What is diagnose-call?

A troubleshooting guide for finding why a specific Synthflow phone call failed or behaved incorrectly. Synthflow is a service for building phone agents; this guide examines the call record, transcript, timeline, actions, and webhook logs.

Use it to investigate missed transfers, dropped calls, silence, repetition, failed web requests, incorrect captured data, or outbound calls that did not connect.

It replaces guesswork with evidence from the call and clearly separates confirmed facts from likely causes or unknowns.

diagnose-call — Skill for Claude Code by SynthFlowAI/AnthropicPlugin

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 SynthFlowAI/AnthropicPlugin --skill diagnose-call

Clone the repo

git clone --depth 1 https://github.com/SynthFlowAI/AnthropicPlugin

Made for: Claude Code.

Or install synthflow, the plugin that ships this one along with the rest of its 7 skills, 2 MCP servers.

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/synthflowai/anthropicplugin/diagnose-call/github.svg)](https://agentmods.dev/skills/synthflowai/anthropicplugin/diagnose-call)

Your own site

<a href="https://agentmods.dev/skills/synthflowai/anthropicplugin/diagnose-call"><img src="https://agentmods.dev/badge/skills/synthflowai/anthropicplugin/diagnose-call/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/synthflowai/anthropicplugin/diagnose-call"><img src="https://agentmods.dev/badge/skills/synthflowai/anthropicplugin/diagnose-call.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 140 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 1,919 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	$0.00140	$0.01919
Opus 5.5	$0.00056	$0.00768
Sonnet 5.5	$0.00028	$0.00384
Haiku 4.5	$0.00014	$0.00192

Measured 5d ago against content hash f2c46930df54, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

diagnose-call 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 5d 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.

plugins/synthflow/skills/diagnose-call/SKILL.md · 108 lines

How it starts

The opening of the file, as written. The whole thing — 108 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Diagnose Call

Purpose

Find out what actually happened on a call, and why, from the evidence Synthflow exposes: the call record, transcript, timeline, executed actions, end-call reason, and webhook logs. Then say clearly what's confirmed, what's likely, and what can't be determined from these tools.

This playbook runs on the Synthflow MCP tools, whether they come from the plugin's bundled server or the official Synthflow connector. It is read-only.

Tools this uses

list_calls — find the call: by lead_phone_number (partial match), model_id, date range, call_status, end_call_reason, duration_min/duration_max.
get_call_details — transcript, timeline, executed actions, end-call reason, labels, recording URL.
get_call_details_batch — up to 25 calls at once, for comparing similar calls.
list_webhook_logs — action and webhook executions, filterable by call_id, model_id, status, webhook_type (custom_action, external_webhook, inbound_webhook), time_range (up to 7d).
get_webhook_log_detail — full request, response, status code, duration, and error for one execution.
get_agent, get_agent_actions, get_action — the configuration the call ran with.
list_agent_versions — whether the agent changed around the time of the call.
search_docs — how a feature is supposed to behave.

What these tools can't show

Be upfront about this — it decides what you can conclude:

Audio: recordings can't be played over MCP. Latency, interruptions, silence, and mispronunciation can't be confirmed from a transcript. Share the recording URL and ask the user to listen at the timestamp.
Telephony internals: there's no SIP signalling, carrier error codes, RTP or media traces, or trunk registration status. When the evidence points at the phone network, say so and recommend opening a support ticket with the call id.
Flow Designer internals: there's no per-node execution trace. You can see what the agent said and which actions ran, not which node it was in.
Webhook logs only go back 7 days through list_webhook_logs.

Read the full file on GitHub · 108 lines

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.

5d ago First seen · 108 lines · 140 tokens per session scan A f2c46930df54

Subscribe to this mod's changes

diagnose-call is a skill published in the GitHub repository SynthFlowAI/AnthropicPlugin (0 stars, last pushed 5d ago), licensed MIT. It adds 140 tokens to every session and 1,919 once invoked, about $0.0006 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 2026-11-09.

Debugging

diagnose-call next to 6 skills from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
diagnose-callSynthFlowAI/AnthropicPlugin	Skill	0	5d ago	MIT	A	140	Claude Code
systematic-debuggingopen-metadata/OpenMetadata	Skill	16k	today	Apache-2.0	A	37	Claude Code
log-error-digestzebbern/claude-code-guide	Skill	4.7k	yesterday	MIT	A	71	Claude Code, Codex
cwv-optimizeradobe/skills	Skill	328	today	Apache-2.0	A	112	Claude Code
ci-fixersipyourdrink-ltd/bernstein	Skill	1.2k	today	Apache-2.0	A	15	Claude Code, Codex
self-healhristo2612/jinn	Skill	329	yesterday	MIT	A	19	Claude Code, Codex
debug-optimized-buildsmohitmishra786/low-level-dev-skills	Skill	288	yesterday	MIT	A	104	Claude Code, Codex