impact-review

impact-review is a skill for Claude Code from Aibier/claude-em-toolkit. It costs 36 tokens per session (422 once invoked), scanned A, original, MIT.

A code-review method that checks both whether a change is correct and what other code may be affected by it. The blast radius means the files, services, or users that could be impacted.

In plain words
What is it for?
Use it to review local Git changes, find callers and consumers, inspect shared APIs or schemas, and list the checks needed before merging.
Why use it?
A change can pass its own tests while breaking callers or shared interfaces elsewhere. Tracing dependencies reveals those risks before the change is merged.

Skill for Claude Code

Written for Claude Code: installed under .claude/.

Good fit Use it to review local Git changes, find callers and consumers, inspect shared APIs or schemas, and list the checks needed before merging.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/aibier/claude-em-toolkit/impact-review
Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Any agent
npx skills add Aibier/claude-em-toolkit --skill impact-review
Clone the repo
git clone --depth 1 https://github.com/Aibier/claude-em-toolkit

Made for: Claude Code.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for impact-review

README.md
[![agentmods](https://agentmods.dev/badge/skills/aibier/claude-em-toolkit/impact-review/github.svg)](https://agentmods.dev/skills/aibier/claude-em-toolkit/impact-review)
Your own site
<a href="https://agentmods.dev/skills/aibier/claude-em-toolkit/impact-review"><img src="https://agentmods.dev/badge/skills/aibier/claude-em-toolkit/impact-review/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for impact-review

Your own site · 80×15
<a href="https://agentmods.dev/skills/aibier/claude-em-toolkit/impact-review"><img src="https://agentmods.dev/badge/skills/aibier/claude-em-toolkit/impact-review.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 36 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 422 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00036 $0.00422
Opus 5 $0.00018 $0.00211
Sonnet 5 $0.00007 $0.00084
Haiku 4.5 $0.00004 $0.00042

Measured 9d ago against content hash ac2a662a6e19, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

impact-review scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 9d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

.claude/skills/impact-review/SKILL.md · 43 lines

What it actually says

Code Review + Impact-of-Change Analysis

Goes one step beyond a normal review: not just "is this code correct" but "what does changing it put at risk".

Steps

  1. Get the change scope: git diff (staged/working tree, or against base branch).

  2. Correctness pass (see also the code-reviewer agent for a dedicated read-only pass): logic errors, edge cases, error handling, test coverage gaps.

  3. Impact / blast-radius pass — for each changed function/type/endpoint/schema:

    • Find call sites / consumers: grep/rg for the symbol across the repo (and across services if it's a shared contract — API, schema, shared package)
    • Identify anything that assumes the old behavior (return type, error conditions, side effects, ordering, performance characteristics)
    • Flag changes to shared/public surfaces (exported APIs, DB schemas, queue message formats) as higher-risk than internal-only changes
  4. Summarize:

    ## Correctness
    <findings, or "no issues found">
    
    ## Blast radius
    - Direct consumers: <files/services that call the changed code>
    - Risk level: <low/medium/high — and why>
    - Things to verify before merging: <specific checks — e.g. "run the
      billing integration suite, it depends on this return shape">
    

Notes

  • This is a local review — run it on your working changes before opening a PR, not as a substitute for CI.
  • "No consumers found" is itself a useful finding — it might mean dead code, or it might mean the search missed cross-service usage; say which you suspect.
Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 9d ago First seen · 43 lines · 36 tokens per session scan A ac2a662a6e19

Subscribe to this mod's changes

impact-review is a skill published in the GitHub repository Aibier/claude-em-toolkit (5 stars, last pushed 3mo ago), licensed MIT. It adds 36 tokens to every session and 422 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.