A safety check for exact identifiers heard during a phone call, such as a confirmation number, ticket number, order ID, or pickup number. It classifies the value before another system writes it into a record.

Use it when a workflow must save an exact value extracted from a call. It checks the returned value and records whether it was only spoken, confirmed in conversation, mismatched, or independently verified.

A phone transcript can contain a plausible but incorrect identifier, and a successful read-back does not prove it is true. This prevents an unverified string from being treated as a fact.

exact-ref — Skill for Claude Code and Codex by CALLE-AI

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 exact-ref

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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/calle-ai/awesome-phone-call-agents/exact-ref/github.svg)](https://agentmods.dev/skills/calle-ai/awesome-phone-call-agents/exact-ref)

Your own site

<a href="https://agentmods.dev/skills/calle-ai/awesome-phone-call-agents/exact-ref"><img src="https://agentmods.dev/badge/skills/calle-ai/awesome-phone-call-agents/exact-ref/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/calle-ai/awesome-phone-call-agents/exact-ref"><img src="https://agentmods.dev/badge/skills/calle-ai/awesome-phone-call-agents/exact-ref.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 47 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 1,332 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.

Model	Per session	Once invoked
Fable 5.1	$0.00047	$0.01332
Opus 5.5	$0.00019	$0.00533
Sonnet 5.5	$0.00009	$0.00266
Haiku 4.5	$0.00005	$0.00133

Measured 1mo ago against content hash d74e97b34f69, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

exact-ref 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 1 executable file (scripts/exactref.mjs), 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/exact-ref/SKILL.md · 100 lines

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.

ExactRef

Use this skill when a CALL-E structured result contains an identifier that will be written into a record: confirmation number, ticket, off-hire reference, order id, pickup number.

This skill does not place a call. It compiles a safe outbound task, then gates the returned identifier with a character-level check and a named provenance state. Fixture replay is the default. Live CALL-E create is host-owned and fail-closed.

Hosts: any Agent Skills-compatible environment (Claude Code, Codex, Cursor, OpenClaw, skills.sh installs). Provider: CALL-E Calls API, Python/TypeScript SDK, CLI, or MCP get_call_run output. Side effects: none. The script reads a JSON file and prints a decision.

When to use

The next write depends on an exact character string from a phone call
CALL-E returned structured_result and someone is about to treat it as true
You need a readback protocol in the outbound task without leaking the intended value
Top-level status is queued and you must not create a second call

When not to use

The value is already on a portal, email, or paper — that is no_call
Medical, legal, emergency, or payment-card capture
Guessing a phone number, country, language, or run_id
Calling track_ui_events or any undocumented MCP tool
Treating MCP COMPLETED or Calls task_completed as permission to write

Run it (no install, no credentials)

scripts/exactref.mjs is a single zero-dependency Node 18+ file. Exit 0 only when the decision is writable, 2 when classified but blocked, 1 on bad input.

# The live 2026-09-05 miss: readback said yes, one letter is wrong → mismatch, exit 2
node scripts/exactref.mjs classify --intended 07198FECTIST --extracted 07198SECTIST --readback

# Gate a saved CALL-E call object (REST, SDK, `calle call status --json`, or MCP result{} envelope)
node scripts/exactref.mjs gate --call references/call-fs01.json --field identifier --intended 07198FECTIST

# Human typed the value from a written channel → independently_verified, exit 0
node scripts/exactref.mjs verify --intended 07198FECTIST --extracted 07198SECTIST --typed 07198FECTIST --second-channel

# Compile an outbound task; exit 2 if the intended value leaks into it
node scripts/exactref.mjs compile --field "off-hire reference" --destination "the supplier desk" --intended 07198FECTIST

# Self-check: re-classify every fixture, exit 1 if any disagrees with its expected provenance
node scripts/exactref.mjs fixtures

Read the full file on GitHub · 100 lines

Files

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.

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.

1mo ago First seen · 100 lines · 47 tokens per session scan A d74e97b34f69

Subscribe to this mod's changes

exact-ref is a skill published in the GitHub repository CALLE-AI/awesome-phone-call-agents (109 stars, last pushed yesterday), licensed MIT. It adds 47 tokens to every session and 1,332 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 2026-09-16.

Security

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