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 deployment-approval-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/deployment-approval-call)<a href="https://agentmods.dev/skills/calle-ai/awesome-phone-call-agents/deployment-approval-call"><img src="https://agentmods.dev/badge/skills/calle-ai/awesome-phone-call-agents/deployment-approval-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/deployment-approval-call"><img src="https://agentmods.dev/badge/skills/calle-ai/awesome-phone-call-agents/deployment-approval-call.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Excessive Agency · line 74 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
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 | $0.01113 |
| Opus 5 | $0.00032 | $0.00557 |
| Sonnet 5 | $0.00013 | $0.00223 |
| Haiku 4.5 | $0.00006 | $0.00111 |
Grade A, and why
deployment-approval-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 — 100 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Deployment Approval Call
Use this skill when you are about to do something you cannot undo and a person has to say yes first.
It does not invent an approval mechanism. It drives the runnable
phone-approval-gate app, which
places one CALL-E call per approver, reads the change out loud, requires the
person to read back a one-time code shown in this conversation and returns an
exit code plus a hash-chained record.
When to use
- A production deploy, restore, migration, bulk refund, mass email, data deletion or any step the user described as needing sign-off.
- The user is not the approver or the user asked for a named owner to authorize the step.
- The approver is away from a keyboard, which is exactly when a phone call beats a message.
When not to use
- The action is reversible and cheap. Ask in chat instead of ringing a phone.
- The user is the approver and is already in this conversation. Ask them here.
- You do not have an enrolled approver with a phone number in E.164 form and a scope that covers the environment. Do not guess a number, a country code, a region or a name.
- Anything medical, legal, financial advice or an emergency. See
references/safety.md. - Chasing a different answer after a rejection. One rejection ends the workflow.
How it works
- You write a request file: the change title, a one line summary, the environment, who requested it and the enrolled approvers in ladder order.
- You run the gate in preview and show the user the exact call script.
- On the user's go-ahead you run it live. The gate prints a six digit code for the current approver. Show that code to the user in your reply, because the approver reads it back on the call and that is what binds the approval to this change. The caller asks who answered before it reads any change detail, so a wrong person hears nothing about the change.
- You read the exit code. Nothing else counts as an approval.
What ships with it
2 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 · 100 lines · 65 tokens per session scan A 8023ec61514a
deployment-approval-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 1,113 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…