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 build-actiongit 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/build-action)<a href="https://agentmods.dev/skills/synthflowai/anthropicplugin/build-action"><img src="https://agentmods.dev/badge/skills/synthflowai/anthropicplugin/build-action/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/build-action"><img src="https://agentmods.dev/badge/skills/synthflowai/anthropicplugin/build-action.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 | $0.00159 | $0.02581 |
| Opus 5.5 | $0.00064 | $0.01032 |
| Sonnet 5.5 | $0.00032 | $0.00516 |
| Haiku 4.5 | $0.00016 | $0.00258 |
Grade A, and why
build-action 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.
How it starts
The opening of the file, as written. The whole thing — 170 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Build Action
Purpose
Actions are what an agent can do beyond talking: call an API, extract data after the call, transfer, send an SMS, book, navigate an IVR, score the call, or email a summary. This skill builds them in the order that works:
plan → check prerequisites → create → initialize/test → attach → verify on a call
The MCP action tools have their own field names, which differ from the REST API and from the dashboard labels. Most failed action calls come from using the wrong field names, so follow the shapes below exactly, and read an existing action with get_action before changing it.
This playbook runs on the Synthflow MCP tools, whether they come from the plugin's bundled server or the official Synthflow connector.
Tools this uses
list_actions,get_action— find existing actions; read exact field names before any update.list_integrations— required before booking or any provider-backed action.test_api_call— call the user's endpoint directly to see the real response before building on it.create_action—name,type,action_data.update_action—action_slug,update_data,confirmed.initialize_action— sends a test request for a custom action and activates it. Required after creating or changing one.attach_action_to_agent/detach_action_from_agent—model_id,action_slug,attachment_type(before,during,after),confirmed.get_agent_actions— what's attached to an agent now.list_webhook_logs,get_webhook_log_detail— request and response of real action executions, for debugging.
Some tool descriptions mention confirm_action and show_form. Those UI tools don't exist over MCP:
- Confirmation: state the change in the chat (action, agent, timing, what changes) and get the user's explicit yes before calling a tool with
confirmed: true. - Secrets: never ask the user to paste an API key or token into the chat, and never put one in
action_data. Create the action without the credential and have the user add it in the action's settings in the Synthflow dashboard.
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 · 170 lines · 159 tokens per session scan A 282e0fbde5b7
build-action is a skill published in the GitHub repository SynthFlowAI/AnthropicPlugin (0 stars, last pushed 5d ago), licensed MIT. It adds 159 tokens to every session and 2,581 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.
build-action compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| build-actionSynthFlowAI/AnthropicPlugin | Skill | 0 | 5d ago | MIT | A | 159 | Claude Code |
| mcp-tool-developersickn33/agentic-awesome-skills | Skill | 50k | today | MIT | A | 38 | Claude Code |
| mem0-oss-to-platformmem0ai/mem0 | Skill | 69k | 8d ago | Apache-2.0 | A | 217 | Claude Code, Codex |
| azure-mgmt-botservice-dotnetmicrosoft/skills | Skill | 3.2k | yesterday | MIT | A | 78 | Claude Code |
| fastapi-router-pymicrosoft/skills | Skill | 3.2k | yesterday | MIT | A | 46 | Claude Code |
| dev-runtimelangwatch/langwatch | Skill | 5.0k | today | Apache-2.0 | A | 172 | Claude Code |
| api-designericrisco/rsc-harness | Skill | 608 | yesterday | MIT | A | 105 | Claude Code, Codex |