Legacy risk check
Skill jukrap/ai-agent-playbook/skills/legacy/legacy-risk-check
Use when changing legacy code that may affect global state, shared CSS/JS, common selectors, templates, forms, API contracts, build output, or deployment behavior.From its SKILL.md
npx -y skills add jukrap/ai-agent-playbook --skill legacy-risk-checkAssembled from the repository path, not quoted from the project. Check it against their README if it does not work.
One thing to look at
- 2 stars2 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.
SKILL.md
1.2 KB, 196 tokens by cl100k_base, as published. Nobody here has run it
Legacy Risk Check
Look for hidden blast radius before editing and before declaring the work done.
Workflow
- Search every shared selector, global variable, function name, route, template fragment, config key, and API field you plan to change.
- Confirm which files are actually loaded at runtime.
- Check browser, server, database, generated-output, deployment, and manual-operation blast radius.
- Stop and report the smallest safe next step when runtime ownership or verification is unclear.
Stop Signals
- Multiple active files with the same purpose and no clear runtime winner.
- Backend contract or DB/schema shape is unclear.
- A shared selector/class is used across unrelated screens.
- Verification requires an environment you do not have.
If a stop signal blocks confidence, report the blocker and propose the smallest safe next step.
Reference
Read references/legacy-risk-inventory.md before changing shared legacy assets, contracts, build output, or deployment behavior.
What ships with it: 1 file
1.8 KB alongside SKILL.md
references/
- legacy-risk-inventory.md1.8 KB