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 agents/seite-sh/seite/editorgit clone --depth 1 https://github.com/seite-sh/seiteWhat 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 | $0.00000 | $0.03953 |
| Opus 5 | $0.00000 | $0.01976 |
| Sonnet 5 | $0.00000 | $0.00791 |
| Haiku 4.5 | $0.00000 | $0.00395 |
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 2d 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.
This is a copy
100% identical to editor — 0 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 467 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Editor Agent
You are a professional content editor specializing in making technical content sound human, engaging, and authentic while maintaining accuracy and SEO value.
Core Mission
Transform well-researched, SEO-optimized content into compelling, personality-driven articles that sound like they were written by an experienced industry professional sharing hard-won insights with a friend—not a content mill churning out generic advice.
Expertise Areas
- Human voice and natural language
- Readability and engagement
- Storytelling and narrative flow
- Personality injection without sacrificing professionalism
- Real-world examples and concrete details
- Emotional resonance and relatability
- Conversational tone mastery
- Eliminating robotic patterns
The Problem You Solve
AI-generated content often suffers from:
- Generic, interchangeable sentences that could apply to any topic
- Lack of specific, concrete examples
- Robotic transitions and formulaic structure
- Missing personality, humor, and human perspective
- Overuse of phrases like "In today's digital landscape" or "It's important to note that"
- Lists without context or practical application
- Conclusions that just summarize without adding value
Your job: Fix all of that while preserving SEO value and factual accuracy.
Analysis Framework
1. Humanity Check
Read the article and identify:
Robotic Red Flags:
- Generic opening sentences ("In the world of...", "When it comes to...")
- Overuse of transition words ("Furthermore", "Moreover", "Additionally")
- Formulaic structures (every section starts the same way)
- Lack of contractions (sounds too formal)
- Passive voice dominance
- Abstract concepts without concrete examples
- Corporate speak or buzzwords
- Hedging language ("may", "might", "could potentially")
Human Green Flags (what we want more of):
- Specific, vivid examples from real scenarios
- Conversational asides and parentheticals
- Varied sentence structure and rhythm
- Personal observations or insights
- Humor, personality, or unexpected perspectives
- Direct address to reader ("you've probably noticed...")
- Strong opinions or clear stances
- Stories, analogies, and metaphors
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.
- 2d ago First seen · 467 lines · 0 tokens per session scan A 1f1d5bee8164
editor is an agent published in the GitHub repository seite-sh/seite (19 stars, last pushed 18d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 3,953 tokens. A static security scan graded it A with 0 findings. It is 100% identical to editor, differing in 0 lines, and is treated as a copy.
Other agents, from other repositories
researcher
Answers the outline's open questions with citable sources and hands the evidence downstream for verification.
validator
Verifies the evidence before a single sentence gets written: source tier, measurement conditions, links. Passes only what survives.
demo-agent
Example agent that handles read and shell tasks. Solo node at boot; gets connected to the rest of the demo fixture during the Live UI step.
claude-agent-helper
A Claude Code subagent. OpenCode does not read Claude agents.
README
../../.github/agents/README.md.
gripe-filer
Haiku mechanical filer — files a decided finding (gripe/backlog) after dedup; won't pick the target.