| Sonnet 5 | $0.00006 | $0.00176 |
| Haiku 4.5 | $0.00003 | $0.00088 |
Grade D, and why
channels-setup scanned grade D with 3 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Downloads and executes remote codehighSupply chain
curl | sh runs whatever the server returns today, which is not necessarily what it returned when this was reviewed.
curl -s -X POST http://localhost:21568/auth/local | python3 -c "import sys,json; print(json.load(sys.stdin).get('token',''))" Reads agent configuration directoriesmediumAgent snooping
.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.
cat ~/.claude/settings.json 2>/dev/null | grep -A 3 "talon-channels" || echo "Not configured" Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
curl -s http://localhost:21568/health 2>/dev/null || echo "Server not running" How it starts
The opening of the file, as written. The whole thing — 121 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Channels Setup Guide
Help the user set up the Talon Channels universal server so any client can connect to Claude Code via WebSocket.
Steps
1. Verify Installation
The channels MCP server should already be configured. Verify:
# Check if the channels server is in MCP config
cat ~/.claude/settings.json 2>/dev/null | grep -A 3 "talon-channels" || echo "Not configured"
2. Check Server Health
curl -s http://localhost:21568/health 2>/dev/null || echo "Server not running"
3. Get Auth Token
Clients need a token to connect:
curl -s -X POST http://localhost:21568/auth/local | python3 -c "import sys,json; print(json.load(sys.stdin).get('token',''))"
Or read from discovery file:
cat ~/.talon/channels_token 2>/dev/null || echo "No token file"
4. Connect a Client
Any WebSocket client can connect:
ws://localhost:21568/ws?token=TOKEN&mode=full&name=my-client
Mode options:
chat— Chat only, no hook eventsmonitor— Read-only view of all eventsfull— Everything: chat + hooks + permissionscustom— Pick categories:?mode=custom&categories=tools,permissions,session
Available categories: chat, tools, permissions, session, notifications, subagents, lifecycle, filesystem, worktree, compact, elicitation, prompts
5. Example: Connect from Node.js
import WebSocket from 'ws';
const token = 'YOUR_TOKEN';
const ws = new WebSocket(`ws://localhost:21568/ws?token=${token}&mode=full&name=my-app`);
ws.on('message', (data) => {
const msg = JSON.parse(data);
const payload = msg.payload;
if (payload.type === 'event' && payload.data.type === 'hook_event') {
console.log('Hook:', payload.data.hook_event_name, payload.data.data);
}
if (payload.type === 'stream') {
console.log('Reply:', payload.event);
}
});
// Send a chat message
ws.send(JSON.stringify({
type: 'chat_message',
text: 'Hello from my app!',
chat_id: 'my-chat-1',
}));
// Respond to permission request
ws.send(JSON.stringify({
type: 'permission_verdict',
request_id: 'req-123',
behavior: 'allow',
}));
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 2d ago First seen · 121 lines · 30 tokens per session scan D 8b0591d972ac
channels-setup is a command published in the GitHub repository gettalon/talon-plugins (6 stars, last pushed 5mo ago), licensed MIT. It adds 30 tokens to every session and 881 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it D with 3 findings (downloads and executes remote code, reads agent configuration directories, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other commands, from other repositories
review-session
Arm-2 — critique the current/last session for efficiency & quality, emit a Zone-A distillation, offer a deliberate GitHub feedback report.
render
Inspect an archived transcript (gzipped) — show counts, tool calls, errors. Useful after a PreCompact or SessionEnd, before deciding to write a retroactive /continuum:checkpoint.
qa
Dispatch a verifiable browser task to the qa-tester subagent. Use for regression checks, smoke tests, and any task with a clean pass/fail outcome. Supports an EXHAUSTIVE mode that verifies every control behind an honesty gate.
design-qa
Agent-driven design QA — walk the running app, judge design/UX, and drop a Comment-Mode comment on every issue (visible to the human as pins). Then read the session back and fix everything in bulk. Optional focus argument steers the pass.
checkpoint
Write a new link in the continuum chain summarizing decisions/changes since the last link.
dream
Roll up the last N links into a single phase-digest link; originals move to archived/ (never deleted).