agentleFS
malinskibeniaminmalinskibeniamin/skills/blast-radius/SKILL.md

blast-radius

Skill4 starsChanged 11 days agoMITView on GitHub

Find non-local breakage from a change and prove the decisive safety invariant with executable evidence. Use for blast radius, what could this break, or a suspicious small diff.

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

5 rules. 0 are common, 4 are distinctive, and 1 is 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.

  • 1

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    When proving changed behavior or maintaining verification, read the Poteto adaptation.

    line 6
  2. Distinctive:

    Read the complete change, changed symbols, call sites, producers, consumers, schemas, and public surfaces.

    line 24
  3. Distinctive:

    Look where symbol search stops: serialized data, database columns, feature flags, another language, library source at the pinned version, …

    line 26
  4. Very specific:

    If the running user path is available, exercise it through /dogfood.

    line 29
  5. Distinctive:

    Keep risks evidence-backed and bounded.

    line 39

“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

When proving changed behavior or maintaining verification, read the Poteto adaptation.

Blast radius

Find what a change can break beyond its diff. Listing callers is reconnaissance, not the result. The result is the one fact the change is safe because of, proven as directly as practical.

Contract

  • Fixed point: review the requested base through current working state unless the caller supplies another point.
  • Fence: inspect non-local contracts and run verification; do not edit product code.
  • Question: what hidden consumer, lifecycle, wire shape, shared state, or external contract can turn this change into a defect?

Proof ladder

Move each safety fact down this ladder as cheaply as possible: source line -> walked counterexample -> executable script or test -> real running entrypoint. A claim below executable proof is unproven, not safe by confidence.

Pass

  1. Read the complete change, changed symbols, call sites, producers, consumers, schemas, and public surfaces. State what behavior differs, including implicit timing and lifecycle changes.
  2. Name the decisive safety invariant. Prefer one fact that clears several speculative risks, such as "the operation only removes expired entries and is otherwise inert."
  3. Look where symbol search stops: serialized data, database columns, feature flags, another language, library source at the pinned version, teardown order, retries, concurrency, and callers reached through configuration.
  4. Build the smallest credible failure path. Separate confirmed risks from checked-and-cleared paths. Cite exact evidence; a search that finds nothing is evidence only when the searched scope is complete.
  5. Prove the invariant through the real code. Add a disposable script or focused public-contract test when that is the cheapest executable check. Do not keep a test that only repeats source text.
  6. If the running user path is available, exercise it through /dogfood. Record where each fact stopped on the proof ladder.

Output

  • Change: observable semantic difference.
  • Safety invariant: exact fact, proof rung, command, and observation; otherwise unproven.
  • Risks: failure path, likelihood, impact, evidence, and cheapest check.
  • Cleared: paths checked and the evidence that clears them.
  • Before merge: smallest command or reproduction that fails if the invariant is false.

Keep risks evidence-backed and bounded. Do not inflate a list of possibilities after the decisive invariant has been proven.

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.