impact-review

impact-review is a skill for Claude Code, Codex from HenriqueCotta/ownership-driven-ai-customization-architecture. It costs 31 tokens per session (272 once invoked), scanned A, original, MIT.

A workflow for checking how a change may affect related parts of a repository. It decides whether those parts need updates now or should be recorded as follow-up work.

In plain words
What is it for?
Use it after a change to inspect relevant ownership files, overlays, and follow-through rules, then document what was updated, deferred, or intentionally left unchanged.
Why use it?
It prevents important consequences from being missed while avoiding unnecessary changes across the whole repository.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Use it after a change to inspect relevant ownership files, overlays, and follow-through rules, then document what was updated, deferred, or intentionally left unchanged.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/henriquecotta/ownership-driven-ai-customization-architecture/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 HenriqueCotta/ownership-driven-ai-customization-architecture --skill impact-review
Clone the repo
git clone --depth 1 https://github.com/HenriqueCotta/ownership-driven-ai-customization-architecture

Made for: Claude Code, Codex.

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/henriquecotta/ownership-driven-ai-customization-architecture/impact-review/github.svg)](https://agentmods.dev/skills/henriquecotta/ownership-driven-ai-customization-architecture/impact-review)
Your own site
<a href="https://agentmods.dev/skills/henriquecotta/ownership-driven-ai-customization-architecture/impact-review"><img src="https://agentmods.dev/badge/skills/henriquecotta/ownership-driven-ai-customization-architecture/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/henriquecotta/ownership-driven-ai-customization-architecture/impact-review"><img src="https://agentmods.dev/badge/skills/henriquecotta/ownership-driven-ai-customization-architecture/impact-review.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 31 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 272 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 $0.00031 $0.00272
Opus 5 $0.00015 $0.00136
Sonnet 5 $0.00006 $0.00054
Haiku 4.5 $0.00003 $0.00027

Measured 12d ago against content hash 6fbce8cdebc7, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, 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 12d 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.

starter-kit/.github/skills/impact-review/SKILL.md · 30 lines

What it actually says

Impact Review

Use this skill when:

  • a change may affect more than its origin path
  • the repository's follow-through policy still needs a concrete decision in the current task
  • you need to decide between no action, immediate reconciliation, or explicit follow-up

Workflow

  1. Confirm the originating change and the requested scope.
  2. Find the relevant ownership nodes, overlays, and Follow-Through Triggers.
  3. Build a short list of downstream surfaces that could realistically matter.
  4. Inspect only the surfaces whose state could still change the decision.
  5. Decide which surfaces need no action, an update now, or explicit carry-forward.
  6. Use scripts, CI, or runbooks for exact repeatable checks.
  7. Finish by stating what was updated, what was intentionally deferred, and where that follow-through now lives if it matters.

Guardrails

  • Do not enumerate the whole repository by default.
  • Do not treat every trigger as a command to widen scope aggressively.
  • Do not leave meaningful follow-through implicit if the current pass is not closing it.
  • Do not create a new skill per trigger shape when this workflow is still sufficient.
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. 12d ago First seen · 30 lines · 31 tokens per session scan A 6fbce8cdebc7

Subscribe to this mod's changes

impact-review is a skill published in the GitHub repository HenriqueCotta/ownership-driven-ai-customization-architecture (5 stars, last pushed 4mo ago), licensed MIT. It adds 31 tokens to every session and 272 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.