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 skills/conn-castle/agent-layer/dispatch-agentnpx skills add conn-castle/agent-layer --skill dispatch-agentgit clone --depth 1 https://github.com/conn-castle/agent-layerWhat 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 | $0.00049 | $0.00405 |
| Opus 5 | $0.00024 | $0.00202 |
| Sonnet 5 | $0.00010 | $0.00081 |
| Haiku 4.5 | $0.00005 | $0.00040 |
Grade A, and why
dispatch-agent 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.
What it actually says
Dispatch Agent
If the MCP tools are unavailable, report the missing server; do not substitute command-line calls.
- Call
dispatch_options; map the requested target toagent,model, andreasoning_effort. Ask if ambiguous. - Call
dispatch_startonce with exactly one prompt source and retain its session handle. Do not replace active work. - Call
dispatch_waitwith the handle. If it returnsrunningor is interrupted, call it again with the same handle. Oncompleted, read the Markdown file atresult_path; reportfailedorcancelled.
For parallel work, call dispatch_start once per independent conversation and
retain each handle. Call dispatch_wait for those handles in parallel when supported.
Continuing a conversation
After a terminal result, use dispatch_continue only for useful follow-up,
requested information, or corrective action within the current scope. It
preserves the provider conversation context. Pass the same handle and exactly
one prompt source, then call dispatch_wait again.
Use dispatch_start when fresh context is required, not dispatch_continue.
Cancelling a conversation
dispatch_cancel permanently stops active provider work. Call it only when the
user explicitly requests cancellation or an active skill explicitly instructs
you to abandon the dispatch.
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 · 38 lines · 49 tokens per session scan A 2fc73a19a75d
dispatch-agent is a skill published in the GitHub repository conn-castle/agent-layer (10 stars, last pushed 3d ago), licensed MIT. It adds 49 tokens to every session and 405 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 skills, from other repositories
deepagent-research-delegation
Use this skill when external references or broader codebase discovery is required; delegate to a research subagent and synthesize findings.
copilotkit-setup
Use when adding CopilotKit to an existing project or bootstrapping a new CopilotKit project from scratch. Covers framework detection, package installation, runtime wiring (managed Intelligence or self-hosted SSE), provider setup, and first working chat integration.
copilotkit-channels
Use for the CODE half of a managed Intelligence Channel with Slack or Microsoft Teams: customising the Channel a CLI-scaffolded project already ships, or — for a project the CLI did not generate — writing the Channel declaration, the long-running host, and the awaited activation call. Teams provider setup is in scope…
runtime
@copilotkit/runtime — mount a fetch-native CopilotRuntime on any JS server, wire middleware, pick an AgentRunner, instantiate BuiltInAgent (Factory Mode with TanStack AI is the preferred default) or plug in any of 12 external agent frameworks (Mastra, LangGraph, CrewAI Crews/Flows, PydanticAI, ADK, LlamaIndex, Agno…
copilotkit-integrations
Use when wiring an external agent framework (LangGraph, CrewAI, PydanticAI, Mastra, ADK, LlamaIndex, Agno, Strands, Microsoft Agent Framework, or others) into a CopilotKit application via the AG-UI protocol.
a2ui-renderer
Render A2UI (Agent-to-UI declarative surfaces) in CopilotKit v2. Enable the runtime via CopilotRuntime({ a2ui: {...} }), then enable the provider via . Auto-activates via /info — do NOT manually pass renderActivityMessages. createA2UIMessageRenderer ships from @copilotkit/react-core/v2; low-level primitives…