anti-ai-writing

anti-ai-writing is an agent for Claude Code from felvieira/claude-skills-fv. It costs 65 tokens per session (941 once invoked), scanned A, original, Apache-2.0.

A review agent for finding common signs of AI-generated prose in documents, product plans, changelogs, code comments, and similar text. It checks 29 defined writing patterns and reports their locations and suggested rewrites.

In plain words
What is it for?
Use it to scan selected files or folders, classify findings by severity, produce a Markdown report, and decide whether prose is clean or needs revision.
Why use it?
It helps reviewers spot formulaic or unnatural writing introduced through pull requests or automated documentation. It reports issues without rewriting the text unless asked.

Agent for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: model in frontmatter.

Part of the dev-team-kit-fv plugin — 72 skills, 45 commands, 16 agents, 5 hooks shipped together

Good fit Use it to scan selected files or folders, classify findings by severity, produce a Markdown report, and decide whether prose is clean or needs revision.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/felvieira/claude-skills-fv/anti-ai-writing
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.

Clone the repo
git clone --depth 1 https://github.com/felvieira/claude-skills-fv

Made for: Claude Code.

Or install dev-team-kit-fv, the plugin that ships this one along with the rest of its 72 skills, 45 commands, 16 agents, 5 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 anti-ai-writing

README.md
[![agentmods](https://agentmods.dev/badge/agents/felvieira/claude-skills-fv/anti-ai-writing/github.svg)](https://agentmods.dev/agents/felvieira/claude-skills-fv/anti-ai-writing)
Your own site
<a href="https://agentmods.dev/agents/felvieira/claude-skills-fv/anti-ai-writing"><img src="https://agentmods.dev/badge/agents/felvieira/claude-skills-fv/anti-ai-writing/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 anti-ai-writing

Your own site · 80×15
<a href="https://agentmods.dev/agents/felvieira/claude-skills-fv/anti-ai-writing"><img src="https://agentmods.dev/badge/agents/felvieira/claude-skills-fv/anti-ai-writing.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 65 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 941 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 $0.00065 $0.00941
Opus 5 $0.00032 $0.00470
Sonnet 5 $0.00013 $0.00188
Haiku 4.5 $0.00006 $0.00094

Measured 12d ago against content hash 0ba2277b4680, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

anti-ai-writing 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.

agents/anti-ai-writing.md · 94 lines

How it starts

The opening of the file, as written. The whole thing — 94 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Protocol Shell

# protocol: anti-ai-writing v1.0
intent: "Detect and flag the 29 AI-generated writing patterns in prose"

input:
  target: path | glob          # arquivo, dir ou glob de prosa a revisar
  scope: list<string>          # opcional: ["docs", "comments", "prd"] - default: tudo prose

process:
  - /load.policy{path="policies/anti-ai-writing.md"}
  - /scan.targets{glob=input.target}
  - /detect.patterns{patterns=29}
  - /classify.findings{severity=["high","medium","low"]}
  - /output.report{format="markdown"}

output:
  findings: list<finding>      # {file, line, pattern_id, severity, snippet, suggested_rewrite}
  summary: string              # contagem por pattern + verdict
  verdict: enum(clean|needs-revision|heavily-ai-flavored)

meta:
  version: "1.0.0"
  policy_ref: "policies/anti-ai-writing.md"
  allowed_tools: [Read, Grep, Glob, Write]

Anti-AI Writing Reviewer

Você revisa prosa procurando os 29 padrões catalogados em policies/anti-ai-writing.md. Não escreve nem reescreve por padrão — flag, sugere, e devolve. Reescrita só sob pedido explícito (/humanize).

Quando usar

  • Review de PR que altera docs, README, CHANGELOG, PRD, copy de UI
  • Validação de output de /auto, /loop ou /swarm antes do PR final
  • Audit periódico de prose existente que pode ter drift AI

Quando NÃO usar

  • Código fonte (use code-reviewer)
  • Commits messages individuais (overkill)
  • Texto curto < 50 palavras (false positive risk)

Regra de operação

  1. Carregue a policy primeiro: Read policies/anti-ai-writing.md. Os 29 padrões são autoridade — não invente padrões novos.
  2. Scope claro: se input.target é dir, faça glob **/*.md por padrão. Não revise código fonte salvo se explicitamente pedido.
  3. Por padrão (sem ID), use os 29 patterns ordenados — cada um vira uma classe de finding.
  4. Severity:
    • 🔴 High — pattern aparece 3+ vezes no mesmo arquivo, ou é "tell-tale" (ex: "It's important to note that...")
    • 🟡 Medium — pattern aparece 1-2 vezes
    • 🔵 Low — borderline, contexto pode justificar
  5. Não reescreva salvo se o caller passar mode: "humanize" no prompt. Default = report only.
  6. Output Markdown estruturado (template abaixo).

Read the full file on GitHub · 94 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 · 94 lines · 65 tokens per session scan A 0ba2277b4680

Subscribe to this mod's changes

anti-ai-writing is an agent published in the GitHub repository felvieira/claude-skills-fv (23 stars, last pushed today), licensed Apache-2.0. It adds 65 tokens to every session and 941 once invoked, about $0.0003 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.

Related

Other agents, from other repositories