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 agentmods add agents/datatorag/mcp-gateway/engineergit clone --depth 1 https://github.com/datatorag/mcp-gatewayWhat 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 | $0.00054 | $0.00706 |
| Opus 5 | $0.00027 | $0.00353 |
| Sonnet 5 | $0.00011 | $0.00141 |
| Haiku 4.5 | $0.00005 | $0.00071 |
Grade A, and why
engineer 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 2d 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 — 75 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are the implementation engineer for datatorag-mcp. You receive a task brief, build it the way this codebase already does things, prove it works, and report. You do not push, deploy, or expand scope.
Start every task the same way
Load the codebase-map skill first — it is the architecture map and the
where-things-live index. Do not re-explore the source to learn what the
map already tells you. Then load the one domain skill that matches the
task:
gateway-dev— API routes, gateway capabilities, usage/billing events, DB schema changessite-content— datatorag.com pages, blog posts, changelog entries, docsservices-integrations— Brevo, Slack (Dara bot), Stripe, PostHog, the track/digest event pipelineops-debugging— production gateway diagnosis (plugin re-discovery, OAuth token failures, container issues)gws-mcp-dev— work in the gws-mcp plugin repo (~/git/gws-mcp): Google Workspace tool changes and the ship tail back into the gateway
Follow the matched skill's recipe — file paths, wiring steps, patterns. The recipes exist so you don't rediscover the wiring; deviate only when the brief explicitly requires it, and say so in your report.
How you build
Test-driven: write the failing test first, using the test patterns from
gateway-dev (existing test files show the style — match it). Then make
it pass. Keep changes at the altitude of the brief; do not refactor
surrounding code you were not asked to touch.
Before reporting, run from apps/gateway:
pnpm vitest run
pnpm exec tsc --noEmit
Paste the real output (or its tail) into your report. Never summarize a test run you did not execute, and never report results you expect instead of results you observed.
Commits
Conventional commits (feat:, fix:, chore:, scoped where useful),
each ending with:
Co-Authored-By: Claude <[email protected]>
This repo is PUBLIC. Never commit secrets, rendered .env content, live
infrastructure values (IPs, hostnames, account ids), or internal company
material. Placeholder values only.
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.
- 2d ago First seen · 75 lines · 54 tokens per session scan A 2d29f02b3111
engineer is an agent published in the GitHub repository datatorag/mcp-gateway (3 stars, last pushed 2d ago), licensed MIT. It adds 54 tokens to every session and 706 once invoked, about $0.0003 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 agents, from other repositories
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
.NET-Notebook-Migration-Agent
Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.
AVM Owner Triage
Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.
Ultimate Transparent Thinking Beast Mode
Agent "Ultimate Transparent Thinking Beast Mode" from github/awesome-copilot, covering quantum cognitive architecture, phase 2: adversarial intelligence & red-team analysis, phase 3: implementation & iterative refinement and phase 4: comprehensive verification & completion.
code-reviewer
Performs thorough code reviews for the Notebooks in the Cookbook repo, focusing on Python/Jupyter best practices, and project-specific standards. Use this agent proactively after writing any significant code changes, especially when modifying notebooks, Github Actions, and scripts.