infrastructure-effect-classification
/infrastructure-effect-classification
Use when writing or reviewing rules that let an operations agent run infrastructure commands on AWS, Fortinet, Kubernetes, or remote hosts, by classifying verbs by the effect they leave rather than how they sound.
- Author
- otixe ↗
- Repository
- agent-skills ↗
- Licence
- MIT
- Last repository change
- 26.10.2026
Assessment and security
- Files in this package
- 1
- Scripts
- 0
- HTML comments
- 0
- URLs in SKILL.md
- 0
No signals detected. Repository changed on 26.10.2026, without references to retired models or APIs.
MIT, open: use and modify while retaining author attribution.
What it does and when to use it
Use when writing or reviewing rules that let an operations agent run infrastructure commands on AWS, Fortinet, Kubernetes, or remote hosts, by classifying verbs by the effect they leave rather than how they sound.
Original author description
Use when writing or reviewing rules that let an operations agent run infrastructure commands on AWS, Fortinet, Kubernetes, or remote hosts, by classifying verbs by the effect they leave rather than how they sound.
How it works
- Authorization and test boundary
- Method
- Limits
SKILL.md preview
--- name: infrastructure-effect-classification description: "Use when writing or reviewing rules that let an operations agent run infrastructure commands on AWS, Fortinet, Kubernetes, or remote hosts, by classifying verbs by the effect they leave rather than how they sound." --- # Infrastructure Command Effect Classification ## Authorization and test boundary These instructions grant no permission. Confirm the exact resources, allowed effects and data handling before acting. Use synthetic canaries and disposable fixtures for deliberate failures; never use real credentials as test inputs. Keep secrets and fragments out of model context, arguments, logs and plaintext artifacts. Imports, constructors, help and dry-run commands may have effects. Establish external-effect isolation before executing untrusted code; application stubs are not a sandbox. Record untested scope and obtain separate authorization for production changes or destructive actions. ## Method 1. Classify each proposed operation by its actual effects, environment, reversibility and blast radius, not by verb spelling. Sync-with-delete, ingress authorization and infrastructure-state removal all mutate state. 2. Separate observation, reversible local work, external or production mutation, and destructive or irreversible work. Mixed commands inherit the strongest effect class they contain. 3. Identify the authorized identity and capability boundary for every resource. Read-only labels or prose are not technical enforcement; verify permissions and command startup behavior. 4. Detect contradictory predicates and impossible requirements. Write narrow, explicit exceptions such as an authorized identity check rather than an open-ended bypass. 5. Record scope and approval before effects. Use proportionate evidence for small reversible work and full controls where sensitive data, production, migrations or irreversibility demand them. 6. Challenge the rules with counterexamples and known bypass cases. Independent review tests the stated boundary; it does not grant new permission. ## Limits A short prompt can summarize a policy but cannot implement RBAC, network isolation or irreversible-action approval. Escalate unknown effects instead of inventing authority.
Versions
The database has no other skills named infrastructure-effect-classification.
Database snapshot: 13.11.2026 · package version d362e46a8710 (SHA-256 digest of the entire package)
Downloads in the last 30 days: 0 · ranking
Report a problem with this skill: harmful content, incorrect descriptions or an author’s removal request.
Similar skills
- 100research-to-deploy
Researches infrastructure best practices and generates deployment-ready configurations, Terraform modules, Dockerfiles, and CI/CD pipelines. Use when the user needs to deploy services, set up infrastructure, or create cloud configurations based on current best practices. Trigger… - 100create-infrastructure
Generate Harness Infrastructure Definition YAML for deployment targets and create via MCP. Use when user says "create infrastructure", "infrastructure definition", "k8s cluster config", "deployment target", or wants to configure where workloads run. - 100arn-infra-assess
This skill should be used when the user says "assess infrastructure", "infra assess", "arn infra assess", "infrastructure assessment", "analyze infrastructure needs", "what infrastructure do I need", "infrastructure audit", "app infrastructure assessment", "full infra… - 100rr
Sync code and run commands on remote machines. Use when running tests, builds, or commands remotely, syncing files to hosts, setting up remote development, or troubleshooting rr configuration.