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 SynthFlowAI/AnthropicPlugin --skill call-reviewgit clone --depth 1 https://github.com/SynthFlowAI/AnthropicPluginWrote 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/synthflowai/anthropicplugin/call-review)<a href="https://agentmods.dev/skills/synthflowai/anthropicplugin/call-review"><img src="https://agentmods.dev/badge/skills/synthflowai/anthropicplugin/call-review/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/synthflowai/anthropicplugin/call-review"><img src="https://agentmods.dev/badge/skills/synthflowai/anthropicplugin/call-review.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00096 | $0.01549 |
| Opus 5.5 | $0.00038 | $0.00620 |
| Sonnet 5.5 | $0.00019 | $0.00310 |
| Haiku 4.5 | $0.00010 | $0.00155 |
Grade A, and why
call-review 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 2mo 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 — 103 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Call Review
Purpose
Pull a batch of recent calls for one agent, inspect them, and surface the problems — so issues are caught in review instead of live on customer calls. Default batch size is the last 100 calls.
This playbook runs on the Synthflow MCP tools, whether they come from the plugin's bundled server or the official Synthflow connector. It does not require any external API or script.
Tools this uses
list_calls— get the batch of recent calls for the agent.get_call_details— pull transcript, outcome, duration, and metadata for a specific call.get_call_analytics— pull aggregate metrics across the batch.list_agents— identify the agent when the user hasn't named one.
Recordings can't be played over MCP. When call details include a recording URL, share it so the user can listen — don't assert audio-only findings from the transcript (see Rules).
Before starting
Confirm three things. If the user already gave them, don't re-ask — proceed.
- Which agent. If not named, use
list_agentsand ask the user to pick. Never guess. - Batch size and window. Default: last 100 calls, no date filter. Honor any override ("last 50", "yesterday", "this week").
- Custom failure list (optional). Ask whether this agent has known failure types to check specifically. If yes, take them as the agent-specific checklist (see "Agent-specific failures" below). If none, run generic checks only.
State any assumption you make rather than asking a second clarifying round.
Step 1 — Pull the batch
Use list_calls for the chosen agent, limited to the batch size (default 100). For each call, note: call ID, timestamp, duration, direction, and outcome/status if available.
Drop and count separately any calls that are not real conversations: no-connects, voicemail, and calls under ~5 seconds. Report how many were excluded and why — don't let them dilute the problem rates.
If list_calls returns fewer than requested, review what exists and say so.
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.
- 2mo ago First seen · 103 lines · 96 tokens per session scan A 223fa0a36e44
call-review is a skill published in the GitHub repository SynthFlowAI/AnthropicPlugin (0 stars, last pushed 5d ago), licensed MIT. It adds 96 tokens to every session and 1,549 once invoked, about $0.0004 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 2026-08-30.
call-review compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| call-reviewSynthFlowAI/AnthropicPlugin | Skill | 0 | 5d ago | MIT | A | 96 | Claude Code |
| imagegenopenai/codex | Skill | 135k | today | Apache-2.0 | A | 113 | Codex |
| playwright-climicrosoft/playwright | Skill | 100k | today | Apache-2.0 | A | 19 | Claude Code |
| browser-automationopenclaw/openclaw | Skill | 394k | today | MIT | A | 36 | Claude Code |
| local-ai-agentsmicrosoft/ai-agents-for-beginners | Skill | 80k | 8d ago | MIT | A | 200 | Claude Code, Codex |
| next-cache-components-adoptionvercel/next.js | Skill | 144k | today | MIT | A | 95 | Claude Code |
| chat-pet-sprite-creationmicrosoft/vscode | Skill | 195k | today | MIT | A | 53 | Claude Code, Codex |