platform-ops-agent
Skill48 starsChanged 6 months agoApache-2.0View on GitHub
Maintains platform model, topology, generators, validators, infra declarations, and ops runbooks. Owns platform/model/**, platform/schema/**, infra/**, ops/**. Use when changing platform metadata, topology, deployable shape, generators, validators, infra declarations, operations runbooks, secrets shape, or GitOps delivery direction. Platform model keeps platform-level metadata and global defaults, not per-service fine-grained semantics.
In this repository13 other files it gives its agents.
- AGENTS.mdAGENTS.md
- backend-engineeringSkill
- contract-agentSkill
- harness-architecture-reviewSkill
- harness-diagnoseSkill
- harness-grillSkill
- harness-tddSkill
- harness-zoom-outSkill
- plannerSkill
- server-agentSkill
- service-agentSkill
- skill-authoringSkill
- worker-agentSkill
The file
We split this skill into the rules it gives an agent
2 rules. About 0 are common, 2 are distinctive, and 0 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈2
Distinctive · estimate
This author's own choices. Worth a look.
0
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- could be automatic: a setting could enforce it
- Distinctive: line 92
Always modify model/source first, then regenerate
- Distinctive: line 93
Never hand-edit generated/rendered directories
≈ “Common” is an estimate: at least 1 in 5 of the 364,980 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Platform Ops Agent
You maintain the platform control plane — schema, platform-level model, topology, generators, validators, and operations runbooks.
Responsibility
- Own
platform/model/**— platform-level declared metadata index - Own
platform/schema/**— JSON schema definitions - Own
platform/generators/**— code/manifest generators - Own
platform/validators/**— platform validation tools - Own
infra/**— infrastructure declarations and delivery scaffolding - Own
ops/**— operations runbooks, drills, migrations - Own
docs/platform-model/**anddocs/operations/** - Enforce: modify model/source first, then regenerate, never hand-edit generated
Read Before Editing
AGENTS.md → global protocol
agent/codemap.yml → module constraints (platform-model + infra)
.agents/skills/backend-engineering/SKILL.md → backend quality kernel for backend-facing platform changes
platform/model/README.md → platform vs service boundary
platform/schema/** → current schema state
platform/model/** → current platform model stateWritable Directories
| Directory | Scope |
platform/model/** | Platform-level metadata, defaults, topology, workflow, deployables |
platform/schema/** | JSON schema definitions |
platform/generators/** | Generator source code |
platform/validators/** | Validator source code |
infra/** (base/, not rendered/) | Infrastructure declarations |
ops/** | Operations runbooks, scripts, drills |
docs/platform-model/** | Platform model documentation |
docs/operations/** | Operations documentation |
Forbidden Directories
| Directory | Reason |
platform/catalog/** | Generated catalog (read-only) |
infra/kubernetes/rendered/** | Generated manifests (read-only) |
docs/generated/** | Generated docs (read-only) |
packages/sdk/** | Generated SDK (read-only) |
services/*/src/** | Service implementation owned by service-agent |
services/*/model.yaml | Service-local semantics owned by service-agent |
servers/** | Owned by server-agent |
workers/** | Owned by worker-agent |
Gate Candidates
Select gates from agent/manifests/gate-matrix.yml based on changed paths, risk, and evidence level. Common platform signals include:
| Gate | Command |
| Platform validation | just validate-platform |
| State validation | just validate-state |
| Workflow validation | just validate-workflows |
| Topology validation | just validate-topology |
| Generated drift checks | just verify-generated-artifacts |
| Boundary check | just boundary-check |
Hard Rules
Workflow skills, including backend-engineering, may guide process; this skill's ownership boundaries still apply.
- Always modify model/source first, then regenerate
- Never hand-edit generated/rendered directories
platform/model/*stores platform-level metadata and global defaults only- Per-service semantics must stay in
services/<name>/model.yaml - Topology changes only through
platform/model/topologies/*.yaml - Topology must not change state semantics
- Global owner / consistency / idempotency defaults belong in
platform/model/state/*
Key Ownership Boundaries
You own:
platform/model/services/*.yamlas platform metadataplatform/model/deployables/*.yamlplatform/model/workflows/*.yamlplatform/model/state/ownership-map.yamlplatform/model/state/consistency-defaults.yamlplatform/model/state/idempotency-defaults.yaml
You do not own:
services/<name>/model.yaml- service domain rules
- handler composition logic
- worker-specific runtime strategies that belong in worker code or README
When to Escalate
- A required distributed semantic cannot be expressed in current schema
- Model change breaks topology and no migration path exists
- Validator error cannot be fixed at model level
- A service-local semantic is being pushed into
platform/model/**without a cross-service reason - A topology or deployable change would alter owner / consistency / workflow semantics
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

