risk-adaptive-review

risk-adaptive-review is a skill for Claude Code, Codex from wazimmerman/zimster. It costs 27 tokens per session (1,739 once invoked), scanned A, original, MIT.

A review guide that adjusts the depth of a code review to the risk of the change, such as its scope, security impact, concurrency, or reliance on hardware or external services.

In plain words
What is it for?
It helps classify changes as low, standard, or high risk and choose targeted or repeated reviews at important architectural and integration boundaries.
Why use it?
It helps focus review effort where mistakes could spread widely or be difficult to detect, instead of treating every change the same way.

Skill for Claude CodeCodex

Written for Claude Code and Codex: shipped in a Claude Code plugin, but also agents/openai.yaml present. Also seen: mentions Codex.

Part of the zimster plugin — 12 skills, 1 command, 4 agents, 1 hook shipped together

Good fit It helps classify changes as low, standard, or high risk and choose targeted or repeated reviews at important architectural and integration boundaries.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/wazimmerman/zimster/risk-adaptive-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 wazimmerman/zimster --skill risk-adaptive-review
Clone the repo
git clone --depth 1 https://github.com/wazimmerman/zimster

Made for: Claude Code, Codex.

Or install zimster, the plugin that ships this one along with the rest of its 12 skills, 1 command, 4 agents, 1 hook.

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 risk-adaptive-review

README.md
[![agentmods](https://agentmods.dev/badge/skills/wazimmerman/zimster/risk-adaptive-review/github.svg)](https://agentmods.dev/skills/wazimmerman/zimster/risk-adaptive-review)
Your own site
<a href="https://agentmods.dev/skills/wazimmerman/zimster/risk-adaptive-review"><img src="https://agentmods.dev/badge/skills/wazimmerman/zimster/risk-adaptive-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 risk-adaptive-review

Your own site · 80×15
<a href="https://agentmods.dev/skills/wazimmerman/zimster/risk-adaptive-review"><img src="https://agentmods.dev/badge/skills/wazimmerman/zimster/risk-adaptive-review.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 27 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,739 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 $0.00027 $0.01739
Opus 5 $0.00014 $0.00870
Sonnet 5 $0.00005 $0.00348
Haiku 4.5 $0.00003 $0.00174

Measured 11d ago against content hash b89bd228a03d, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

risk-adaptive-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 11d 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.

plugins/zimster/skills/risk-adaptive-review/SKILL.md · 196 lines

How it starts

The opening of the file, as written. The whole thing — 196 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Risk-Adaptive Review

Review follows risk and architectural seams, not plan-heading count.

Risk dimensions

Dimension Low Medium High
Blast radius local unit subsystem public/cross-system
Concurrency none ordinary async races, cancellation, ownership
Security/data none recoverable auth, secrets, destructive change
Boundary internal stable dependency hardware, OS, unstable service
Novelty existing pattern adaptation new architecture
Observability deterministic fixture needed difficult/live-only

Profile mapping

Profile Deterministic rule Review
Micro All dimensions Low, one coherent slice, no public contract or hard trigger Owner verification only
Standard One or more Medium dimensions, subsystem/multi-component work, and no High/hard trigger Clean-context independent_review at the concentrated seam or integration point
High risk Any High dimension or hard trigger Early load-bearing review plus final clean-context integration independent_review

Hard triggers include auth/trust, destructive migration, concurrency ownership, public compatibility, native OS/hardware, unstable service, or live-only proof. Report the selected profile and rationale.

Owner-inline inspection is self_review; it cannot satisfy Standard or High-risk independent_review. Approval applies only to the exact candidate base/head, review-package ID, stable semantic-contract digest, and required lens set. The digest covers binding text, intended claims, implementation locations, and evidence scope, but excludes mutable evidence references, statuses, observations, and verification results. Final evidence may advance without invalidating approval when that contract and the candidate are unchanged. If review is unavailable, use OWNER_VERIFIED_REVIEW_UNAVAILABLE, never approval. CANDIDATE_COMPLETE requires the profile-appropriate semantic approval and complete matrix evidence. High-risk work requires all load-bearing obligations and final integration approval.

Read the full file on GitHub · 196 lines

Files

What ships with it

3 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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. 11d ago First seen · 196 lines · 27 tokens per session scan A b89bd228a03d

Subscribe to this mod's changes

risk-adaptive-review is a skill published in the GitHub repository wazimmerman/zimster (2 stars, last pushed 10d ago), licensed MIT. It adds 27 tokens to every session and 1,739 once invoked, about $0.0001 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.

Related

Other skills, from other repositories

architecture-review

Method for assessing a codebase's structure — duplication, single-responsibility violations, layering problems, and coupling — and recommending minimal, incremental improvements. Use when asked to review architecture, assess structure or technical debt, evaluate module boundaries, or plan a refactor. Reviews the…

thixpin/pitway · 0 tokens

security-audit

Security review and hardening workflow — root-cause analysis of vulnerabilities, authentication and authorization checks, least privilege, input handling, secret hygiene, and security regression tests. Use when reviewing code for security, fixing a vulnerability, hardening a feature, or handling auth, permissions…

thixpin/pitway · 92 tokens

code-quality-review

Checklist and method for reviewing code quality — readability, maintainability, SOLID, DRY, performance, and backward compatibility. Use when asked to review code, a diff, a branch, or a merge request for quality, or before finalizing significant changes. For GitHub PR review use the built-in /review; for…

thixpin/pitway · 79 tokens

safe-change

Trace, implement, test, and independently review one bounded software change. Use for ordinary feature, bug-fix, or refactor work after the repository is bootstrapped; do not use for broad repository cleanup, production operations, or undefined rewrites.

cz1993/vibe-coding-repository-standard · 54 tokens

behavior-implement

Implement behavior through a red-green-refactor cycle when focused automated tests are proportionate. Use for product behavior changes and for engineering tooling and infrastructure only when native checks are insufficient and concrete complexity or failure risk warrants dedicated tests.

yarlson/yarstack · 48 tokens

ai-slop-cleaner

Clean AI-generated code slop with a regression-safe, deletion-first workflow and optional reviewer-only mode.

naimkatiman/continuous-improvement · 25 tokens