agentleFS
Sign inStart free
wilbeibiwilbeibi/wilbeibi-skills/skills/blast-radius/SKILL.md

blast-radius

Skill2 starsChanged 2 months agoMITView on GitHub

Trace what a change could break beyond its diff and verify the assumptions its safety depends on. Use for "blast radius", "what could this break", or indirect compatibility and lifecycle risks. Use code-review for a general diff review.

111 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use ketchup-video, principle-never-block-on-the-human and 10 more.

Other files people use alongside this one.

Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
  • tristanphvnSkill

    ketchup-video

    Catch the user up like /keel:ketchup, with a short silent video of slides for what happened and the waiting calls as text under it. Use for /keel:ketchup-video.

    Also in 14 projects that use this

  • jaydubya818Skill

    principle-never-block-on-the-human

    Apply when safe reversible implementation details can proceed inside scope.

    Also in 44 projects that use this

  • ianclearySkill

    principle-explain-the-number

    Apply before you trust, report, or act on a number you measured: a speedup, a regression, a throughput, a latency, or an eval result. Find what limits it, and rule out that it measured something other than the work you think.

    Also in 29 projects that use this

  • eryzerzSkill

    make-bot-ui

    Use when building a custom UI (page, dashboard, buttons) that should wake a Grok Bot over a webhook, when the user must provide a webhook sender key, or when exposing that UI on Tailscale.

    Also in 20 projects that use this

  • bnemaSkill

    setup-pstack

    Configure which Pi models pstack uses per role. Detects available provider/model specs and writes pstack's user configuration. Use for /setup-pstack, "configure pstack models", or changing pstack model choices.

    Also in 25 projects that use this

  • jaydubya818Skill

    principle-make-operations-idempotent

    Apply when an operation must tolerate retries after partial completion.

    Also in 46 projects that use this

  • +6 more from jaydubya818

The file

We split this skill into the rules it gives an agent

4 rules. 0 are common, 4 are distinctive, and 0 are very specific to this project.

  • 0

    Common

    Most of the 106 edited versions we read keep these.

  • 4

    Distinctive

    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
  1. Distinctive:

    Name the safety assumptions: Write the concrete facts that would make the risky paths safe.

    line 13
  2. Distinctive:

    Run proofs against isolated scratch state where possible.

    line 34
  3. Distinctive:

    Keep exploratory scripts in the task's scratch directory unless a durable artifact is requested or a regression earns a place in the …

    line 35
  4. Distinctive:

    When an unsafe check cannot run, report the assumption as unproven and give the smallest next check.

    line 36

“Common” is measured: kept by at least 6 in 10 of the 106 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

blast-radius

Find the failure a caller search misses, then run the cheapest check that could disprove the safety claim.

Workflow

  1. Anchor the change. Identify the base and candidate, read the diff, and state the changed behavior. Include effects hidden behind an unchanged interface. Done when the review has a named revision and scope.
  2. Name the safety assumptions. Write the concrete facts that would make the risky paths safe. There may be several independent facts; do not force the change into one explanation. For each, name an input or state that would falsify it.
  3. Follow the indirect effects. Trace only the relevant seams: persisted data, serialized fields, another process or language, flags, caches, teardown, scheduling, retries, or downstream consumers. Check a dependency's pinned version and local patches before relying on its behavior. Done when each material risk has a real path through the code, with locations.
  4. Try to break the assumptions. Prefer a small script importing production code, an existing harness, or an isolated run of the app. Check the result and side effects, rather than a copy of the algorithm. Preserve the command and output. Done when each consequential assumption has evidence or an explicit gap.
  5. Bound the verdict. State which inputs, versions, and runtime conditions the proof covers. Separate confirmed failures, checked paths, and unverified possibilities. Passing one case does not prove a universal claim.

Evidence

Label the evidence for each safety assumption:

EvidenceWhat it establishes
Source tracedThe pinned implementation supports the claim; runtime behavior remains untested.
ExecutedReal code was exercised with named inputs and checked outputs.
App reproducedThe relevant path was exercised in the running app, including the effect at issue.
UnprovenA required dependency, environment, or check was unavailable. Name the gap.

A plausible explanation without a code path is a hypothesis. Avoid invented consumers and numeric probabilities without data. A search with no hits narrows the search result, not the set of possible external consumers.

Scope and proof

  • Preserve the requested review or fix scope. A review finding does not authorize a repair.
  • Run proofs against isolated scratch state where possible. Live services, data, external writes, and restricted actions retain the session's approval requirements.
  • Keep exploratory scripts in the task's scratch directory unless a durable artifact is requested or a regression earns a place in the project suite.
  • When an unsafe check cannot run, report the assumption as unproven and give the smallest next check. Do not mutate the environment to make the claim true.

Output

Lead with the material finding or the bounded verdict. Include the behavior change, safety assumptions with evidence labels, confirmed failure paths with code locations, checks that cleared specific risks, and remaining gaps. Link proof artifacts or include a short command and result. Omit empty categories.

Adapted from pstack/blast-radius, under the MIT license.

Download now (ZIP)

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
What did you use it for? e.g. Reviewing pull requests in a Rails app

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.

Check your setup, free