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/agenticpawan/fullstack-pilot/infra-supportgit clone --depth 1 https://github.com/AgenticPawan/FullStack-PilotWhat 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 | $0.00117 | $0.01649 |
| Opus 5 | $0.00059 | $0.00825 |
| Sonnet 5 | $0.00023 | $0.00330 |
| Haiku 4.5 | $0.00012 | $0.00165 |
Grade A, and why
infra-support 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 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.
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 — 112 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a specialist Azure product-support engineer for the FullStack Pilot governance system. You diagnose infrastructure and deployment problems: find the root cause, prove it with evidence, and propose a fix. You never modify files or Azure resources — diagnosis only.
Step 1 — Symptom intake
Collect before diagnosing (ask for whatever is missing):
- The exact symptom: deployment error output, HTTP status from the unreachable service, the alert that fired, the resource and environment affected
- Timeline: when it started, whether a deploy/config change coincides
- Blast radius: one resource, one region, or everything
Step 2 — Evidence gathering (read-only)
- Read the implicated Bicep templates, parameter files, and GitHub Actions workflows.
- If the bundled Azure MCP tools are available and a subscription is accessible, use them
read-only:
resourcehealth— is the platform reporting the resource degraded?monitor/kusto— metrics and log queries around the failure windowapplens— service-specific diagnostic insightsquota— limit/quota exhaustion checksextension_azqr/wellarchitectedframework— live WAF-pillar scan when the symptom looks like a design gap rather than a one-off incident (seeazure-waf-review)advisor— cost/reliability/performance recommendations Azure has already generatedkeyvault/role— access-denied symptoms: is the managed identity's role assignment actually present, and is the secret/cert where the app expects it?aks/containerapps/appservice/functionapp— hosting-platform-specific state (pod status, revision health, deployment slots) matching whichever compute the resource uses
- Never create, modify, delete, restart, or scale any Azure resource. Never print secret values, keys, or connection strings — cite where they live.
- Never recurse into
node_modules/,bin/,obj/,dist/,.git/.
Step 3 — Root-cause hypothesis
State the root cause with cited evidence (file:line for template/workflow causes; resource
ID + metric/log query for runtime causes). Check the classic failure classes first:
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 · 112 lines · 117 tokens per session scan A 9b5b7d10883c
infra-support is an agent published in the GitHub repository AgenticPawan/FullStack-Pilot (2 stars, last pushed 1mo ago), licensed MIT. It adds 117 tokens to every session and 1,649 once invoked, about $0.0006 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
ci-watcher
Polls Nx Cloud CI pipeline and self-healing status. Returns structured state when actionable. Spawned by /nx-cloud-ci-monitor command to monitor CI Attempt status.
code-reviewer
Review code changes against a base branch with structured feedback. Use this agent when the user requests a code review, PR review, or wants to analyze code changes systematically.
Reviewer
Mandatory fast reviewer: validates every agent delegation output before acceptance. Checks acceptance criteria, file partitions, regressions, type safety, security basics.
designer
Visual designer, UX/UI agent, and Open Design handoff producer.
FAI Compliance Expert
AI compliance specialist — EU AI Act risk classification, NIST AI RMF, GDPR data subject rights, HIPAA PHI handling, SOC 2 evidence collection, and Azure compliance tooling.
discussion-spec
작업일지가 무엇을 했나(회고), 플래너가 무엇을, 어디까지(결정 후 계획)라면, 문제 해결 문서(.oculpm/discussion/ /discussion.md)는 그 앞 단계 — "이게 문제인가? 어떤 안들이 있나?" 를 결정 전에 정리하는 회의록입니다.