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 skills add conn-castle/agent-layer --skill dispatch-agentgit clone --depth 1 https://github.com/conn-castle/agent-layerWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/conn-castle/agent-layer/dispatch-agent)<a href="https://agentmods.dev/skills/conn-castle/agent-layer/dispatch-agent"><img src="https://agentmods.dev/badge/skills/conn-castle/agent-layer/dispatch-agent/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/conn-castle/agent-layer/dispatch-agent"><img src="https://agentmods.dev/badge/skills/conn-castle/agent-layer/dispatch-agent.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What 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 5.1 | $0.00049 | $0.00544 |
| Opus 5.5 | $0.00020 | $0.00218 |
| Sonnet 5.5 | $0.00010 | $0.00109 |
| Haiku 4.5 | $0.00005 | $0.00054 |
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 1mo 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 itshandleandinvocation_id. Do not replace active work. - Call
dispatch_waitwith exactly one ofhandleorinvocation_id. If it returnsrunningor is interrupted, call it again with the same selector. An oldinvocation_idnever follows a later continuation. Oncompleted, calldispatch_outputwith artifactfinal_answer(wait also returnsresult_path). Onfailedorcancelled, calldispatch_inspectanddispatch_outputwith artifacteventsfor available partial output; cancelled is not termination proof.
For parallel work, call dispatch_start once per independent conversation and
retain each handle and invocation_id. Call dispatch_wait for those selectors
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 and creates a new invocation_id.
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.
Do not continue while termination_confirmed is false for the active
invocation.
Cancelling a conversation
dispatch_cancel requests that provider work stop. Call it only when the
user explicitly requests cancellation or an active skill explicitly instructs
you to abandon the dispatch. Inspect termination_confirmed before treating
the invocation as unable to execute. Repeated cancel retries an unconfirmed
stop.
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.
- 1mo ago Changed · +10 lines 158a30433928
- 1mo 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 today), licensed MIT. It adds 49 tokens to every session and 544 once invoked, about $0.0002 per session on Opus 5.5. 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
artifact-deploy
One-click deploy a user's pre-built app/artifact into their OWN AWS account and get a global public HTTPS link (Vercel-like), with a default TTL and promote-to-persistent. Use when the user says "deploy this", "ship this demo", "give me a public link", "share this externally", or "deploy to AWS".
explain-for
Explain a topic, code, error or design decision for one named audience (a 5-year-old, a manager, a designer, a grad student, a parent). Resolves who it is for, pins the ground truth first, then tunes vocabulary, analogy, tone and depth to that audience. Use when an audience is named.
papyrus-latex-suggestions
Propose inline replacement text (old -> new) as accept/reject suggestions, LaTeX 'suggesting mode' / track changes, rendered in the PDF. Use when the author wants concrete edit proposals to accept or reject. For remarks ABOUT the text rather than replacements, use papyrus-latex-comments.
pptagent
Create and revise editable PowerPoint presentations from a brief using HTML slide sources, rendering, and visual review. Use when the requested deliverable is a PPTX deck. The host authors the slides; text-only hosts can use an external visual reviewer.
company-employee
The protocol every employee of a PenguinHarness organization follows — read the handbook first, act on [orgtrigger] work runs, schedule tickets from the desk session and do the work in ticket sessions, block instead of idling, ask the board in the all-hands channel before anything heavy, costly, irreversible or…
agent-initialization
Initialize or extend an Agent from a user requirement - write AGENTS.md, set identity metadata, and create, install or import Skills and hook packages (scripts the harness runs on every prompt, before tool calls, or after a task). For an Agent with an in-app workbench, pair with penguin-plugin; for a standalone…