lictor-rotate

lictor-rotate is a skill for Claude Code from Raffa-jarrl/Lictor-AI. It costs 80 tokens per session (3,048 once invoked), scanned A, original, Apache-2.0.

A step-by-step guide for replacing a leaked API key with a new one. An API key is a secret string that lets software access a service, and the guide covers several common providers and generic OAuth services.

In plain words
What is it for?
Use it when a key from providers such as Stripe, OpenAI, GitHub, AWS, Slack, or Supabase has been exposed. It explains where to rotate the key, how urgent the situation is, and how to update the application safely.
Why use it?
A leaked key may let others use an account or service and cannot be made safe simply by deleting it from code. The guide directs you through revoking or replacing it and checking that the new key works.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the lictor-security-suite plugin — 4 skills shipped together

Good fit Use it when a key from providers such as Stripe, OpenAI, GitHub, AWS, Slack, or Supabase has been exposed. It explains where to rotate the key, how urgent the situation is, and how to update the application safely.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/raffa-jarrl/lictor-ai/lictor-rotate
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 Raffa-jarrl/Lictor-AI --skill lictor-rotate
Clone the repo
git clone --depth 1 https://github.com/Raffa-jarrl/Lictor-AI

Made for: Claude Code.

Or install lictor-security-suite, the plugin that ships this one along with the rest of its 4 skills.

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 lictor-rotate

README.md
[![agentmods](https://agentmods.dev/badge/skills/raffa-jarrl/lictor-ai/lictor-rotate/github.svg)](https://agentmods.dev/skills/raffa-jarrl/lictor-ai/lictor-rotate)
Your own site
<a href="https://agentmods.dev/skills/raffa-jarrl/lictor-ai/lictor-rotate"><img src="https://agentmods.dev/badge/skills/raffa-jarrl/lictor-ai/lictor-rotate/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 lictor-rotate

Your own site · 80×15
<a href="https://agentmods.dev/skills/raffa-jarrl/lictor-ai/lictor-rotate"><img src="https://agentmods.dev/badge/skills/raffa-jarrl/lictor-ai/lictor-rotate.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 80 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,048 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. 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 $0.00080 $0.03048
Opus 5 $0.00040 $0.01524
Sonnet 5 $0.00016 $0.00610
Haiku 4.5 $0.00008 $0.00305

Measured 12d ago against content hash f2de6c832cf6, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

lictor-rotate scanned grade A with 1 finding 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 12d 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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

8. **Verify rotation worked:** try the old key with `curl
skills/plugins/lictor-security-suite/skills/lictor-rotate/SKILL.md · 290 lines

How it starts

The opening of the file, as written. The whole thing — 290 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Lictor Rotate — guided key rotation

A key got leaked. The user needs to rotate it. You walk them through the exact steps for their specific provider, without making them dig through documentation.

How invocation works

The user typed /lictor-rotate (with or without a provider name). Three shapes:

  1. /lictor-rotate alone — ask which provider
  2. /lictor-rotate stripe — go straight to the Stripe runbook
  3. /lictor-rotate openai sk-... — they pasted the leaked key

If a key string is pasted into the chat: redact it in your reply. Don't echo sk_live_AAAA...EFGH back at them. Say "your sk_live_*... EFGH key" using only the prefix and last 4 chars. The full key shouldn't end up in chat logs more times than necessary.

What you do (general flow)

  1. Confirm urgency. Is the key already in a public repo or a deployed site? If yes, this is "do it in the next hour" urgent. If no (e.g. they found it in a private repo and want to clean up), it's "do it today" urgent.
  2. Walk them through the provider's rotation flow. Use the provider-specific runbook below. Be specific: the exact URL, the exact button label.
  3. Tell them what to do with the new key. Replace the old key in their .env, restart their dev server, redeploy.
  4. Help them check for damage. Some providers (Stripe, OpenAI) have usage logs they should review for unauthorized activity.
  5. Confirm the old key is dead. Most providers let you test by trying to use the old key — it should return 401.

Provider runbooks

Stripe

  1. Open https://dashboard.stripe.com/apikeys
  2. Find the live secret key (starts with sk_live_) — match on the prefix the user gave you
  3. Click the ··· menu next to it → Roll key
  4. Stripe asks: "How long should the old key remain active?" Pick 0 seconds (immediate revocation) unless they have automated systems they need to update first
  5. Stripe shows the new key once — copy it now, you can't see it again
  6. Where to put the new key:
    • .env.local (or .env.production for deployed environment)
    • Variable name: STRIPE_SECRET_KEY (or whatever they used)
    • Restart their dev server
    • Redeploy to production (Vercel/Netlify environment variables UI)
  7. Check for damage:
  8. Verify rotation worked: try the old key with curl https://api.stripe.com/v1/charges -u <OLD_KEY>: — should return 401 Unauthorized

Read the full file on GitHub · 290 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. 12d ago First seen · 290 lines · 80 tokens per session scan A f2de6c832cf6

Subscribe to this mod's changes

lictor-rotate is a skill published in the GitHub repository Raffa-jarrl/Lictor-AI (18 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 80 tokens to every session and 3,048 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.