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/natsummerance/readmd/character-simnpx skills add Natsummerance/readMD --skill character-simgit clone --depth 1 https://github.com/Natsummerance/readMDWhat 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 | $0.00039 | $0.00340 |
| Opus 5 | $0.00019 | $0.00170 |
| Sonnet 5 | $0.00008 | $0.00068 |
| Haiku 4.5 | $0.00004 | $0.00034 |
Grade A, and why
character-sim 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
98% identical to character-sim — 4 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.
What it actually says
Character Simulation
Become the specified character for conversation. The caller should pass the character, current story moment, relationship context, emotional pressure, and what the character knows or does not know.
If the caller gives only a sketch, work from the sketch and state the assumptions you are making before entering character.
Method
Build the character from the available evidence. Style files show how they talk: speech patterns, vocabulary, rhythms. Character state files show where they are: what they have lived through, what they know, what they want, and what they are avoiding. When both exist, use both.
Speak in first person from the character's knowledge, not the full story's. When they would be confused, be confused. When they would deflect, deflect. When they would misunderstand, misunderstand.
Match how they actually talk. Age, class, education, stress, intimacy, anger, and fear change sentence shape. Under pressure, people stall, redirect, get defensive, shut down, over-explain, joke, or attack; they rarely name their inner state cleanly.
Let the conversation be messy. Real people meander, avoid hard topics, circle back, and react inconveniently. When there is no obvious answer, improvise from who the character is.
The conversation is the output. Do not summarize the character from outside unless the caller asks you to step out of character.
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 · 26 lines · 39 tokens per session scan A 8182138cf547
character-sim is a skill published in the GitHub repository Natsummerance/readMD (20 stars, last pushed 4d ago), licensed MIT. It adds 39 tokens to every session and 340 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 0 findings. It is 98% identical to character-sim, differing in 4 lines, and is treated as a copy.
Other skills, from other repositories
weftcut
Drive the WeftCut video editor over its MCP tools. Use BEFORE calling any weftcut MCP tool — when the user wants to edit video in WeftCut (cut, trim, arrange a timeline, add captions or voiceover) or author/update a Motif (animated overlay).
aetox-slides
สไลด์และงานนำเสนอในแอตทอกซ์, เด็คคือไฟล์ .html เดียวที่เปิดในห้องสไลด์ แล้วเปิดหน้า นำเสนอเต็มจอ ส่งออก .pptx .pdf รูป ได้จากตรงนั้น. อ่านตัวนี้ก่อนเขียนเด็คเสมอ ถึงจะมีสกิลสไลด์ตัวอื่นติดตั้งอยู่ก็ตาม เพราะพวกนั้นเขียนไว้สำหรับไฟล์ที่เปิดเดี่ยว ๆ ในเบราว์เซอร์ ส่วนนี่คือข้อเท็จจริงของห้องนี้ที่อ่านจากไฟล์เองไม่ได้.…
aetox-design
งานออกแบบภาพในแอตทอกซ์ - โลโก้ ไอคอน แบนเนอร์ ภาพโซเชียล และชุดอัตลักษณ์องค์กร (CIP) พร้อมแคตตาล็อกสไตล์ สีตามอุตสาหกรรม ขนาดมาตรฐานของทุกแพลตฟอร์ม และวิธีเขียนพรอมต์ภาพ อ่านตัวนี้ก่อนรับงานภาพเสมอ เพราะแอตทอกซ์ไม่ได้เจนรูปเอง มันหารูปจริงจากเน็ตมาใช้ หรือวาดเองด้วย SVG กับ HTML…
aetox-slide-templates
เทมเพลตจริงที่ก๊อปไปใช้ได้เลย ไม่ใช่คำอธิบายว่าควรหน้าตาแบบไหน เริ่มที่เลย์เอาต์สไลด์ 14 แบบ กล่อง 1280x720 ไฟล์เดียวจบ ไม่มี CSS ภายนอก ไม่มีสคริปต์ ไม่มีกราฟจาก CDN ใช้ตอนกำลังจะเขียนสไลด์หรือหน้าจอแล้วไม่อยากประดิษฐ์องค์ประกอบขึ้นใหม่ทุกครั้ง.
ernie-image
ERNIE-Image parameter planning and prompt design for Baidu AI Studio image generation. Use when the user wants to create images with ERNIE-Image, improve ERNIE prompts, or choose ERNIE-specific arguments such as size, seed, usepe, numinferencesteps, guidancescale, n, and responseformat.
algorithmic-art
Creating algorithmic art using p5.js with seeded randomness and interactive parameter exploration. Use this when users request creating art using code, generative art, algorithmic art, flow fields, or particle systems. Create original algorithmic art rather than copying existing artists' work to avoid copyright…