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/ai-dispatchgit 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 | $0.00046 | $0.00664 |
| Opus 5 | $0.00023 | $0.00332 |
| Sonnet 5 | $0.00009 | $0.00133 |
| Haiku 4.5 | $0.00005 | $0.00066 |
Grade A, and why
ai-dispatch scanned grade A with 0 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.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 97 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AI Dispatch
Dispatch tasks to different AI backends via dispatch <backend> "prompt".
First Use — Auto Setup
Before dispatching, check if dispatch is available:
which dispatch
If not found, run setup:
bash $SKILL_DIR/../../scripts/setup.sh
If config is missing (~/.config/ai-dispatch/config.json), setup will:
- Check environment for existing
ANTHROPIC_API_KEY/ANTHROPIC_AUTH_TOKEN - If found, auto-create config from env
- If not, ask the user for API keys
- Install
dispatchanddcheckto PATH
Usage
# Simple — backend + prompt (auto-adds all flags)
dispatch ark-code "implement binary search"
dispatch glm "translate to Chinese: hello world"
dispatch ark-minimax "analyze this codebase"
# Check progress
dcheck --latest
# List backends
dispatch --list
Available Backends
| Command | Model | Best for |
|---|---|---|
ark-code |
Doubao Seed 2.0 Code | Code generation |
ark-pro |
Doubao Seed 2.0 Pro | General reasoning |
ark-minimax |
MiniMax M2.5 | Analysis, research |
ark-kimi |
Kimi K2.5 | Long context |
ark-deepseek |
DeepSeek V3.2 | Complex reasoning |
ark-glm |
GLM-4.7 | Chinese via Ark |
ark-auto |
Auto routing | Smart selection |
glm |
GLM-5 | Chinese language |
Adding Custom Backends
Edit ~/.config/ai-dispatch/config.json:
{
"backends": {
"my-api": {
"description": "My custom API",
"env": {
"ANTHROPIC_BASE_URL": "https://my-api.example.com",
"ANTHROPIC_API_KEY": "sk-..."
},
"models": { "opus": "my-model", "sonnet": "my-model", "haiku": "my-model" }
}
}
}
Then: dispatch my-api "hello"
Advanced
# Explicit mode (full control over claude flags)
dispatch ark claude -p --dangerously-skip-permissions "prompt"
# Interactive (named pipe for follow-ups)
dispatch ark claude-interactive
# Resume session
dispatch ark claude -p --resume <SESSION_ID> "follow up"
# Codex
dispatch ark codex "prompt"
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 · 97 lines · 46 tokens per session scan A bf25309af3a3
ai-dispatch is a command published in the GitHub repository gettalon/talon-plugins (6 stars, last pushed 5mo ago), licensed MIT. It adds 46 tokens to every session and 664 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other commands, from other repositories
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.
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).
review-session
Arm-2 — critique the current/last session for efficiency & quality, emit a Zone-A distillation, offer a deliberate GitHub feedback report.
feedback
File a plugin-capability-gap note, or flush queued notes to GitHub issues.
telemetry
Inspect, opt in/out of, and audit mochi's anonymous usage telemetry.