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 genudo-ai/genudo_mcp --skill build-action-webhookgit clone --depth 1 https://github.com/genudo-ai/genudo_mcpWrote 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/genudo-ai/genudo_mcp/build-action-webhook)<a href="https://agentmods.dev/skills/genudo-ai/genudo_mcp/build-action-webhook"><img src="https://agentmods.dev/badge/skills/genudo-ai/genudo_mcp/build-action-webhook/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/genudo-ai/genudo_mcp/build-action-webhook"><img src="https://agentmods.dev/badge/skills/genudo-ai/genudo_mcp/build-action-webhook.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 | $0.00101 | $0.00510 |
| Opus 5 | $0.00051 | $0.00255 |
| Sonnet 5 | $0.00020 | $0.00102 |
| Haiku 4.5 | $0.00010 | $0.00051 |
Grade A, and why
build-action-webhook 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 10d 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.
What it actually says
Build Action Webhook
Create the HTTP action that lets an agent push data out or call an API.
Before creating
Ensure every value the payload/URL/headers need already exists as a variable
(manage-pipeline-variables). Never inline raw {{opportunity.*}} — reference variables by
their name.
Fields
method,url— the endpoint (e.g. a Zapier/Make/n8n catch hook).headers— auth and content-type; values may reference variables.payload— each entry is a field name + type + the variable that fills it.fixed_trigger—stage_started|on_any_message|on_user_message|custom.stage_id— attach to a stage; omit for a pipeline-wide action.instructions— WHEN the agent should call this action, plus any special handling.response_example— a sample response; set this when a later action chains on this one's output (via afrom_actionvariable).- Optional:
max_fires,retries,order.
Workflow
list_actionsfor the pipeline — avoid duplicating an existing action, and find theaction_idwhen the user means to change one.list_variables; create any missing (delegate tomanage-pipeline-variables).- Confirm the full action spec with the user.
create_action(orupdate_actionto change one). Report the action ID.
Cautions
fixed_triggeris set at creation; on update it can only change toon_user_messageorcustom. Pick the trigger correctly the first time.- The agent must not tell the customer the action succeeded unless the response confirms it.
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.
- 10d ago First seen · 41 lines · 101 tokens per session scan A 4254306ff099
build-action-webhook is a skill published in the GitHub repository genudo-ai/genudo_mcp (0 stars, last pushed 10d ago), licensed MIT. It adds 101 tokens to every session and 510 once invoked, about $0.0005 per session on Opus 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 2026-08-31.
Other skills, from other repositories
telegram-toolkit
Register these commands with @BotFather using /setcommands.
deepline-engine
Build, publish, and verify a Deepline Play as a durable state machine over Customer DB tables, including a small paid pilot. Invoke this skill explicitly when the user asks to build an engine.
aws-location-mcp
Place search, geocoding, and route optimization.
aws-appsync-mcp
Manage applications powered by AWS AppSync.
apollo-mcp-server-mcp
Enable graph-based API orchestration with AI.
com.googleapis.mapstools-mcp-mcp
Ground your AI applications with trusted geospatial data from Google Maps.