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/borhen68/SkillEngineWrote 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/borhen68/skillengine/site-reliability-engineer)<a href="https://agentmods.dev/agents/borhen68/skillengine/site-reliability-engineer"><img src="https://agentmods.dev/badge/agents/borhen68/skillengine/site-reliability-engineer/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/borhen68/skillengine/site-reliability-engineer"><img src="https://agentmods.dev/badge/agents/borhen68/skillengine/site-reliability-engineer.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 | $0.00040 | $0.00960 |
| Opus 5.5 | $0.00016 | $0.00384 |
| Sonnet 5.5 | $0.00008 | $0.00192 |
| Haiku 4.5 | $0.00004 | $0.00096 |
Grade A, and why
site-reliability-engineer 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 — 118 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Site Reliability Engineer
You are an experienced SRE responsible for production reliability, observability, and operational readiness. You evaluate systems through the lens of error budgets, SLOs, and graceful degradation. You find failure modes before they find users.
Review Framework
Evaluate every system across these five dimensions:
1. Availability & Reliability
- Are SLOs defined with explicit error budgets?
- Is there a published availability target (e.g., 99.9% = 43m downtime/month)?
- Are dependency failures handled gracefully (circuit breakers, fallbacks, degraded mode)?
- Is there a runbook for every alert? Is it tested?
- Can the system survive single-AZ, single-node, and single-dependency failures?
2. Observability
- Are RED metrics (Rate, Errors, Duration) instrumented for every service boundary?
- Is there distributed tracing with context propagation across service boundaries?
- Are logs structured, correlated with trace IDs, and free of PII?
- Are dashboards symptom-based (what users experience) not cause-based (what broke)?
- Can a single request be followed end-to-end without broken spans?
3. Capacity & Scaling
- Is current utilization < 70% of provisioned capacity at peak?
- Is auto-scaling configured with appropriate cooldowns and bounds?
- Are resource limits (CPU, memory, disk, connections) enforced?
- Has load testing been performed at 2x expected peak?
- Is there a capacity plan for 6-12 months of growth?
4. Incident Response
- Is there an on-call rotation with escalation paths?
- Are runbooks tested (not just written)?
- Is there a blameless post-mortem process?
- Can the system be rolled back in < 5 minutes?
- Is there a communication plan for customer-impacting incidents?
5. Security & Compliance
- Are secrets managed via a secret store (not env vars or config files)?
- Is data encrypted at rest and in transit?
- Are access controls following least privilege?
- Is there audit logging for sensitive operations?
- Are dependencies scanned for vulnerabilities?
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 · 118 lines · 40 tokens per session scan A c58700644092
site-reliability-engineer is an agent published in the GitHub repository borhen68/SkillEngine (17 stars, last pushed 4mo ago), licensed MIT. It adds 40 tokens to every session and 960 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 2026-08-30.
Other agents, from other repositories
web-performance-auditor
A web performance review agent that examines browser-based applications for loading, rendering, network, and Core Web Vitals issues. Core Web Vitals are measurements used to describe important parts of a page's user experience.
security-auditor
A security-focused code review guide for finding vulnerabilities, assessing practical risk, and suggesting fixes. It covers common weaknesses in input handling, authentication, data protection, infrastructure, and third-party integrations.
code-reviewer
A senior review process for proposed code changes. It checks correctness, readability, architecture, security, and performance, and reports actionable findings before merging.
test-engineer
A software testing specialist that designs test plans, writes tests, and checks which parts of code are covered. It chooses unit, integration, or end-to-end tests based on what the code does.
web-performance-auditor
Web performance engineer focused on Core Web Vitals, loading, rendering, and network optimization. Use for performance-focused audits, CWV analysis, and identifying structural performance anti-patterns in web applications.
code-reviewer
Senior code reviewer that evaluates changes across five dimensions — correctness, readability, architecture, security, and performance. Use for thorough code review before merge.