klai: Command for Claude Code

.claude/commands/klai/tenant-review.md

tenant-review is a command for Claude Code from GetKlai/klai. It costs 36 tokens per session (751 once invoked), scanned A, original, MIT.

A review command that checks the current code changes against rules for keeping one tenant's data separate from another's. A tenant is one customer or isolated account in a shared application.

In plain words
What is it for?
Use it before pushing a feature branch, merging a pull request, reviewing someone else's branch, or finishing work on tenant-related code.
Why use it?
It can catch changes that might allow customers to see or affect each other's data before CI or a code review does.

Command for Claude Code

Written for Claude Code: allowed-tools in frontmatter. Also seen: reads .claude/ paths; mentions subagents; $skill-name invocation.

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/commands/klai/tenant-review.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 tenant-review

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

Your own site · 80×15
<a href="https://agentmods.dev/commands/getklai/klai/tenant-review"><img src="https://agentmods.dev/badge/commands/getklai/klai/tenant-review.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 36 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 751 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 $0.00036 $0.00751
Opus 5 $0.00018 $0.00376
Sonnet 5 $0.00007 $0.00150
Haiku 4.5 $0.00004 $0.00075

Measured 9d ago against content hash c8bdb488ea22, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

tenant-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 9d 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/commands/klai/tenant-review.md · 77 lines

How it starts

The opening of the file, as written. The whole thing — 77 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/klai:tenant-review

Run het klai-tenant-review agent op de huidige diff. Output: gestructureerde lijst met HARD findings (blockers) en SOFT findings (review-items), elk geanchored op file:line met verwijzing naar de relevante sectie van standards.md.

Default behavior

Vergelijkt huidige working tree + commits tegen main. Voor pre-push of pre-PR checks: gebruik origin/main.

Wanneer gebruiken

  • Voor git push op een feature-branch — vang regressies vóór CI ze vangt
  • Voor PR-merge — sanity check dat de changes alignen met standards.md
  • End-of-session — als je tenant-relevante files hebt aangeraakt
  • Bij review van iemand anders' PR — checkt out the branch + run dit

Wat het NIET doet

  • Geen full security audit (gebruik klai-security-audit agent)
  • Geen lint / format / type check (dat is ruff check / pyright / CI)
  • Geen impact-analysis (gebruik CodeIndex impact)
  • Geen merge-conflict resolution

Process

  1. Bepaal base-ref (uit args of default main)
  2. Run git fetch origin <base-ref> (silent — keep cache fresh)
  3. Run git diff $base-ref --stat om te tonen welke files in scope zijn
  4. Spawn klai-tenant-review agent via natural-language delegation
  5. Print de structured output

Voorbeelden

/klai:tenant-review                    # diff vs local main
/klai:tenant-review origin/main        # diff vs origin (pre-push)
/klai:tenant-review main..feature/xyz  # specific branch

Implementation

# 1. Resolve base-ref
BASE="${1:-main}"

# 2. Show scope
echo "Tenant-isolation review op diff vs $BASE"
git fetch origin --quiet 2>&1 || true
git diff "$BASE" --stat | tail -20

# 3. Delegate to agent
# Use the klai-tenant-review subagent to apply all 15 checks from
# .claude/skills/klai/tenant-isolation-checks/SKILL.md against the diff
# vs $BASE. Output the structured report (HARD findings, SOFT findings,
# confidence). If there are no tenant-relevant files in the diff, return
# "Geen tenant-relevant changes — review skipped."

Read the full file on GitHub · 77 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. 9d ago First seen · 77 lines · 36 tokens per session scan A c8bdb488ea22

Subscribe to this mod's changes

tenant-review is a command published in the GitHub repository GetKlai/klai (11 stars, last pushed today), licensed MIT. It adds 36 tokens to every session and 751 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 2026-08-30.