ai-instructions: Skill for Cursor

.cursor/skills/review-ai-customization-files/SKILL.md

review-ai-customization-files is a skill for Cursor from lsampaioweb/ai-instructions. It costs 90 tokens per session (1,978 once invoked), scanned A, original, MIT.

A read-only checker for files that tell AI coding tools how to work. It compares the chosen files for repeated, conflicting, unclear, or inefficient instructions.

In plain words
What is it for?
Use it to audit AI instruction files, compare rules across folders, check file-matching settings, and receive a scored structured report.
Why use it?
It helps find rules that disagree, repeat themselves, or are too vague for an AI tool to follow reliably. It requires you to provide the files or folders to inspect.

Skill for Cursor

Written for Cursor: installed under .cursor/.

This is lsampaioweb/ai-instructions's own configuration. It tells 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-ai-customization-files/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/lsampaioweb/ai-instructions

Made for: 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-ai-customization-files

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

Your own site · 80×15
<a href="https://agentmods.dev/skills/lsampaioweb/ai-instructions/review-ai-customization-files"><img src="https://agentmods.dev/badge/skills/lsampaioweb/ai-instructions/review-ai-customization-files.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 90 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,978 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 $0.00090 $0.01978
Opus 5.5 $0.00036 $0.00791
Sonnet 5.5 $0.00018 $0.00396
Haiku 4.5 $0.00009 $0.00198

Measured 1mo ago against content hash b983b2280880, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

review-ai-customization-files 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 1mo 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-ai-customization-files/SKILL.md · 121 lines

How it starts

The opening of the file, as written. The whole thing — 121 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AI Customization Audit

Arguments

  • Required: file, file list, folder, or glob to audit.
  • Optional for single-file scopes: explicit review-ledger path.

1. Scope and Analysis

  1. Review only the user-provided scope. If it is missing, stop and request it.
  2. Resolve the style contract in this order: workspace .github/instructions/ai-customization.instructions.md, then the applicable user-level contract supplied by the environment. If neither exists, stop and report the missing prerequisite.
  3. Load and apply the resolved style contract.
  4. Resolve the supplied scope to files. Require at least one readable target file; otherwise report the scope as invalid and return BLOCKED.
  5. Identify active references among the files in scope.

2. Review State and Convergence

  1. Load the review ledger before scanning when it exists.
  2. For a single-file scope, use <file>.review-ledger.md as the default ledger path. An explicit ledger path takes precedence over the default path. Validate and use the selected path consistently for loading, reporting, creation approval, and updates. If it does not exist, report it as not initialized and do not silently fall back to another path. If an existing ledger is unreadable or does not contain the required fields, report Review ledger: invalid with the path and reason, return BLOCKED, and do not scan or modify the target file.
  3. For a folder or glob, review each resolved file independently and use <file>.review-ledger.md beside each file as its deterministic ledger path. Do not require one shared folder ledger or an explicit ledger path.
  4. If the resolved ledger does not exist, report Review ledger: not initialized and continue the current scan. Do not create an empty ledger.
  5. Assign each new finding the next unused severity number in the applicable ledger or current report. Treat every new finding as PROVISIONAL until its ID and required fields are written to the ledger; only then mark its ID state LEDGER. Preserve provisional IDs when the ledger is approved and created unless they conflict with existing entries.
  6. Assign each finding a stable fingerprint based on canonical file identity, category, and normalized substantive problem. Do not include line location in the fingerprint.
  7. When a ledger exists, assign each new finding the next unused number for its severity in that ledger. Reuse the ledger ID when the same fingerprint appears again. Do not call a new finding immutable or LEDGER until the ledger update is complete. Sort findings for display independently of their IDs.
  8. Without a ledger, do not infer FIXED, ACCEPTED, or REJECTED status from conversation history, diffs, or filenames. Treat the review as having no persisted finding history.
  9. Mark findings as OPEN, FIXED, ACCEPTED, or REJECTED.
  10. Do not report FIXED, ACCEPTED, or REJECTED findings again unless the relevant content snapshot, referenced instruction, or applicable scope has materially changed.
  11. When a resolved finding materially changes, retain its fingerprint and ID, mark it OPEN, store the new snapshot, and append the transition to its resolution history.
  12. A wording preference, optional rewrite, or alternative style is not a finding.
  13. When no new or unresolved substantive findings remain, report Findings: none and return READY.
  14. When no ledger exists, state that current findings are clean only for this scan; do not claim that previous findings were resolved. If the scan has no findings, leave the ledger uncreated.
  15. Update the target files only after explicit user confirmation.
  16. When the user approves target-file fixes, create or update each affected file's adjacent ledger in the same operation and record the approved findings as FIXED, unless the user explicitly excludes ledger changes.
  17. Create or update the ledger only after explicit user confirmation when a finding is explicitly accepted or rejected without changing the target file. Do not create a ledger for a clean scan.
  18. Store at least the finding ID, fingerprint, file path, category, status, content snapshot or revision, and resolution note in the ledger. A valid ledger must be readable and contain those fields for every finding.

Read the full file on GitHub · 121 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. 1mo ago Changed · +35 lines · +31 tokens per session b983b2280880
  2. 2mo ago First seen · 86 lines · 59 tokens per session scan A 8a74432ebeda

Subscribe to this mod's changes

review-ai-customization-files is a skill published in the GitHub repository lsampaioweb/ai-instructions (1 stars, last pushed 5d ago), licensed MIT. It adds 90 tokens to every session and 1,978 once invoked, about $0.0004 per session on Opus 5.5. 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

review-ai-customization-files compared with skills from other repositories

review-ai-customization-files next to 6 skills from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
review-ai-customization-fileslsampaioweb/ai-instructionsSkill15d agoMITA90Cursor
imagegenopenai/codexSkill133kyesterdayApache-2.0A113Codex
playwright-climicrosoft/playwrightSkill99kyesterdayApache-2.0A19Claude Code
local-ai-agentsmicrosoft/ai-agents-for-beginnersSkill79k4d agoMITA200Claude Code, Codex
systematic-debuggingobra/superpowersSkill313k3d agoMITA21Claude Code
next-cache-components-adoptionvercel/next.jsSkill143ktodayMITA95Claude Code
next-partial-prefetching-adoptionvercel/next.jsSkill143ktodayMITA103Claude Code