Skip to content
Agentmart
Submit a tool

bounds-blast-radius

Trace what an exact code or configuration change could break beyond its diff, such as callers, shared state, client contracts, caches, serialization, and…

Skill by boundsj

IndexedMIT
Write a review

Chalk Labs

Need help deploying bounds-blast-radius?

Chalk Labs sets up agents like this inside real teams: connected to your tools, tested on your data, with a human in the loop where it matters.

Book a call

Install

Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.

npx agentmarket install skill/boundsj-bounds-blast-radius

Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.

Get the weekly diff

The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.

We use your email only for this newsletter. Privacy

About

Trace what an exact code or configuration change could break beyond its diff, such as callers, shared state, client contracts, caches, serialization, and migrations, and test the safety assumption it rests on. Use before shipping a change you do not fully trust.

Use cases: testing

No reviews yet. Installed it? Reviews come from verified installers only. How reviews work

Permissions

What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.

Tools
No tools found
Secrets
None asked for
Install scripts
None found

Network hosts it talks to 1

  • codeload.github.com · found in install command

Files it touches

  • ~/.claude/skills/bounds-blast-radius

What's inside

Skill name
bounds-blast-radius
Description
Trace what an exact code or configuration change could break beyond its diff, such as callers, shared state, client contracts, caches, serialization, and migrations, and test the safety assumption it rests on. Use before shipping a change you do not fully trust.
License
MIT
Instructions
35 lines in SKILL.md · view on GitHub

Files (3)

  • LICENSE.txt
  • NOTICE.md
  • SKILL.md

SKILL.md (first lines)

# Bounds blast radius

Find what a specific change breaks elsewhere, and prove or disprove the fact its safety rests on. Search hits are not the deliverable; neither is a convincing writeup without proof.

Pin the change to exact revisions, or to a fixed snapshot of uncommitted edits. If it cannot be identified, ask. Read what the diff implies without spelling out: changed defaults, ordering, timing, error paths, removed fallbacks.

Most risky-looking changes are safe or unsafe because of one or two facts, such as "this evicts only entries no reader still holds" or "every deployed client already sends the new field". Name them early and spend the effort there.

## Look where symbol search stops

- Callers, dynamic dispatch, generated code, and other languages reading the same bytes.
- Shared state: other writers, and mutable caches treated as authority.
- Client contracts: payloads, path formats, schemas, versions already deployed, and fields a client silently drops.
- Caches, freshness, and pagination across restart or retry.
- Cancellation, late completion after teardown, concurrent writers, interrupted jobs, and retries that run twice.
- Serialization, persisted formats, and migrations meeting old data or mixed versions.
- Flags, configuration, and pinned or patched dependencies; read library source when behavior matters.
- Leakage between training, validation, and evaluation data.

Cite real `file:line` or library source. Never invent a caller or API; an empty search is a result.

## Prove it

Take each load-bearing fact as far as is cheap: stated, cited, failure path shown unreachable, executed against real code, reproduced in the running app or device. When execution is authorized and safe, write the smallest check that calls the real interface through existing runners and fails loudly if you are wrong, then report its output. Keep throwaway checks outside the change unless asked. Never mutate shared or production systems to prove a point.

## Report

- **What changed,** including the non-obvious part, at which revisions.
- **Safety fact:** level reached and proof, or "unproven".
- **Risks:** mechanism, location, likelihood and cost, how to check.
- **Cleared:** what you checked and why it is fine.
- **Before merge:** the cheapest check that catches the real bug.
- **Not executed:** named checks not run, and why.

From boundsj/bounds-skills, MIT.

More from boundsj/bounds-skills

Signals

Stars
0
Forks
0
Open issues
0
Last commit (this folder)
Oct 17, 2026 (14 days ago)

From GitHub (fetched Oct 24, 2026).

Details

License
MIT
First seen
Oct 24, 2026
Last checked
Oct 24, 2026

More from boundsj

Done for you

Rather not set it up yourself?

Chalk Labs scopes, builds and runs agents for your team: the task audit, the eval harness, the integrations and the weekly ops report. Fixed scope, priced before we start.

See how we build AI agents →Read the case studies

Chalk Labs is a two-founder AI and growth studio. We build AI agents, CRMs and MVPs for Web3 and AI companies, and have shipped 50+ product and token launches.

launches shipped
50+
launches shipped
media placements
500+
media placements
founders on every account
2
founders on every account

Press we've placed: Forbes · CoinDesk · Decrypt · Cointelegraph · The Block

Rahil Jain, Co-founder, Chalk Labs. Ex-Goldman Sachs engineer. You talk to the person who builds it.

Get bounds-blast-radius running in your business

Tell us what you want to automate. A founder replies within one working day with a plan, not a pitch deck.

Goes to the Chalk Labs founders, not the newsletter. Privacy

Need help deploying bounds-blast-radius?

CallGet help
Cite this page

bounds-blast-radius skill. Agent Mart. https://agentmart.dev/skills/boundsj-bounds-blast-radius (last updated 2026-10-24)