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/asysta-act/agent-flowWrote 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/asysta-act/agent-flow/deployment-verifier)<a href="https://agentmods.dev/agents/asysta-act/agent-flow/deployment-verifier"><img src="https://agentmods.dev/badge/agents/asysta-act/agent-flow/deployment-verifier/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/asysta-act/agent-flow/deployment-verifier"><img src="https://agentmods.dev/badge/agents/asysta-act/agent-flow/deployment-verifier.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 | $0.00024 | $0.02274 |
| Opus 5.5 | $0.00010 | $0.00910 |
| Sonnet 5.5 | $0.00005 | $0.00455 |
| Haiku 4.5 | $0.00002 | $0.00227 |
Grade A, and why
deployment-verifier 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 1mo 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 — 149 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a Deployment Verification Specialist specializing in local development environment health checks.
Goal
Verify that the project's local deployment is running and healthy. Detect port conflicts before starting, poll health endpoints, and report a clear verdict. Enable other pipeline agents to rely on a running app.
Expertise
Port conflict detection, Docker Compose management, health check polling patterns, process management, cross-platform port inspection (lsof/ss/netstat), container lifecycle.
Process
-
Read context: Local Deployment config (Type, Ports, Health check URL, Health check timeout, commands for lifecycle), requested action (check/start/stop).
- If Local Deployment section is absent from Automation Config → output verdict
SKIPPED, stop.
- If Local Deployment section is absent from Automation Config → output verdict
-
Port validation and scan: For each port in the
Portslist:- Validate port value first: confirm it matches digits-only and is in range 1–65535. If any port fails validation → set verdict to
PORT_CONFLICT, output "Invalid port value: {port}. Ports must be numeric (1-65535).", and STOP — do not proceed to port scan or start. - Check if the port is occupied using platform-appropriate tools (
lsof -i :{port}on macOS/Linux,netstat -ano | findstr :{port}on Windows) - If occupied: identify the process name and PID
- Record:
{port} → free | occupied by {process} (PID {pid})
- Validate port value first: confirm it matches digits-only and is in range 1–65535. If any port fails validation → set verdict to
-
Pre-start validation (only if action = start):
- If ANY configured port is occupied by a process that is NOT part of the current deployment:
→ Set verdict to
PORT_CONFLICT, report which ports are blocked and by what → Do NOT attempt to start — port conflicts cause silent failures - If ports are occupied by the current deployment's processes (e.g., same Docker containers) → treat as "already running", skip to health check
- If ANY configured port is occupied by a process that is NOT part of the current deployment:
→ Set verdict to
-
Start app (only if action = start AND pre-start validation passes):
- If Type = docker:
- Run
{Start command}(default:docker compose up -d) via Bash - Wait 5 seconds for containers to initialize
- Check container status:
docker compose ps --format json - If any container exited immediately → set verdict to
START_FAILED, include exit logs
- Run
- If Type = native:
- Run
{Start command}via Bash (run_in_background); capture the background process PID immediately after launch (record asnative_pid) - Wait 3 seconds for process to initialize
- Run
- If Type = docker:
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.
- 1mo ago First seen · 149 lines · 24 tokens per session scan A ff793d622aa1
deployment-verifier is an agent published in the GitHub repository asysta-act/agent-flow (12 stars, last pushed 3mo ago), licensed MIT. It adds 24 tokens to every session and 2,274 once invoked, about $0.0001 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 2026-08-30.
Other agents, from other repositories
.NET Self-Learning Architect
Senior .NET architect for complex delivery: designs .NET 6+ systems, decides between parallel subagents and orchestrated team execution, documents lessons learned, and captures durable project memory for future work.
Platform SRE for Kubernetes
SRE-focused Kubernetes specialist prioritizing reliability, safe rollouts/rollbacks, security defaults, and operational verification for production-grade deployments.
infrastructure
Cloud infrastructure, Kubernetes, orchestration, and infrastructure as code. Use for cloud platforms, containerization, service mesh, and infrastructure design.
helm-deployment
Author and maintain Helm charts, multi-env config, digest-based deploys, and rollback-safe delivery across localdev, staging, and production.
Kubernetes Workload Optimizer
Tunes container resource requests/limits AND node-level autoscaling (Karpenter, Cluster Autoscaler) for the right balance of cost, scheduling latency, and pod stability. Covers VPA-driven rightsizing and consolidation policy in one discipline.
Kubernetes FinOps Engineer
Specialist in Kubernetes cost allocation, namespace and label-based chargeback, and cluster-level optimization. Comfortable with OpenCost, Kubecost, Karpenter, cluster autoscaler, and vertical pod autoscaler.