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 call-data-minimization-auditorgit 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/call-data-minimization-auditor)<a href="https://agentmods.dev/skills/calle-ai/awesome-phone-call-agents/call-data-minimization-auditor"><img src="https://agentmods.dev/badge/skills/calle-ai/awesome-phone-call-agents/call-data-minimization-auditor/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/call-data-minimization-auditor"><img src="https://agentmods.dev/badge/skills/calle-ai/awesome-phone-call-agents/call-data-minimization-auditor.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 | $0.01781 |
| Opus 5.5 | $0.00031 | $0.00712 |
| Sonnet 5.5 | $0.00015 | $0.00356 |
| Haiku 4.5 | $0.00008 | $0.00178 |
Grade A, and why
call-data-minimization-auditor 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 15d 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 — 139 lines — stays where its author put it; the contents beside it link to each section on GitHub.
call-data-minimization-auditor
The goal file is the shopping list. The agent buys the list - nothing else, not twice, and never reads the numbers back in full.
Data minimization is the principle that a data collector asks for what the task needs and nothing more (GDPR Article 5(1)(c): "adequate, relevant and limited to what is necessary"). A calling agent that follows the principle in its goal file but drifts on the line - "while I have you, what is your date of birth?", re-asking a name it already captured, or repeating a full card number back "to confirm" - collects data the task never authorized, one polite sentence at a time.
On a phone call the risk compounds. The line is recorded, the transcript is stored, and every extra datum the agent elicits or repeats in full becomes another copy of sensitive personal data in another log. An agent that asks for two fields and repeats one masked is a smaller liability than one that asks for five and echoes a card number verbatim. This skill audits the agent's asks against the goal file's scope, lexically and offline.
When To Use
- after any CALL-E call that collects personal data, together with the goal file (plain text or plan JSON) the call was built from
- when a transcript shows the agent asking for data nobody put in the goal, re-asking for data the caller already gave, or reading a full card or ID number back instead of a masked confirmation
- before placing calls, to craft a minimal-collection intake goal with an explicit fields list, a refusal line, a masking policy, and a no-re-asking rule
What It Checks
Verdicts
| Verdict | Meaning |
|---|---|
MINIMAL |
Every agent data request is in the goal's scope, none redundant, no full-datum echo |
OVERCOLLECTION_DETECTED |
At least one request is out of scope, redundant, or an echo of a full sensitive datum (attached to the request or listed under echoes) |
NO_DATA_REQUESTED |
The agent made no lexically detectable data requests (callee volunteering never counts against it) |
GOAL_FILE_LACKS_FIELD_LIST |
Requests exist but the goal file names no recognizable data categories; every request is unverifiable |
What ships with it
10 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.
- references/example-goal-unverifiable.txt 51 B
- references/example-goal-vague.txt 25 B
- references/example-goal.txt 204 B
- references/example-transcript-overcollection.json 1.2 KB
- references/example-transcript-unverifiable.json 764 B
- references/example-transcript.json 760 B
- references/examples.md 6.4 KB
- references/safety.md 1.9 KB
- scripts/data_minimization_auditor.py 18 KB runs code
- scripts/test_data_minimization_auditor.py 27 KB runs code
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.
- 15d ago First seen · 139 lines · 77 tokens per session scan A aed0126f1535
call-data-minimization-auditor 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 1,781 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 2026-10-05.
Other skills, from other repositories
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…
next-cache-components-optimizer
Optimize the meaningful UI available immediately from a Next.js route on an initial load (hard navigation) or named client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route and entry point at a time; the shipped test then guards…