klai: Skill for Claude Code

.claude/skills/klai/tenant-isolation-checks/SKILL.md

klai-tenant-isolation-checks is a skill for Claude Code from GetKlai/klai. It costs 206 tokens per session (2,551 once invoked), scanned A, original, MIT.

A checklist for reviewing code changes that could weaken tenant isolation. Tenant isolation keeps one organization or customer's data separate from another's.

In plain words
What is it for?
It is for reviewing diffs involving tenant-aware database models, row-level security, webhooks, and related access controls.
Why use it?
It helps catch missing database protections and unsafe data-access patterns before they reach production.

Skill for Claude Code

Written for Claude Code: installed under .claude/. Also seen: positional $N argument.

This is GetKlai/klai's own configuration. It tells Claude Code how to work on klai 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 klai configures →

View source ↗ GetKlai/klai
Reuse

Borrowing it

Nothing to install: this file belongs to GetKlai/klai. 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/GetKlai/klai/main/.claude/skills/klai/tenant-isolation-checks/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/GetKlai/klai

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 klai-tenant-isolation-checks

README.md
[![agentmods](https://agentmods.dev/badge/skills/getklai/klai/tenant-isolation-checks/github.svg)](https://agentmods.dev/skills/getklai/klai/tenant-isolation-checks)
Your own site
<a href="https://agentmods.dev/skills/getklai/klai/tenant-isolation-checks"><img src="https://agentmods.dev/badge/skills/getklai/klai/tenant-isolation-checks/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 klai-tenant-isolation-checks

Your own site · 80×15
<a href="https://agentmods.dev/skills/getklai/klai/tenant-isolation-checks"><img src="https://agentmods.dev/badge/skills/getklai/klai/tenant-isolation-checks.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 206 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,551 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. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
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 $0.00206 $0.02551
Opus 5 $0.00103 $0.01275
Sonnet 5 $0.00041 $0.00510
Haiku 4.5 $0.00021 $0.00255

Measured 10d ago against content hash 63e970fb63a7, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

klai-tenant-isolation-checks 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 10d 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/klai/tenant-isolation-checks/SKILL.md · 252 lines

How it starts

The opening of the file, as written. The whole thing — 252 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Klai Tenant-Isolation Checks

This skill codifies the patterns from reports/audit-tenant-isolation-2026-05-05/standards.md as a reviewable checklist. Use it when reviewing a code diff to catch tenant-isolation regressions BEFORE they ship.

How to use

Given a diff (git diff main or PR diff), walk every changed line through the relevant checks below. Each check has a hard-or-soft verdict:

  • HARD — blocker, must be fixed before merge
  • SOFT — flag for review, may be acceptable with explicit justification

Output format per finding:

[HARD|SOFT] file:line — <pattern violated>
  Current:    <code excerpt>
  Standard:   <link to standards.md section>
  Suggestion: <concrete fix>

Check 1: Postgres RLS coverage (HARD)

For every new SQLAlchemy model with org_id/tenant_id/customer_id:

  • Does an alembic migration create a Cat-D RLS policy on the table?
  • Is ENABLE ROW LEVEL SECURITY + FORCE ROW LEVEL SECURITY set?
  • Is there an explicit WITH CHECK clause?
  • Is the policy named tenant_isolation (or _select / _insert for split policies)?

For every new SQL text() query against an RLS-protected table:

  • Does it include WHERE org_id = ... OR rely on RLS via tenant_scoped_session()?

For every new op.create_table(...) in alembic:

  • If the table has org_id/tenant_id, is RLS added in the same migration?

Standards ref: standards.md sections 1, 2

Check 2: Session-helper discipline (HARD)

For every new AsyncSessionLocal() direct usage (no helper):

  • Is there a # cross-org-by-design: <reason> comment explaining why no helper?
  • Does the code IMMEDIATELY call set_tenant(db, org_id) before any RLS query?
  • If background task / poller: is tenant_scoped_session(org_id) or cross_org_session() used instead?

HARD — implicit cross-org via "no filter" is the bug class we're eliminating.

Standards ref: standards.md sections 3, 4

Check 3: Cat-A WITH CHECK discipline (HARD)

Read the full file on GitHub · 252 lines

Files

What ships with it

1 file 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. 10d ago First seen · 252 lines · 206 tokens per session scan A 63e970fb63a7

Subscribe to this mod's changes

klai-tenant-isolation-checks is a skill published in the GitHub repository GetKlai/klai (11 stars, last pushed today), licensed MIT. It adds 206 tokens to every session and 2,551 once invoked, about $0.0010 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 2026-08-30.

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