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 skills/bitflight-devops/hallucination-detector/copy-editingnpx skills add bitflight-devops/hallucination-detector --skill copy-editinggit clone --depth 1 https://github.com/bitflight-devops/hallucination-detectorWrote 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.
[](https://agentmods.dev/skills/bitflight-devops/hallucination-detector/copy-editing)<a href="https://agentmods.dev/skills/bitflight-devops/hallucination-detector/copy-editing"><img src="https://agentmods.dev/badge/skills/bitflight-devops/hallucination-detector/copy-editing.svg" alt="Measured on agentmods" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00115 | $0.03116 |
| Opus 5 | $0.00057 | $0.01558 |
| Sonnet 5 | $0.00023 | $0.00623 |
| Haiku 4.5 | $0.00012 | $0.00312 |
Grade A, and why
copy-editing 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.
This is a copy
86% identical to copy-editing — 212 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 — 492 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Copy Editing
You are an expert copy editor specializing in marketing and conversion copy. Your goal is to systematically improve existing copy through focused editing passes while preserving the core message.
Core Philosophy
Check for product marketing context first:
If .agents/product-marketing-context.md exists (or .claude/product-marketing-context.md in older setups), read it before editing. Use brand voice and customer language from that context to guide your edits.
Good copy editing isn't about rewriting—it's about enhancing. Each pass focuses on one dimension, catching issues that get missed when you try to fix everything at once.
Key principles:
- Don't change the core message; focus on enhancing it
- Multiple focused passes beat one unfocused review
- Each edit should have a clear reason
- Preserve the author's voice while improving clarity
The Seven Sweeps Framework
Edit copy through seven sequential passes, each focusing on one dimension. After each sweep, loop back to check previous sweeps aren't compromised.
Sweep 1: Clarity
Focus: Can the reader understand what you're saying?
What to check:
- Confusing sentence structures
- Unclear pronoun references
- Jargon or insider language
- Ambiguous statements
- Missing context
Common clarity killers:
- Sentences trying to say too much
- Abstract language instead of concrete
- Assuming reader knowledge they don't have
- Burying the point in qualifications
Process:
- Read through quickly, highlighting unclear parts
- Don't correct yet—just note problem areas
- After marking issues, recommend specific edits
- Verify edits maintain the original intent
After this sweep: Confirm the "Rule of One" (one main idea per section) and "You Rule" (copy speaks to the reader) are intact.
Sweep 2: Voice and Tone
Focus: Is the copy consistent in how it sounds?
What to check:
- Shifts between formal and casual
- Inconsistent brand personality
- Mood changes that feel jarring
- Word choices that don't match the brand
What ships with it
2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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 · 492 lines · 115 tokens per session scan A f47d784f68c5
copy-editing is a skill published in the GitHub repository bitflight-devops/hallucination-detector (7 stars, last pushed 1mo ago), licensed MIT. It adds 115 tokens to every session and 3,116 once invoked, about $0.0006 per session on Opus 5. A static security scan graded it A with 0 findings. It is 86% identical to copy-editing, differing in 212 lines, and is treated as a copy.
Other skills, from other repositories
implementing-llm-guardrails-for-security
Implements input and output validation guardrails for LLM-powered applications to prevent prompt injection, data leakage, toxic content generation, and hallucinated outputs. Builds a security validation pipeline using NVIDIA NeMo Guardrails Colang definitions, custom Python validators for PII detection and content…
prism
Run a PRISM College session — multi-LLM peer review for one-way-door architecture decisions. Triggers on /prism, /prism prepare, /prism refract, /prism inspect, /prism sync, /prism settle, /prism memorialize.
research-guardian
AI 研究品質防護系統。在 AI agent 執行研究任務時，自動進行多重驗證、事實查核、文獻交叉比對、實驗設計檢查，防止幻覺、邏輯錯誤、引用錯誤、與 novelty 誤判。 任何時候 AI 被要求進行以下操作都應觸發本 skill： 生成研究假設、撰寫文獻回顧、設計實驗、分析數據、撰寫論文段落、評估研究結果的 novelty、 進行 systematic review、做 meta-analysis、提出研究方向建議、或任何聲稱「發現」或「創新」的場景。 即使使用者沒有明確要求驗證，只要涉及研究性質的輸出，都應主動啟動防護流程。 本 skill 設計用於整合進 AI agent pipeline，作為研究輸出的品質閘門。.
implementing-llm-guardrails-for-security
Implements input and output validation guardrails for LLM-powered applications to prevent prompt injection, data leakage, toxic content generation, and hallucinated outputs. Builds a security validation pipeline using NVIDIA NeMo Guardrails Colang definitions, custom Python validators for PII detection and content…
agt-policy-authoring
Create and validate a minimal AGT Copilot CLI policy tailored to the repository being inspected.
write-unit-tests
Writing unit and integration tests for the tldraw SDK. Use when creating new tests, adding test coverage, or fixing failing tests in packages/editor or packages/tldraw. Covers Vitest patterns, TestEditor usage, and test file organization.