AgentStack
Sign in Publish
MCP servers Skills Toolkits Why AgentStack Sell Docs
Sign in
SKILL verified MIT Self-run

Backend Change Safety

skill-jukrap-ai-agent-playbook-backend-change-safety · by jukrap

Use when changing backend services, modules, workers, scheduled jobs, integrations, queues, configuration, or server-side business logic.

↗ Website ↗ Repository
— No reviews yet
0 installs
4 views
0.0% view→install

Install

$ agentstack add skill-jukrap-ai-agent-playbook-backend-change-safety

✓ scanned · ✓ verified — works with Claude Code, Cursor, and more.

Security review

✓ Passed

No 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.

Are you the author of Backend Change Safety? Claim this listing to set pricing, connect Stripe payouts, and keep 70% of every sale.
Sign up to claim

About

Backend Change Safety

Use this as the primary backend skill for non-trivial server-side changes that are not only API mapping or server-rendered flow work.

Workflow

  1. Identify entrypoints, owners, runtime mode, data stores, side effects, and downstream consumers before editing.
  2. Classify the change as additive, compatible, behavior-changing, destructive, operational, or integration-facing.
  3. Keep controllers, services, repositories, workers, config, and module entrypoints in their existing responsibility boundaries.
  4. Verify request paths, async paths, retries/idempotency, permissions, configuration, logs/metrics, and rollback shape.
  5. Use request-validation-error-contract for request parsing, validation, and client-visible error changes.
  6. Use job-worker-reliability for jobs, workers, queues, schedulers, retries, and dead-letter paths.
  7. Load the relevant stack profile from references/stacks/ only after the repository stack is known.

Reference

Read references/backend-change-checklist.md before implementing or reviewing backend changes with shared runtime, persistence, or integration risk.

Read references/api-versioning-compatibility.md when a route, DTO, SDK, event, webhook, or client-visible payload may need compatibility handling.

Read references/transaction-side-effect-boundary.md when persistence, external side effects, events, jobs, or retries must stay consistent.

Read references/config-cache-runtime-contracts.md when changing configuration, feature flags, caches, process startup, or runtime defaults.

Read references/stack-profile-selection.md when the repository stack is known and you need to choose a Java, Kotlin, Node, Python, Go, .NET, or PHP profile.

Read references/async-boundary-idempotency.md for workers, queues, scheduled jobs, webhooks, retries, and duplicate-delivery safety.

Source & license

This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.

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.

More in Agent Skills