agentmods.dev

znak-callops

znak-callops is a skill for Claude Code, Codex from CALLE-AI/awesome-phone-call-agents. It costs 46 tokens per session (976 once invoked), scanned A, original, MIT.

A structured phone inquiry that asks an authorized service provider about availability and price without making a booking. It preserves exact transcript quotations and marks information that remains unknown.

In plain words
What is it for?
It prepares and checks one service inquiry, records the provider's answers and quotations, and returns an inspectable result.
Why use it?
A caller may need to know where each answer came from, rather than relying on an unchecked summary. The workflow separates what was said from what has been independently verified.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: reads ~/.codex paths; mentions Codex.

not rated 109repo +2 yesterday A scan 46 tokens original MIT

Good fit It prepares and checks one service inquiry, records the provider's answers and quotations, and returns an inspectable result.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/calle-ai/awesome-phone-call-agents/znak-callops
View source ↗ CALLE-AI/awesome-phone-call-agents
Install

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.

Any agent
npx skills add CALLE-AI/awesome-phone-call-agents --skill znak-callops
Clone the repo
git clone --depth 1 https://github.com/CALLE-AI/awesome-phone-call-agents

Made for: Claude Code, Codex.

Wrote 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.

agentmods badge for znak-callops

README.md
[![agentmods](https://agentmods.dev/badge/skills/calle-ai/awesome-phone-call-agents/znak-callops/github.svg)](https://agentmods.dev/skills/calle-ai/awesome-phone-call-agents/znak-callops)
Your own site
<a href="https://agentmods.dev/skills/calle-ai/awesome-phone-call-agents/znak-callops"><img src="https://agentmods.dev/badge/skills/calle-ai/awesome-phone-call-agents/znak-callops/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.

agentmods 80×15 button for znak-callops

Your own site · 80×15
<a href="https://agentmods.dev/skills/calle-ai/awesome-phone-call-agents/znak-callops"><img src="https://agentmods.dev/badge/skills/calle-ai/awesome-phone-call-agents/znak-callops.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 46 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 976 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00046 $0.00976
Opus 5.5 $0.00018 $0.00390
Sonnet 5.5 $0.00009 $0.00195
Haiku 4.5 $0.00005 $0.00098

Measured 1mo ago against content hash 7458baae3a46, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

znak-callops 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.

The scan reads SKILL.md. This mod also ships 4 executable files (scripts/callops.py, scripts/dispatch.py, scripts/test_callops.py, …), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

skills/znak-callops/SKILL.md · 78 lines

How it starts

The opening of the file, as written. The whole thing — 78 lines — stays where its author put it; the contents beside it link to each section on GitHub.

ZNAK CallOps

Turn a bounded service inquiry into a CALL-E plan and an inspectable result. This skill adds a small executable evidence checker: a completed call is not a verified answer, and a quote present in a transcript is not independent proof of its truth.

Setup and verification

Requires Python 3.10+ for the local helper, and an Agent Skills-compatible host with authenticated CALL-E MCP tools or Python 3.11+ with the optional official SDK adapter for live calls. Copy this whole directory to the host's skill directory. For Codex, use ~/.codex/skills/znak-callops/. Use references/call-e.md to connect the official provider. The helper uses only Python's standard library and never connects to a network.

From the repository root, run the synthetic no-call demonstration:

python3 skills/znak-callops/scripts/callops.py demo
python3 -m unittest discover -s skills/znak-callops/scripts -p 'test_*.py'

Read references/examples.md for inputs, expected results, and manual verification. These tests exercise local code, not the CALL-E service. The live host integration has not been verified by a real call in this contribution. For the optional executable SDK path, read references/sdk-dispatch.md. dispatch.py defaults to a no-network preview and imports the official SDK only after explicit live/read opt-in. No live CALL-E call has been verified through either path.

Workflow

  1. Establish the user's exact question, service scope, preferred time window, known destination, language, and permission to call that recipient for this purpose. Read references/safety.md before dispatch.
  2. Use prepare-goal with the resolved request to produce the bounded call brief. Show the masked destination, purpose, and inquiry only; do not book, accept a quote, pay, cancel, or disclose additional personal details. A request to prepare a plan alone does not authorize a phone call.
  3. Invoke CALL-E plan_call with the user's latest message verbatim in user_input. Pass only known fields; use the prepared brief as goal. Follow the live tool schema. A plan does not place a call.
  4. After the user clearly authorizes this call and the plan is ready, invoke run_call once with exactly the returned plan_id and confirm_token. Keep those opaque values out of public artifacts. Retain the returned run_id in the host's private task record. Follow the recovery rules in the provider reference; a timeout is not permission to redial.
  5. Read get_call_run until a terminal outcome or a monitoring pause. If transcript turns are available, preserve their exact text, order, and speaker. Map them to the helper's documented input. The provider's response schema is discovered at runtime; this normalized packet is local, not a CALL-E wire format.
  6. Propose full provider-turn quotations for availability, quoted_price, and follow_up. Never clip qualifying words. Run validate-result on that packet. If the provider exposes only a summary, leave the unsupported fields UNKNOWN.
  7. Return the checked quotes and their source pointers. Review relevance and ambiguity: the checker verifies quote identity, not semantic interpretation, speaker authenticity, provider honesty, or that a time remains available. Leave booking and other commitments to a separate user decision.

Read the full file on GitHub · 78 lines

Files

What ships with it

12 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.

Changes

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.

  1. 1mo ago First seen · 78 lines · 46 tokens per session scan A 7458baae3a46

Subscribe to this mod's changes

znak-callops is a skill published in the GitHub repository CALLE-AI/awesome-phone-call-agents (109 stars, last pushed yesterday), licensed MIT. It adds 46 tokens to every session and 976 once invoked, about $0.0002 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.

Research
Related

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…

microsoft/ai-agents-for-beginners · 200 tokens

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…

vercel/next.js · 95 tokens

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.

microsoft/vscode · 53 tokens

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…

microsoft/vscode · 71 tokens

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…

vercel/next.js · 83 tokens

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…

vercel/next.js · 123 tokens