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 exception-resolution-callsgit 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/exception-resolution-calls)<a href="https://agentmods.dev/skills/calle-ai/awesome-phone-call-agents/exception-resolution-calls"><img src="https://agentmods.dev/badge/skills/calle-ai/awesome-phone-call-agents/exception-resolution-calls/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/exception-resolution-calls"><img src="https://agentmods.dev/badge/skills/calle-ai/awesome-phone-call-agents/exception-resolution-calls.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 | $0.00077 | $0.02997 |
| Opus 5.5 | $0.00031 | $0.01199 |
| Sonnet 5.5 | $0.00015 | $0.00599 |
| Haiku 4.5 | $0.00008 | $0.00300 |
Grade A, and why
exception-resolution-calls 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.
How it starts
The opening of the file, as written. The whole thing — 288 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Resolving blocked workflows by phone
When to use this
Use it when three things are true at once:
- a workflow is stuck on a fact only a person has ("did you get the order?", "will it ship Friday?", "can you take this job?");
- the answer has to change system state, not just get logged;
- a wrong answer has a real cost, so "we think they said yes" is not good enough.
Do not use it for open-ended conversations, for anything where the caller must negotiate or commit the business to something, or where no bounded set of questions exists. Those are not exception resolution; they are sales, and they need a human.
The shape of the problem
The tempting design is: call, ask the model what happened, update the record. That design fails in production for a reason worth stating plainly.
Extraction and authority are different jobs. A model is good at turning a messy conversation into structured fields. It is not the right thing to decide whether a purchase order may be closed, because when the evidence is thin it will still return something, and that something becomes a business fact nobody chose.
So split them:
CALL-E Your policy code
────── ────────────────
holds the conversation decides what the answer means
extracts strict JSON re-validates the JSON
reports confidence can refuse to act on low confidence
never touches state owns every state transition
Build it in this order
1. Model uncertainty before you model success
Write the result schema first, and give every judgment field an unknown
value. This is the single highest-leverage decision in the whole design.
{
"type": "object",
"additionalProperties": false,
"required": ["received", "po_status", "needs_human"],
"properties": {
"received": {
"type": "string",
"enum": ["yes", "no", "unknown"],
"description": "Use yes ONLY when they clearly confirm receipt. Use unknown when the answer was hedged, second-hand or unclear — for example 'I think someone in logistics has it'."
},
"po_status": {
"type": "string",
"enum": ["on_time", "delayed", "blocked", "unknown"],
"description": "Never infer a status from tone or from a polite acknowledgement."
},
"needs_human": {
"type": "string",
"enum": ["yes", "no", "unknown"],
"description": "Use yes when they ask for a person, dispute the record, or raise pricing, payment terms or contract changes."
}
}
}
What ships with it
5 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.
- 1mo ago First seen · 288 lines · 77 tokens per session scan A 0fa53f2499bc
exception-resolution-calls is a skill published in the GitHub repository CALLE-AI/awesome-phone-call-agents (109 stars, last pushed yesterday), licensed MIT. It adds 77 tokens to every session and 2,997 once invoked, about $0.0003 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 2026-09-15.
Other skills, from other repositories
story-readiness
Checks whether a story is ready to implement: clear acceptance criteria, no open questions, valid ADR and dependencies. Use when the user asks if a story, or the sprint's stories, are ready to start or build.
recipe-create-meet-space
Create a Google Meet meeting space and share the join link.
workthreads
SpecStory Workthreads - a weekly work-thread rollup across a team's repos from SpecStory coding histories (any agent - Claude Code, Codex, Cursor, Gemini, and more). It groups the window's sessions into threads of work per project and labels each new / open / recently closed, so a lead sees what shipped, what is still…
atmos-config
Atmos root configuration: atmos.yaml discovery, precedence, deep merging, basepath, imports, minimal bootstrap, and routing to narrower Atmos skills.
projects
List all managed projects with status, branch, open PRs, and open issue counts — portfolio-level view.
handle-linkedin-connection-request-signal
Use this skill when someone sends a team member an inbound LinkedIn connection request. An inbound request is a deliberate, ACTIVE first-party intent signal — meaningfully stronger than a passive profile view — and it deserves different scoring rules. The skill resolves and enriches the requester, gates them through…