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.
/plugin marketplace add MikkoParkkola/anti-ai-tell/plugin install anti-ai-tellWrote 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.
[](https://agentmods.dev/commands/mikkoparkkola/anti-ai-tell/aat-lint)<a href="https://agentmods.dev/commands/mikkoparkkola/anti-ai-tell/aat-lint"><img src="https://agentmods.dev/badge/commands/mikkoparkkola/anti-ai-tell/aat-lint/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.
<a href="https://agentmods.dev/commands/mikkoparkkola/anti-ai-tell/aat-lint"><img src="https://agentmods.dev/badge/commands/mikkoparkkola/anti-ai-tell/aat-lint.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00019 | $0.00228 |
| Opus 5 | $0.00010 | $0.00114 |
| Sonnet 5 | $0.00004 | $0.00046 |
| Haiku 4.5 | $0.00002 | $0.00023 |
Grade A, and why
aat-lint 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.
What it actually says
Run the anti-ai-tell linters on $ARGUMENTS (a file or directory; default: the
current directory's changed files).
- For prose (
.md,.txt):python3 ${CLAUDE_PLUGIN_ROOT}/skills/anti-ai-tell/lint.py <file> --prose - For code/markup (
.css,.tsx,.svg,.docx, ...):python3 ${CLAUDE_PLUGIN_ROOT}/skills/anti-ai-tell/visual_lint.py <file_or_dir> - If a
fingerprint.jsonexists, pass--fingerprint fingerprint.jsonso the user's chosen accent/font is not flagged.
Report the findings grouped by severity (Hard-tell / Strong-flag / Density-watch), then remind: a clean lint is the floor, not the ceiling — do the Tier-2 hand-pass (hierarchy, point of view, a rough edge) the linter can't see.
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.
- 12d ago First seen · 16 lines · 19 tokens per session scan A 74343ef451a0
aat-lint is a command published in the GitHub repository MikkoParkkola/anti-ai-tell (3 stars, last pushed 8d ago), licensed MIT. It adds 19 tokens to every session and 228 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.
Other commands, from other repositories
humanizer
Humanize text — strip AI-writing patterns from pasted text or a file without changing what it says.
slop-chop
Clean AI writing tells from a file or pasted text with slop-chop.
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.
converge
Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.