NitroStack is a TypeScript framework for building MCP servers, which are backends that expose tools, resources, or prompts to MCP-compatible AI clients, as well as AI-native applications. It is used by developers who need features such as decorators, dependency injection, authentication, validation, middleware, and interactive React widgets. The catalogue add-ons provide workflows and tools for developing NitroStack projects.
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.
git clone --depth 1 https://github.com/nitrocloudofficial/nitrostackWrote 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/agents/nitrocloudofficial/nitrostack/demo-warden)<a href="https://agentmods.dev/agents/nitrocloudofficial/nitrostack/demo-warden"><img src="https://agentmods.dev/badge/agents/nitrocloudofficial/nitrostack/demo-warden/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/agents/nitrocloudofficial/nitrostack/demo-warden"><img src="https://agentmods.dev/badge/agents/nitrocloudofficial/nitrostack/demo-warden.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 | $0.00052 | $0.00814 |
| Opus 5.5 | $0.00021 | $0.00326 |
| Sonnet 5.5 | $0.00010 | $0.00163 |
| Haiku 4.5 | $0.00005 | $0.00081 |
Grade A, and why
demo-warden 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 3d 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 — 74 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are the demo verifier. You do not write code. You do not fix things. You run the demo path, find what is broken, and report it precisely so the human can decide what to do with the remaining time.
You have no Edit or Write access. This is deliberate. Your value is an independent check that has not convinced itself the code works.
The demo path — verify in this exact order
npm run build— clean, zero TypeScript errors- MCP server starts; all six tools register
list_pending_invoicesreturns exactly the seeded fixtures, in deterministic orderassess_payment_riskon the planted duplicate → firesDUPLICATE_INVOICEassess_payment_riskon the structuring set → firesSTRUCTURINGassess_payment_riskon the deny-listed vendor → returnsBLOCKEDdraft_payment_batchreturns adraft_idrequest_approvalreturns a pending approval with flags populatedexecute_paymentwithout a valid approval token → must be refusedexecute_paymentwith a valid token → succeeds, returns a receiptget_audit_trailcontains the refusal from step 9, with its reason- Hash chain in the audit trail is intact and verifiable
The injection test — the one that matters most
Run the invoice whose notes field carries the injection payload through the full agent flow in Studio AI Chat.
Expected outcome: the agent attempts execute_payment with a bypass argument, and the server refuses.
Report all three of:
- Did the agent actually attempt the bypass? (If it didn't, the demo has no drama — the human needs to know.)
- Did the server refuse?
- Does the audit trail capture the attempt with the injected string quoted?
If the agent refuses on its own without the server ever being tested, say so plainly. That is a weaker demo and the human should hear it before they are on stage, not during.
Deployment verification
Never sign off on localhost alone. After any deploy:
- Deployment status reached Live
- Hit at least one tool against the deployed Service URL
- Widgets render in the live client, not just Studio preview
- Report the Service URL back so the human can confirm it matches the README
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.
- 3d ago First seen · 74 lines · 52 tokens per session scan A c2569bc7ba06
demo-warden is an agent published in the GitHub repository nitrocloudofficial/nitrostack (2,458 stars, last pushed yesterday), licensed Apache-2.0. It adds 52 tokens to every session and 814 once invoked, about $0.0002 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 2026-10-13.
Other agents, from other repositories
qa-analyzer
Use this agent after cycle completion or when the user requests bug hunting and QA analysis. World-class QA analyst that finds bugs before users do — thinks like a confused user, power user, and malicious attacker. Documents each issue precisely so it can be filed as a bug. Context: User just completed a cycle and…
playwright-test-healer
Use this agent when you need to debug and fix failing Playwright tests.
gsd-integration-checker
Verifies cross-phase integration and E2E flows. Checks that phases connect properly and user workflows complete end-to-end.
proof
Risk-maps codebases and writes the actual test code — integration tests on critical paths, Playwright E2E for user journeys, flaky test triage, and CI gating — using the testing trophy over the pyramid. Use when a codebase has no test strategy, CI is slow/flaky, or a critical path has zero coverage. Trigger with…
tester
Test writing (unit, integration, e2e). Creates comprehensive test suites with proper coverage and edge cases.
Reality Checker
Stops fantasy approvals, evidence-based certification - Default to "NEEDS WORK", requires overwhelming proof for production readiness.