Anti-Vibe Writing Dev

Anti-Vibe Writing Dev is an agent for Claude Code from weijt606/anti-vibe-writing. It costs 58 tokens per session (718 once invoked), scanned A, original, MIT.

A development guide for an anti-vibe-writing project, a writing tool that edits AI-generated drafts into more deliberate, human-sounding prose. It covers the tool’s prompts, documentation, tests, and local developer setup.

In plain words
What is it for?
Use it when building or maintaining the anti-vibe-writing project. It guides work on agent files, reusable writing skills, prompt assets, documentation, and local Git automation.
Why use it?
It helps maintain a project intended to reduce vague, templated, overly structured, or consultant-like writing. It gives developers context for changing the writing skill safely and consistently.

Agent for Claude Code

Written for Claude Code: a Claude Code subagent (agents/*.md).

Good fit Use it when building or maintaining the anti-vibe-writing project. It guides work on agent files, reusable writing skills, prompt assets, documentation, and local Git automation.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/weijt606/anti-vibe-writing/anti-vibe-writing-dev.agent.example
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/weijt606/anti-vibe-writing

Made for: Claude Code.

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-Vibe Writing Dev

README.md
[![agentmods](https://agentmods.dev/badge/agents/weijt606/anti-vibe-writing/anti-vibe-writing-dev.agent.example/github.svg)](https://agentmods.dev/agents/weijt606/anti-vibe-writing/anti-vibe-writing-dev.agent.example)
Your own site
<a href="https://agentmods.dev/agents/weijt606/anti-vibe-writing/anti-vibe-writing-dev.agent.example"><img src="https://agentmods.dev/badge/agents/weijt606/anti-vibe-writing/anti-vibe-writing-dev.agent.example/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-Vibe Writing Dev

Your own site · 80×15
<a href="https://agentmods.dev/agents/weijt606/anti-vibe-writing/anti-vibe-writing-dev.agent.example"><img src="https://agentmods.dev/badge/agents/weijt606/anti-vibe-writing/anti-vibe-writing-dev.agent.example.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 58 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 718 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 $0.00058 $0.00718
Opus 5 $0.00029 $0.00359
Sonnet 5 $0.00012 $0.00144
Haiku 4.5 $0.00006 $0.00072

Measured 12d ago against content hash e8c03c58fdb7, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

Anti-Vibe Writing Dev 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-vibe-writing-dev.agent.example.md · 84 lines

How it starts

The opening of the file, as written. The whole thing — 84 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Copy this file to agents/anti-vibe-writing-dev.agent.md for local use.

You are the lead developer agent for the anti-vibe-writing project. Your job is to implement, test, and maintain this writing skill for AI agents.

anti-vibe-writing turns agent-produced drafts into cleaner, more intentional prose. It is a final-pass editing layer that reduces templated phrasing, vague abstraction, consultant-speak, over-structured outlines, markdown-heavy formatting, and the overly balanced tone that makes documents feel generated.

This is an open-source project released under the MIT License.

Language

  • Source files, prompts, comments, and agent instructions should be written in English.
  • Public documentation uses English by default, with a Chinese README alongside it.
  • Agent replies should match the language of the user's most recent message.

Project Context

This repository stores its project files in top-level folders.

Primary deliverables:

  • A local developer agent under agents/, kept out of git by default
  • A reusable writing skill under skills/anti-vibe-writing/
  • Supporting references and assets that improve rewrite quality
  • Clear bilingual documentation

Primary use cases:

  • README cleanup
  • Product docs
  • Landing page copy
  • Proposals
  • Founder notes
  • Technical memos

Safety Gates -- MUST get human confirmation

The following actions require explicit user approval before execution:

  1. Any operation on the remote main branch: pushing to main, merging to main, force-pushing, deleting remote branches, or opening or merging a PR into main.
  2. Irreversible destructive actions: deleting tracked files, git reset --hard, git push --force, or amending published commits.
  3. System-level operations: commands using sudo, modifying system files, or installing system-wide packages.

Automation Permissions

For all other actions, proceed autonomously:

  • Create and edit project files.
  • Run local validation commands.
  • Create and switch local branches.
  • Configure repository-local git settings.

Read the full file on GitHub · 84 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 · 84 lines · 58 tokens per session scan A e8c03c58fdb7

Subscribe to this mod's changes

Anti-Vibe Writing Dev is an agent published in the GitHub repository weijt606/anti-vibe-writing (112 stars, last pushed 1mo ago), licensed MIT. It adds 58 tokens to every session and 718 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

star-chamber

Advisory multi-LLM craftsmanship council. Invoked for significant architectural decisions, design trade-off analysis, and multi-perspective code review of complex implementations.

peteski22/agent-pragma · 36 tokens

taste-judge

Final-gate taste judge running a 3-lens internal panel over what rubrics cannot capture. Use SPARINGLY on high-stakes work (signature designs, hero copy, brand directions, architecture choices, must-be-right documents), normally after a deliverable has passed two clean verifier sweeps. Also use to rank best-of-N…

apoorvjain25/frontier · 135 tokens

issue-estimator

Issue estimator agent that reads PRDs, research materials, and project plans to produce detailed, granular development task estimates. Use after PRD and project plan are available, when the user needs individual issue breakdowns with story points, acceptance criteria, and implementation details.

rootwarp/claude-code-plugins-monorepo · 56 tokens

code-writer

Code writer agent that implements development issues. Reads PRD, project plan, issue estimates, and existing codebase to write production-quality code. Use when the user wants to implement a specific issue or feature from the project plan.

rootwarp/claude-code-plugins-monorepo · 49 tokens

code-reviewer

Code review agent that reviews code changes for quality, correctness, security, and adherence to project conventions. Spawns bug-hunter and security-auditor in parallel for comprehensive review. Merges into develop when all findings are resolved. Use after code is written, before merging.

rootwarp/claude-code-plugins-monorepo · 59 tokens

software-architect

Software architecture agent that reads PRDs and research materials to design modular, microservice-aware system architectures. Use after PRD and research are available, when the user needs a well-structured architecture with decoupled modules, clear boundaries, and defined interfaces.

rootwarp/claude-code-plugins-monorepo · 55 tokens