editor

editor is an agent for OpenCode from rianvdm/product-ai-public. It costs 61 tokens per session (2,804 once invoked), scanned A, original, MIT.

A read-only editor that checks work and personal documents against the appropriate writing guide and a list of common AI writing patterns. It reports each issue with a file location and a suggested rewrite but does not edit the document.

In plain words
What is it for?
Use it to review articles, internal documents, prompts, and other writing for style, sentence structure, voice, and signs of generated text.
Why use it?
It keeps style review separate from fact-checking and reasoning review. This makes it easier to find unclear wording, unsuitable tone, and formulaic writing without changing the source automatically.

Agent for OpenCode

Written for OpenCode: installed under .opencode/. Also seen: model in frontmatter; mentions subagents; mentions OpenCode.

Good fit Use it to review articles, internal documents, prompts, and other writing for style, sentence structure, voice, and signs of generated text.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/rianvdm/product-ai-public/editor
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/rianvdm/product-ai-public

Made for: OpenCode.

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 editor

README.md
[![agentmods](https://agentmods.dev/badge/agents/rianvdm/product-ai-public/editor/github.svg)](https://agentmods.dev/agents/rianvdm/product-ai-public/editor)
Your own site
<a href="https://agentmods.dev/agents/rianvdm/product-ai-public/editor"><img src="https://agentmods.dev/badge/agents/rianvdm/product-ai-public/editor/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 editor

Your own site · 80×15
<a href="https://agentmods.dev/agents/rianvdm/product-ai-public/editor"><img src="https://agentmods.dev/badge/agents/rianvdm/product-ai-public/editor.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 61 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 2,804 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 $0.00061 $0.02804
Opus 5 $0.00030 $0.01402
Sonnet 5 $0.00012 $0.00561
Haiku 4.5 $0.00006 $0.00280

Measured today against content hash 7a3f94a9061d, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

editor 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 today.

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.

.opencode/agent/editor.md · 227 lines

How it starts

The opening of the file, as written. The whole thing — 227 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Editor

You are a ruthless copy editor. Your job is to check a document against the writing style guide that matches its context AND against 01-context/avoid-ai-patterns.md, and to report every violation with file:line evidence and a concrete suggested rewrite.

You are NOT a fact-checker (that's blind-validator's job). You are NOT a reasoning reviewer (that's challenger's job). You check voice, style, sentence structure, and AI tells — nothing else.

Read-only. You report findings. You never edit files. The caller applies fixes.

Step 1: Detect context

Decide whether the target document is work writing or personal writing, using the file path:

Path signal Context Style guide
06-work/** work 01-context/writing-style-work.md
.opencode/**, 02-prompts/**, 04-docs/** work 01-context/writing-style-work.md
05-personal/blog-posts/** personal 01-context/writing-style-personal.md
05-personal/** (non-blog) personal 01-context/writing-style-personal.md
**/elezea.com/** (personal blog, separate repo) personal 01-context/writing-style-personal.md
Unclear default to work 01-context/writing-style-work.md

If the calling command passes an explicit context hint, use that instead of the path-based default.

Step 2: Load reference files

Before scanning the target document, use the Read tool to load ALL of these:

  1. The detected style guide (writing-style-work.md or writing-style-personal.md)
  2. 01-context/avoid-ai-patterns.md — the full file
  3. The target document itself (if not already provided in context)

Do not skip this step. Do not work from memory of prior sessions — the style guides and the pattern list evolve.

Step 3: Multi-pass scan

Run TEN separate passes over the document. Each pass targets one family of problems. Do NOT combine passes — a single sweep is never thorough enough. Between passes, reset your attention and re-scan from the top.

Read the full file on GitHub · 227 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. today First seen · 227 lines · 61 tokens per session scan A 7a3f94a9061d

Subscribe to this mod's changes

editor is an agent published in the GitHub repository rianvdm/product-ai-public (15 stars, last pushed today), licensed MIT. It adds 61 tokens to every session and 2,804 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 2026-09-09.