mcpField
D
ds-blast-radius

ds-blast-radius

github.com/aicodekingTesting & quality150275 installsUpdated 6d ago
Repository

About ds-blast-radius

ds-blast-radius is a change-safety review skill for developers and coding agents. It traces hidden breakage beyond text search and asks for evidence from scripts or tests, without making the fixes itself.

Key features

  1. 01Inspect diffs and changed behavior
  2. 02Identify key facts that determine safety
  3. 03Trace dependencies, timing, and data paths
  4. 04Grade claims by proof level
  5. 05Report evidence, breakage, and unknowns

Use cases

  1. 01Reviewing the risks of a code change
  2. 02Checking async ordering, retries, or teardown
  3. 03Verifying compatibility across APIs, databases, or file formats

Install

Copy the command and run it in a terminal.

$npx skills add https://github.com/aicodeking/deepseek-stack --skill ds-blast-radius

After installing, type/ds-blast-radiusin Claude Code to confirm it loaded.

Details

From the project README

ds-blast-radius

Listing callers is easy. The job is finding the breakage that a text search will not show, and proving the change is safe with a run instead of an argument.

Steps

  1. Read the change: the diff, the symbols it adds, changes or removes, and the behavior it now has that the diff does not spell out.
  2. Find the one or two facts the change is safe because of, for example "this only removes cache entries that are already expired". Most risk clears if that fact holds. Spend your effort here.
  3. Look where search stops. Read the source of libraries you call at their pinned version. Check timing: async ordering, teardown, retries. Follow data that leaves the code: API responses, database columns, file formats, config, other languages reading the same data.
  4. Grade each key fact by how far you proved it:
    1. you said so (worthless alone),
    2. you pointed at a real file and line,
    3. you traced the failure path and showed it cannot be reached,
    4. you ran a script or test against the real code that fails loudly if you are wrong,
    5. you reproduced it in the running app.
  5. Push each key fact to level 4 when it is cheap. Usually that is one small script calling the exact function in question.
  6. Report: the key facts, their proof level with the command and output, any real breakage found, and what stayed unproven.

Stop when

  • Every key fact is at level 4 or higher, or you have said why it could not be, and the report is written.
  • Or you found a real break. Report it with the repro and stop.

Rules

  • A convincing write-up is not proof. Show output.
  • Do not fix anything here. Hand fixes to the normal flow.

Comments

Markdown supported