aat-fingerprint

aat-fingerprint is a command for Claude Code from MikkoParkkola/anti-ai-tell. It costs 12 tokens per session (282 once invoked), scanned A, original, MIT.

A command for creating or updating a style fingerprint, a small record of chosen visual and writing preferences.

In plain words
What is it for?
Use it to derive preferences from an existing artifact, ask about missing choices, save them in fingerprint.json, and validate the result.
Why use it?
It gives later checks a reference for personal choices, so deliberate fonts, colours, corner shapes, or visual modes are not mistaken for generic AI output.

Command for Claude Code

Written for Claude Code: ${CLAUDE_PLUGIN_ROOT} variable. Also seen: names the AskUserQuestion tool.

Runs only inside its plugin — its command needs a path that Claude Code sets for a plugin’s own hooks and for nothing else. Install the plugin, not this.

Part of the anti-ai-tell plugin — 1 skill, 2 commands, 3 hooks shipped together

Good fit Use it to derive preferences from an existing artifact, ask about missing choices, save them in fingerprint.json, and validate the result.

Compare 6 commands from other repositories ↓
Install

Getting it into your agent

This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.

Claude Code
/plugin marketplace add MikkoParkkola/anti-ai-tell
Claude Code
/plugin install anti-ai-tell

Made for: Claude Code.

Or install anti-ai-tell, the plugin that ships this one along with the rest of its 1 skill, 2 commands, 3 hooks.

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 aat-fingerprint

README.md
[![agentmods](https://agentmods.dev/badge/commands/mikkoparkkola/anti-ai-tell/aat-fingerprint/github.svg)](https://agentmods.dev/commands/mikkoparkkola/anti-ai-tell/aat-fingerprint)
Your own site
<a href="https://agentmods.dev/commands/mikkoparkkola/anti-ai-tell/aat-fingerprint"><img src="https://agentmods.dev/badge/commands/mikkoparkkola/anti-ai-tell/aat-fingerprint/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 aat-fingerprint

Your own site · 80×15
<a href="https://agentmods.dev/commands/mikkoparkkola/anti-ai-tell/aat-fingerprint"><img src="https://agentmods.dev/badge/commands/mikkoparkkola/anti-ai-tell/aat-fingerprint.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 12 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 282 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 $0.00012 $0.00282
Opus 5 $0.00006 $0.00141
Sonnet 5 $0.00002 $0.00056
Haiku 4.5 $0.00001 $0.00028

Measured 12d ago against content hash 2057823235bd, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

aat-fingerprint 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 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.

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.

plugins/anti-ai-tell/commands/aat-fingerprint.md · 24 lines

What it actually says

Seed or refine the user's fingerprint.json — the single source of truth for their chosen point of view, the cure for generic AI design.

Derive-then-confirm (the chosen seeding flow):

  1. Derive. If the user points at an existing artifact (a site, CSS, deck, or writing sample), run python3 ${CLAUDE_PLUGIN_ROOT}/skills/anti-ai-tell/fingerprint.py derive <file> to extract whatever slots it can read (fonts, accent, radius, mode).
  2. Confirm. Run python3 ${CLAUDE_PLUGIN_ROOT}/skills/anti-ai-tell/fingerprint.py gaps to list the unset slots, then ask the user about ONLY those, via AskUserQuestion (e.g. accent lane: warm/cool/mono/bold). Keep it to 3-5 taps.
  3. Persist. Write the merged result to fingerprint.json in the repo root. Validate with fingerprint.py validate fingerprint.json. Never re-ask a slot that's already set.

If the user has no artifacts and no preferences yet, print the ELITE seed (fingerprint.py seed) as a starting point and let them edit.

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 · 24 lines · 12 tokens per session scan A 2057823235bd

Subscribe to this mod's changes

aat-fingerprint is a command published in the GitHub repository MikkoParkkola/anti-ai-tell (3 stars, last pushed 8d ago), licensed MIT. It adds 12 tokens to every session and 282 once invoked, about $0.0001 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.