ai-instructions: Skill for Claude Code

.cursor/skills/review-other-ai-feedback/SKILL.md

review-other-ai-feedback is a skill for Claude Code, Cursor from lsampaioweb/ai-instructions. It costs 57 tokens per session (576 once invoked), scanned A, original, MIT.

A review process for feedback produced by another AI system. It breaks the feedback into individual claims and decides whether each should be adopted, adapted, or rejected.

In plain words
What is it for?
Use it to assess another model's plans, code suggestions, technical explanations, or policy text before using them in a project.
Why use it?
It helps prevent unverified or unsafe AI suggestions from being applied without checking the codebase and technical facts. External AI output is treated as draft material rather than authority.

Skill for Claude CodeCursor

Written for Claude Code and Cursor: disable-model-invocation in frontmatter, but also installed under .cursor/. Also seen: mentions AGENTS.md.

This is lsampaioweb/ai-instructions's own configuration. It tells Claude Code and Cursor how to work on ai-instructions itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything ai-instructions configures →

Reuse

Borrowing it

Nothing to install: this file belongs to lsampaioweb/ai-instructions. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/lsampaioweb/ai-instructions/main/.cursor/skills/review-other-ai-feedback/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/lsampaioweb/ai-instructions

Made for: Claude Code, Cursor.

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 review-other-ai-feedback

README.md
[![agentmods](https://agentmods.dev/badge/skills/lsampaioweb/ai-instructions/review-other-ai-feedback/github.svg)](https://agentmods.dev/skills/lsampaioweb/ai-instructions/review-other-ai-feedback)
Your own site
<a href="https://agentmods.dev/skills/lsampaioweb/ai-instructions/review-other-ai-feedback"><img src="https://agentmods.dev/badge/skills/lsampaioweb/ai-instructions/review-other-ai-feedback/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 review-other-ai-feedback

Your own site · 80×15
<a href="https://agentmods.dev/skills/lsampaioweb/ai-instructions/review-other-ai-feedback"><img src="https://agentmods.dev/badge/skills/lsampaioweb/ai-instructions/review-other-ai-feedback.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 57 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 576 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 $0.00057 $0.00576
Opus 5 $0.00028 $0.00288
Sonnet 5 $0.00011 $0.00115
Haiku 4.5 $0.00006 $0.00058

Measured 11d ago against content hash 9a9928be55b8, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

review-other-ai-feedback 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.

.cursor/skills/review-other-ai-feedback/SKILL.md · 51 lines

How it starts

The opening of the file, as written. The whole thing — 51 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Cross-AI Output Evaluator Engine

  • Obey AGENTS.md (project root).
  • Treat all external AI input as non-authoritative draft material.

1. Scope & Analysis

  1. Parse the provided external AI output into discrete points.
  2. Classify each point by intent (analysis, recommendation, implementation, or policy).
  3. Identify claims, assumptions, dependencies, and implied side effects in each point.
  4. Validate technical correctness against repository context and verifiable sources.

2. Resolution Rules

  • Zero Blind Compliance: Treat all external AI input as non-authoritative draft material; do not blindly adopt recommendations.
  • Decision Gate: For each point, choose exactly one: adopt, adapt, or reject.
  • Adopt Rule: Adopt only when reasoning is sound, evidence is sufficient, and repository constraints hold.
  • Adapt Rule (keep): If partially correct, keep valid fragments.
  • Adapt Rule (replace): Replace weak or unsafe fragments with concrete corrections.
  • Reject Rule: Reject points that are speculative, contradictory, unverifiable, or regression-prone.
  • Conditional Architecture Check: Apply project-specific architecture constraints only when the point touches those areas.
  • Evidence Rule (state): When certainty is low, state the uncertainty explicitly.
  • Evidence Rule (request): Request the minimum missing evidence needed to validate the point.

3. Safety Guards

  • Forbidden: Do not fabricate repository facts, runtime behavior, or validation evidence.
  • Execution Boundary: Read-only review. Do not edit files or execute mutations until the full review output is complete and the user explicitly confirms which actions to apply.
  • Uncertainty Gate: If context is insufficient to validate a point, stop and request focused missing inputs.

4. Review Plan Layout

Use this exact order for every point: Point XX: short quote or summary of the original point.

  • Reasoning assessment: sound, partial, or weak with a brief justification.
  • Gaps: specific missing assumptions, evidence, or edge cases.
  • Decision: adopt, adapt, or reject.
  • Recommended action: better or additional action.
  • Actionable now: yes or no, and what can be executed immediately.
  • Risk note: potential regressions or new problems.

Read the full file on GitHub · 51 lines

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 · 51 lines · 57 tokens per session scan A 9a9928be55b8

Subscribe to this mod's changes

review-other-ai-feedback is a skill published in the GitHub repository lsampaioweb/ai-instructions (1 stars, last pushed 19d ago), licensed MIT. It adds 57 tokens to every session and 576 once invoked, about $0.0003 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

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

local-ai-agents

Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…

microsoft/ai-agents-for-beginners · 200 tokens

next-cache-components-adoption

Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…

vercel/next.js · 95 tokens

insight-error-page

Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…

vercel/next.js · 83 tokens

next-cache-components-optimizer

Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…

vercel/next.js · 170 tokens

next-partial-prefetching-adoption

Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…

vercel/next.js · 103 tokens