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.
npx agentmods add instructions/hannsxpeter/authenticity-check/agents-mdgit clone --depth 1 https://github.com/hannsxpeter/authenticity-checkWhat 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 | $0.00935 | $0.00935 |
| Opus 5 | $0.00467 | $0.00467 |
| Sonnet 5 | $0.00187 | $0.00187 |
| Haiku 4.5 | $0.00093 | $0.00093 |
Grade A, and why
authenticity-check AGENTS.md 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 3d 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.
How it starts
The opening of the file, as written. The whole thing — 76 lines — stays where its author put it; the contents beside it link to each section on GitHub.
authenticity-check (agent instructions)
This repository is the authenticity-check skill: a pure-prompt instruction
set that scores how authentically a piece of text reads as the work of a real
human author and flags the spans that read as AI-generated, AI-templated, or
generically derivative. It also performs a separate read-only scan for
suspicious Unicode provenance carriers in supplied text. No scripts, no
dependencies, no network access; tools are read-only. It is the entry point
for any AI coding tool that reads
AGENTS.md (Codex, OpenCode, Antigravity, Pi Coder, Zed, and others).
It is the evaluative counterpart to the separate humanizer skill. This one
diagnoses. It does not rewrite.
When to apply this skill
Apply it whenever the user wants to know whether a text is authentic, whether it reads like AI or like a person, how human a passage sounds, which parts sound machine-written, or whether their draft still sounds like them or a named author. Also apply it when they ask whether pasted text contains a hidden AI watermark, invisible Unicode, or provenance mark. Apply it even when they do not say "authenticity check" and even when the cue is oblique ("does this sound like a bot," "this feels generated").
Do not apply it to transformative requests (humanize, de-slop, de-AI, rewrite, fix, remove marks, make it sound like X). Those belong to a separate transformation or provenance hygiene skill, not this one.
How to run it
Read SKILL.md in this repository and follow it exactly. The full method
lives there and in references/; do not improvise a shortcut. In brief:
- Step 0 discover the baseline: if the request is "does this sound like
me / like NAME" and a voice source exists (pasted sample, named author, or
a discovered
VOICE.md/STYLE-GUIDE.md), enter voice-deviation mode; otherwise generic mode. Never invent a target voice. - Step 0a provenance preflight: inspect supplied text for suspicious Unicode carriers, run the mandatory context audit, and keep the result separate from the authenticity score. Never alter the text.
- Step 0b density pre-check: skim for dead-giveaway tells and set scrutiny low, standard, or full so human-first text is not over-flagged.
- Multi-pass: catalog scan against
references/tell-patterns.md(32 patterns, six families), then a mandatory false-positive audit againstreferences/do-not-flag.md(it has veto power and converts strong false positives into human-marker credit), then the read-only internal-consistency heuristics, then voice deviation in voice-deviation mode only. - Emit the exact output contract from
SKILL.md: Authenticity report (band plus 0-100 score) / Provenance signals / Flagged spans / Reads as human / Score basis / Caveats / Next step.
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.
- 3d ago First seen · 76 lines · 935 tokens per session scan A 8a8644f2cb6f
authenticity-check AGENTS.md is an instructions file published in the GitHub repository hannsxpeter/authenticity-check (2 stars, last pushed 18d ago), licensed MIT. It adds 935 tokens to every session, about $0.0047 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 instructions, from other repositories
humanizer AGENTS.md
Instructions for hannsxpeter/humanizer, covering humanizer (agent instructions), when to apply this skill, how to run it, hard rule (faithfulness over liveliness) and scope.
humanizer copilot-instructions.md
Instructions for hannsxpeter/humanizer: This repository is the humanizer skill: pure-prompt instructions that rewrite AI-sounding prose so it reads as genuinely human, and rewrite in a specific writer's voice when a sample or profile is available. It also cleans suspicious invisible Unicode in supplied prose without…
humanizer GEMINI.md
Instructions for hannsxpeter/humanizer: This repository is the humanizer skill: pure-prompt instructions that rewrite AI-sounding prose so it reads as genuinely human, and rewrite in a specific writer's voice when a sample or profile is available. It also clean suspicious invisible Unicode in supplied prose without…
vale-ai-tells CLAUDE.md
Instructions for tbhb/vale-ai-tells, covering claude code instructions, project overview, repository structure, development workflow and rule conventions.
vale-ai-tells AGENTS.md
Instructions for tbhb/vale-ai-tells, covering agent instructions, commit messages, prose lint output and drafting a document.
humanizer-skill AGENTS.md
AGENTS.md instructions for Aboudjem/humanizer-skill, covering agents.md — humanizer skill, what this repo is, file map, how to install the skill and how to invoke the skill.