What is schema-assumption-verifier?

A checker for assumptions about the JSON returned by the CALL-E phone-call API. It compares the application's parsing and status checks with a real call-status response.

Use it after capturing a real response and after writing code that classifies calls or extracts data from them.

It helps prevent code from missing terminal calls, transcripts, or results because the response format differs from what the code expects.

schema-assumption-verifier — Agent for Claude Code 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.

Clone the repo

git clone --depth 1 https://github.com/CALLE-AI/awesome-phone-call-agents

Made for: Claude Code.

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/agents/calle-ai/awesome-phone-call-agents/schema-assumption-verifier/github.svg)](https://agentmods.dev/agents/calle-ai/awesome-phone-call-agents/schema-assumption-verifier)

Your own site

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

Per session 61 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 542 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	$0.00061	$0.00542
Opus 5.5	$0.00024	$0.00217
Sonnet 5.5	$0.00012	$0.00108
Haiku 4.5	$0.00006	$0.00054

Measured 11d ago against content hash add575124c56, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

schema-assumption-verifier 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 11d 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.

apps/python/vendor-discovery-agent/.claude/agents/schema-assumption-verifier.md · 38 lines

What it actually says

You are a schema verification agent. You will be given the real raw JSON output from calle call status --run-id <id> and must check every assumption the codebase makes about that output.

What you must check

Status field normalization
- The API returns status strings with spaces (e.g. "NO ANSWER") not underscores. Read caller.py.
- Find every place that checks status.get("status") or compares it against a set of terminal statuses.
- Confirm all comparisons use .upper().replace(" ", "_") normalization or equivalent.
- Flag as BLOCKING any comparison that would silently treat "NO ANSWER" as a non-terminal status.
Transcript extraction
- Find _extract_transcript_text() and parse_transcript_to_json() in caller.py.
- Verify the paths checked match the actual JSON shape provided. The transcript may be at result.transcript OR result.extracted.transcript — confirm both are checked.
- Flag as BLOCKING if the code assumes a path that doesn't exist in the provided real JSON.
R1 classification inputs
- Find classify_round1(). Verify it reads result.outcome.task_completed (bool) and result.outcome.completion_confidence.score.
- Confirm these paths exist in the provided real JSON sample.
R2 field extraction
- Find extract_round2_fields(). Verify it reads result.extracted and filters out metadata keys.
- Confirm the metadata keys being skipped (repair, calling, goal, region, language, to_phones) actually appear in the real JSON.
Call ID extraction
- Find every place run_id or call_id is extracted from the status output.
- Confirm the field names match the real JSON (run_id at top level, result.call_id nested).

Output format

For each check: quote the relevant code line, quote the relevant JSON path from the provided sample, and state CONFIRMED / MISMATCH / MISSING. Any MISMATCH or MISSING is BLOCKING.

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.

11d ago First seen · 38 lines · 61 tokens per session scan A add575124c56

Subscribe to this mod's changes

schema-assumption-verifier is an agent published in the GitHub repository CALLE-AI/awesome-phone-call-agents (109 stars, last pushed yesterday), licensed MIT. It adds 61 tokens to every session and 542 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 2026-10-09.

Debugging Testing

quality-fixer

Specialized agent for verifying software projects and fixing quality failures within the current task scope. Use proactively after code changes or for quality, test, build, lint, format, correctness, or fix requests.

shinpr/claude-code-workflows · 44 tokens

test-failure-analyst

Reads test output and source to explain why a test fails. Use after a failing test run.

Goldziher/ai-rulez · 26 tokens

mb-debugger

Systematic-debugging specialist for memory-bank. Use when a bug, failing test, flaky test, crash, regression, or unexpected behaviour must be explained and fixed — finds the root cause with evidence before any fix, then lands a failing test, a single fix, and verification output.

fockus/skill-memory-bank · 61 tokens

diagnostician

Specialized root cause debugger. Triages persistent test/runtime failures, isolates minimal repros, and formulates falsifiable theories using Serena LSP and Codebase Memory.

datit309/supergraph · 37 tokens

SWE

Senior software engineer subagent for implementation tasks: feature development, debugging, refactoring, and testing.

archubbuck/workspace-architect · 23 tokens

runtime-observer

Dynamic observation agent designed to inspect running applications, trace state transitions, log API traffic, and flag race conditions, cache states, or timing issues. Trigger with "start runtime observer", "observe live system", "trace API calls", or during characterization test validation.

richfrem/agent-plugins-skills · 56 tokens