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 skills/tqnonline/agent-forge/sre-architectnpx skills add tqnonline/agent-forge --skill sre-architectgit clone --depth 1 https://github.com/tqnonline/agent-forgeWrote 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/skills/tqnonline/agent-forge/sre-architect)<a href="https://agentmods.dev/skills/tqnonline/agent-forge/sre-architect"><img src="https://agentmods.dev/badge/skills/tqnonline/agent-forge/sre-architect.svg" alt="Measured on agentmods" 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 | $0.00243 | $0.05654 |
| Opus 5 | $0.00121 | $0.02827 |
| Sonnet 5 | $0.00049 | $0.01131 |
| Haiku 4.5 | $0.00024 | $0.00565 |
Grade A, and why
sre-architect 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 6d 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 — 379 lines — stays where its author put it; the contents beside it link to each section on GitHub.
SRE Architecture Specialist
Version: 1.0 | Role: Site Reliability Engineering Architect | Tier: 2D Long-tail (trigger-based: SLA/SLO stated)
Design and govern reliability engineering practice for Azure workloads: SLI/SLO decomposition, error budget governance, multi-window burn-rate alerting, chaos engineering via Azure Chaos Studio, blameless postmortem culture, on-call rotation design, runbook authoring, incident command, and toil reduction. Use Microsoft Learn MCP (microsoft_docs_search, microsoft_docs_fetch) to verify current Azure Chaos Studio fault library, target types, and regional availability before finalizing experiment designs; capabilities expand each quarter. Read shared standards: standards/references/coding-stack/preferred-stack.md, standards/references/patterns/cloud-design-patterns.md, standards/references/quality/review-checklist.md.
Telemetry foundation (App Insights, Log Analytics, KQL, OpenTelemetry, SLO signal wiring) is owned by /observability-architect. This skill consumes that foundation and builds governance, alerting policy, and operational practice on top.
Design Principles
- SLI, SLO, SLA: customer-facing SLAs are derived from SLOs, not invented separately. Define SLIs first (what to measure), set SLO targets from reliability data, then commit SLAs to customers at a cushion below the SLO. Reverse engineering SLOs from a committed SLA produces targets with no engineering basis.
- Error budgets are real budgets: when burned, ship fixes, not features. An exhausted error budget is a full stop on feature work. Teams that treat error budgets as advisory rather than binding produce systems with drift between stated and actual reliability.
- Burn-rate alerting over threshold alerting. Multi-window multi-burn-rate (Google SRE Workbook). Raw metric thresholds generate alert fatigue. Two alert windows per SLO (fast-burn for sudden regressions, slow-burn for sustained degradation) with defined burn multipliers produce actionable pages.
- Postmortems blameless. Action items have owners and due dates. Blame produces silence in future incidents. Every postmortem produces a set of time-bound action items assigned to named owners, tracked in the team's issue tracker.
- Chaos engineering in production (with safety controls) over only in staging. Staging environments diverge from production in load, data shape, and dependency topology. Run experiments in production during low-traffic windows with automatic abort conditions and Azure Monitor stop signals.
- Runbooks are living documents: if not tested in the last 90 days, assume stale. Runbooks rotted by 90 days of non-use fail at the worst moment. Schedule quarterly fire-drills; flag any runbook that has not been exercised as "unverified".
- Toil below 50 percent of SRE time: if higher, automate or push back. Toil tracked, measured, and reported each sprint. When toil exceeds half the team's capacity, SRE work is capped to force automation investment.
What ships with it
7 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 6d ago First seen · 379 lines · 243 tokens per session scan A 607d28403f8d
sre-architect is a skill published in the GitHub repository tqnonline/agent-forge (2 stars, last pushed 3mo ago), licensed BSD-3-Clause. It adds 243 tokens to every session and 5,654 once invoked, about $0.0012 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 skills, from other repositories
gke-compute-classes
Configures, optimizes, and troubleshoots GKE ComputeClasses. Use when configuring Spot VMs with on-demand fallback, targeting specific accelerators (GPUs/TPUs) or machine families, restricting ComputeClass access, or debugging pending pods related to node pool auto-creation. Do not use for cluster-level Node Auto…
gke-reliability
Improves GKE workload reliability, using PDBs, health probes, and topology spread constraints. Use when configuring GKE workload reliability, setting up PDBs, or configuring GKE health probes (liveness, readiness, startup). Don't use for disaster recovery setup or full cluster backups (use gke-backup-dr instead).
gke-workload-security
Audits, configures, and hardens workload-level security controls for Google Kubernetes Engine (GKE) applications and namespaces. Covers running cluster security audits (auditcluster.sh), configuring Workload Identity Federation (impersonation, KSA/GSA binding, and pod setup), enforcing Network Policies (default-deny…
nemo-automodel-launcher-config
Configure NeMo AutoModel job launches for interactive runs, Slurm clusters, and SkyPilot cloud execution.
azure-mgmt-botservice-dotnet
Azure Resource Manager SDK for Bot Service in .NET. Management plane operations for creating and managing Azure Bot resources, channels (Teams, DirectLine, Slack), and connection settings. Triggers: "Bot Service", "BotResource", "Azure Bot", "DirectLine channel", "Teams channel", "bot management .NET", "create bot".
cloud-architect
Designs cloud architectures, creates migration plans, generates cost optimization recommendations, and produces disaster recovery strategies across AWS, Azure, and GCP. Use when designing cloud architectures, planning migrations, or optimizing multi-cloud deployments. Invoke for Well-Architected Framework, cost…