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 google-form-callbackgit 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/google-form-callback)<a href="https://agentmods.dev/skills/calle-ai/awesome-phone-call-agents/google-form-callback"><img src="https://agentmods.dev/badge/skills/calle-ai/awesome-phone-call-agents/google-form-callback/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/google-form-callback"><img src="https://agentmods.dev/badge/skills/calle-ai/awesome-phone-call-agents/google-form-callback.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 2 findings, 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 274 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.
- medium Rogue Agent · line 14 Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.Fix: Remove any persistence mechanisms (cron jobs, startup scripts, state files). Skills should not maintain state across sessions without explicit user consent.
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 | $0.00033 | $0.03110 |
| Opus 5 | $0.00016 | $0.01555 |
| Sonnet 5 | $0.00007 | $0.00622 |
| Haiku 4.5 | $0.00003 | $0.00311 |
Grade A, and why
google-form-callback 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 — 362 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Google Form Callback
Use this skill when the user wants to process responses from one or more Google Forms and call respondents who submitted a form that clearly authorizes a phone follow-up.
google-form-callback is an intake, scheduling, and safety orchestration skill.
It does not create a new phone provider, does not create provider-side recurring
schedules, and does not call every phone-looking value in a form. It turns a
known form template into reviewed one-off call candidates.
When To Use
Use this skill for:
- Google Form lead follow-up workflows
- quote request forms
- callback request forms
- appointment or support follow-up forms
- dry-run previews before placing calls from form submissions
- scheduled polling of one or more forms
When Not To Use
Do not use this skill to:
- scrape arbitrary forms for phone numbers
- call respondents from forms whose description or terms do not authorize phone follow-up
- infer country codes or repair ambiguous phone numbers
- create provider-side recurring phone-call jobs
- expose Google OAuth tokens, provider credentials, confirmation tokens, or full phone numbers in user-facing summaries
- provide medical, legal, financial, or emergency advice during generated calls
Template Contract
Edit skills/google-form-callback/template.md when the form fields or generated
CALL-E goal should change. The extraction script reads this file directly, so
field and goal changes should not require code edits.
Do not duplicate business field names or goal text in SKILL.md. Treat
template.md as the source of truth for:
- form fields and required fields
- the E.164 phone field
- the recipient name field
- generated CALL-E goal text
- writeback result and summary field names
Phone numbers must already be E.164.
Workflow
- Confirm the user explicitly wants to process specific Google Forms for callback calls.
- Confirm each form's description or terms make phone follow-up clear.
- Run auth preflight before any export or dry-run. For an end-to-end callback workflow, Google and CALL-E must both be ready before continuing. If either side is unauthenticated, start the repair flow and stop until the user completes authorization.
- Obtain Google Forms metadata and response payloads for the requested form IDs or Drive-discovered forms, plus any submitted-time window, preferably through the local OAuth Google API client.
- Extract field slugs from form item descriptions or help text.
- Normalize each response into structured fields.
- Validate required template fields, E.164 phone numbers, and responseId dedupe state.
- Compile the provider
goalfromskills/google-form-callback/template.md. - Run a dry-run preview first. Show masked phone numbers and skip reasons.
- Place calls only after explicit user confirmation or inside an already approved scheduled run.
- Record processed
responseIdvalues and write the template-defined result and summary fields to the matching row in the linked response spreadsheet.
What ships with it
17 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/examples.md 5.3 KB
- references/google-forms-api.md 7.8 KB
- references/google-oauth-setup.md 2.0 KB
- references/response-mapping.md 3.7 KB
- references/runtime-prompt.md 4.1 KB
- references/safety.md 3.9 KB
- scripts/extract-callback-candidates.mjs 15 KB runs code
- scripts/google-auth.mjs 3.8 KB runs code
- scripts/google-form-api-client.mjs 7.2 KB runs code
- scripts/google-local-api-client.mjs 29 KB runs code
- scripts/google-oauth-lib.mjs 8.8 KB runs code
- scripts/preflight-auth.mjs 6.0 KB runs code
- scripts/process-callback-candidates.mjs 20 KB runs code
- scripts/render-form-script.mjs 16 KB runs code
- scripts/render-runtime-plans.mjs 7.9 KB runs code
- scripts/template-lib.mjs 3.7 KB runs code
- template.md 2.1 KB
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 · 362 lines · 33 tokens per session scan A d145f8e0d1b1
google-form-callback is a skill published in the GitHub repository CALLE-AI/awesome-phone-call-agents (85 stars, last pushed yesterday), licensed MIT. It adds 33 tokens to every session and 3,110 once invoked, about $0.0002 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…
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
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…