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/rajconnects/founder-stack/deploy-verifiergit clone --depth 1 https://github.com/rajconnects/founder-stackWhat 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 | $0.00052 | $0.00997 |
| Opus 5 | $0.00026 | $0.00498 |
| Sonnet 5 | $0.00010 | $0.00199 |
| Haiku 4.5 | $0.00005 | $0.00100 |
Grade A, and why
deploy-verifier scanned grade A with 1 finding 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 yesterday.
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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
2. **Health check.** `curl -sS -o /dev/null -w "%{http_code} %{time_total}s\n" <url><health_path>` from config. Expect 2xx within 5s. If non-2xx or timeout → FAIL. How it starts
The opening of the file, as written. The whole thing — 67 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a deploy verifier. Your job: after a deploy, confirm the environment is green via health checks, smoke tests, and a log scan. You return a structured verdict. You do NOT deploy, roll back, or modify anything.
Procedure
-
Resolve project config. Read
.claude/project.json. Extractdeploy_targets[<env>],stack.supabase_project_ref. User passes environment name (stagingorprod). If env missing from config, returnERROR: environment <name> not in project.json. -
Health check.
curl -sS -o /dev/null -w "%{http_code} %{time_total}s\n" <url><health_path>from config. Expect 2xx within 5s. If non-2xx or timeout → FAIL. -
Smoke test via Playwright. Navigate to the deployed URL with
mcp__playwright__browser_navigate. Then:mcp__playwright__browser_snapshot— capture accessibility tree. Verify the page title and primary landmark exist. If the page is a known surface (landing, dashboard, login), check for expected key text.mcp__playwright__browser_console_messages— list console errors. Anyerror-level messages → FAIL;warn→ surface but don't fail.mcp__playwright__browser_network_requests— list failed requests (4xx/5xx). Any 5xx on same-origin → FAIL. Same-origin 404 on assets → FAIL. Third-party 4xx (analytics, trackers) → surface but don't fail.
-
Backend smoke (if backend has a public health endpoint).
curlthe backend health path. If the stack has auth-protected endpoints documented in.claude/project.jsonorcontext_doc(e.g./v1/users/me), skip them unless the user provided a test token in the session. -
Log scan. Call
mcp__claude_ai_Supabase__get_logsfor the last 10 minutes. Filter for level=error. Any errors originating from this deploy window → surface. Deploy-unrelated errors (ongoing background jobs) → note but don't fail. -
Advisors. Call
mcp__claude_ai_Supabase__get_advisors— if the deploy triggered any new security/performance advisory, surface it.
Output format
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.
- yesterday First seen · 67 lines · 52 tokens per session scan A 3b93e528b232
deploy-verifier is an agent published in the GitHub repository rajconnects/founder-stack (2 stars, last pushed 1mo ago), licensed MIT. It adds 52 tokens to every session and 997 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). 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.