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 CALLE-AI/awesome-phone-call-agents --skill service-dispatch-callgit clone --depth 1 https://github.com/CALLE-AI/awesome-phone-call-agentsWrote 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/calle-ai/awesome-phone-call-agents/service-dispatch-call)<a href="https://agentmods.dev/skills/calle-ai/awesome-phone-call-agents/service-dispatch-call"><img src="https://agentmods.dev/badge/skills/calle-ai/awesome-phone-call-agents/service-dispatch-call/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/calle-ai/awesome-phone-call-agents/service-dispatch-call"><img src="https://agentmods.dev/badge/skills/calle-ai/awesome-phone-call-agents/service-dispatch-call.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00065 | $0.01590 |
| Opus 5 | $0.00032 | $0.00795 |
| Sonnet 5 | $0.00013 | $0.00318 |
| Haiku 4.5 | $0.00006 | $0.00159 |
Grade A, and why
service-dispatch-call 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 12d 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 — 145 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Service Dispatch Call
Use this skill when an agent needs to phone a service vendor about a specific job and bring back a decision-ready answer, such as "find out if the plumber can attend unit 12B today and what it costs."
service-dispatch-call is a purpose-bound outbound workflow skill. It places exactly one call per authorized dispatch, asks a bounded set of questions, and returns a structured result. It does not book the job, accept a quote, agree to a price, or promise the vendor anything. Those are commitments, and commitments belong to a person.
The distinction this skill exists to enforce: gathering an answer is not the same as acting on it.
When To Use
Use this skill for:
- maintenance and repair dispatch, where a job must be matched to a vendor by phone
- availability checks against a shortlist of vendors
- quote gathering, where the price is unknown until someone is asked
- ETA confirmation for an already-accepted job
- any outbound call whose output must be machine-readable rather than a transcript
When Not To Use
Do not use this skill to:
- accept a quote, confirm a booking, or agree to any cost during the call
- call a vendor who is not on the caller's authorized contact list
- call a number the user supplied for a different purpose in an earlier, unrelated request
- redial a call whose outcome is unknown
- work around a missing price by asking the vendor to start anyway
- read tenant, patient, customer, or resident personal details to the vendor
- negotiate, counter-offer, or discuss a competitor's quote
- place a call when the required job fields are incomplete
Core Workflow
- Confirm the dispatch is authorized: the job exists, and the vendor is on the authorized contact list for this purpose.
- Extract the dispatch fields listed under Required Fields. Ask for anything missing. Do not infer a phone number, a trade, or a location from earlier context.
- Reserve an idempotency key derived from the dispatch's own identifier, not from the current timestamp or a fresh random value. See
references/idempotency.md. - Record the dispatch as queued before dialling, so a call that is accepted but never reported is still visible.
- Build the call brief from
references/call-brief.md. The brief opens with a disclosure and refers to the job by an opaque reference, never by an address or a person's name. - Declare the result schema before placing the call. See
references/result-schema.md. - Place exactly one call.
- Validate the returned result against the declared schema. Drop fields you did not ask for. Refuse values outside the declared options rather than coercing them.
- Classify the outcome as
answered,declined,no_answer, orunknown. - If the result contains a cost, a commitment, or a low-confidence field, raise it for human approval and stop. Report the reason.
What ships with it
6 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 12d ago First seen · 145 lines · 65 tokens per session scan A 539b4c8830a2
service-dispatch-call is a skill published in the GitHub repository CALLE-AI/awesome-phone-call-agents (88 stars, last pushed yesterday), licensed MIT. It adds 65 tokens to every session and 1,590 once invoked, about $0.0003 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 2026-08-30.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…