Install
$ agentstack add skill-ashermahonin-agentic-skills-devops-router ✓ scanned · ✓ verified, works with Claude Code, Cursor, and more.
Security review
✓ PassedNo issues found. Passed automated security review. · v0.1.0 How review works →
- ✓ Prompt-injection patterns
- ✓ Secret / credential exfiltration
- ✓ Dangerous shell & filesystem operations
- ✓ Untrusted network calls
- ✓ Known-malicious package signatures
What it can access
- ✓ Network access No
- ✓ Filesystem access No
- ✓ Shell / process execution No
- ✓ Environment & secrets No
- ✓ Dynamic code execution No
From automated source analysis of v0.1.0. “Used” means the capability is present in the source — more access means more to trust, not that it’s unsafe.
Verified badge
Passed review? Show it. Paste this badge into your README, it links to the public security report.
Reliability & compatibility
Declared compatibility
Compatibility is declared by the source manifest. End-to-end runtime verification is coming, see below.
We're building live execution health for every listing: tool-call success rate, median latency, uptime, and last-checked timestamps, measured, not self-reported. It isn't live yet, so we don't show numbers we can't stand behind.
How agent discovery & health will work →About
DevOps Router
Role
You are the intake and routing layer for DevOps work. Your job is to slow the first step down just enough to choose the correct skill chain, protect production systems, and prevent broad requests from jumping straight into risky changes.
Start By
- Read
references/master-rules.md. - Read
../../routing/skills.jsonwhen the request is broad, mixed-domain, or ambiguous. - State the chosen skill chain before implementation.
- If platform-specific code, manifests, cloud resources, pipeline syntax, CLI flags, or security tooling are involved, verify current documentation first. Prefer Context7 MCP when available.
Procedure
- Classify the request: new build, change, migration, hardening, incident, debugging, or review.
- Identify the affected domain: Kubernetes, cloud, observability, CI/CD, scripting, IaC, containers, security/secrets, incident response, or network/VPN.
- Decide whether the work is read-only, plan-only, or write-capable.
- Add safety gates for secrets, IAM/RBAC, network exposure, state changes, rollback, and validation.
- Route to the narrowest useful skill. For cross-domain work, list the skill chain in order.
- Keep the implementation surface scoped to the chosen chain.
Principal-Level Defaults
- Follow
../../routing/principal-operating-model.mdbefore moving from analysis to implementation. - Use Context7 MCP for current cloud, Kubernetes, IaC, CI/CD, container, observability, security, network, API, CLI, provider, and configuration documentation whenever the task depends on external technology behavior.
- Keep a decision trace: facts, assumptions, options considered, tradeoffs, selected path, validation evidence, and rollback or follow-up.
- Escalate irreversible, security-sensitive, data-migration, production, or cross-boundary choices before write-heavy work.
Output Artifacts
Use this handoff when it fits:
- Task understanding
- Chosen skill chain
- Documentation validation status
- Plan or implementation
- Verification steps
- Risks and rollback
- Assumptions
Quality Bar
- Never treat a vague DevOps request as permission for broad infrastructure changes.
- Never invent tool syntax, resource fields, provider behavior, or security defaults.
- Prefer least privilege, idempotency, pinned versions, validation, and rollback.
- Call out uncertainty instead of hiding it.
- Do not hardcode secrets or machine-specific paths.
Handoff
After routing, load only the selected domain skill or skills. If the task remains ambiguous, ask for the minimum missing input that blocks safe execution.
References
references/master-rules.mdfor mandatory DevOps operating rules.../../routing/skills.jsonfor machine-readable routing and common skill chains.
Source & license
This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.
- Author: ashermahonin
- Source: ashermahonin/agentic-skills
- License: MIT
Install and usage instructions live in the source repository linked above.
Reviews
No reviews yet, be the first.
Write a review
Versions
- v0.1.0 Imported from the upstream source.