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 skills add cosmicstack-labs/mercury-agent-skills --skill sre-practicesgit clone --depth 1 https://github.com/cosmicstack-labs/mercury-agent-skillsWrote 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/cosmicstack-labs/mercury-agent-skills/sre-practices)<a href="https://agentmods.dev/skills/cosmicstack-labs/mercury-agent-skills/sre-practices"><img src="https://agentmods.dev/badge/skills/cosmicstack-labs/mercury-agent-skills/sre-practices/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/skills/cosmicstack-labs/mercury-agent-skills/sre-practices"><img src="https://agentmods.dev/badge/skills/cosmicstack-labs/mercury-agent-skills/sre-practices.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00028 | $0.00544 |
| Opus 5 | $0.00014 | $0.00272 |
| Sonnet 5 | $0.00006 | $0.00109 |
| Haiku 4.5 | $0.00003 | $0.00054 |
Grade A, and why
sre-practices 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 8d 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.
What it actually says
SRE Practices
Apply Site Reliability Engineering principles.
Service Level Concepts
| Term | Definition | Example |
|---|---|---|
| SLI | Measured metric | Request latency p95 < 500ms |
| SLO | Target threshold for SLI | 99.9% of requests < 500ms |
| SLA | Contractual commitment (usually looser than SLO) | 99.5% uptime |
Choosing SLOs
- Pick metrics users actually care about
- Start with availability + latency + durability
- Tighten SLOs over time as reliability improves
- Don't over-constrain (cost/effort vs. benefit)
Error Budgets
Error Budget = 100% - SLO
Example: 99.9% SLO → 0.1% error budget = ~8.7 hours/month
How Error Budgets Work
- If error budget remaining → can deploy new features
- If error budget exhausted → freeze deployments, focus on reliability
- Error budget burn rate alerts trigger incident response
- Balance innovation velocity with system stability
Incident Response
Severity Levels
| Level | Definition | Response |
|---|---|---|
| SEV1 | System down, affecting many users | Immediate, all hands |
| SEV2 | Degraded but operational | 30min response |
| SEV3 | Minor issue, workaround exists | Next business day |
| SEV4 | Cosmetic, non-critical | Next sprint |
Incident Command System
- Incident Commander: Coordinates response
- Communications Lead: Status updates, stakeholder comms
- Operations Lead: Technical investigation
- Scribe: Timeline and action log
Postmortem Culture
- Blameless: systems failed, not people
- Focus on: detection, response, prevention
- Action items with owners and due dates
- Share postmortems org-wide
- Track action items to completion
Reliability Patterns
- Circuit breaker: stop cascading failures
- Bulkhead: isolate failure domains
- Retry with exponential backoff + jitter
- Rate limiting: protect against traffic spikes
- Graceful degradation: degrade features, not the whole system
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.
- 8d ago First seen · 71 lines · 28 tokens per session scan A 76351f935d78
sre-practices is a skill published in the GitHub repository cosmicstack-labs/mercury-agent-skills (470 stars, last pushed 17d ago), licensed MIT. It adds 28 tokens to every session and 544 once invoked, about $0.0001 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 2026-09-03.
Other skills, from other repositories
modern-saas-builder
Founder-minded senior product engineer and SaaS architect skill. Use when building, planning, architecting, validating, designing, testing, securing, deploying, or monetizing modern SaaS products, micro-SaaS, web apps, AI agents, Web3/Base applications, agent commerce, or Telegram bots/Mini Apps. Always active when…
claude-md-improver
Audit and improve CLAUDE.md files in repositories. Use when user asks to check, audit, update, improve, or fix CLAUDE.md files. Scans for all CLAUDE.md files, evaluates quality against templates, outputs quality report, then makes targeted updates. Also use when the user mentions "CLAUDE.md maintenance" or "project…
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…
agent-platform-model-registry
Agent Platform Model Registry Management. Use when you need to upload, list, describe, update, or delete machine learning models (and their versions) in the Agent Platform Model Registry. Don't use for model training, model deployment to endpoints, or managing non-Agent Platform models.
chenhao-limit-up
A framework for judging Chinese A-share stocks that have reached the daily price-rise limit, using market mood, sector leadership, and trading momentum.