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 instructions/shihabshahrier/manim-coding-skill/copilot-instructionsgit clone --depth 1 https://github.com/shihabshahrier/manim-coding-skillWrote 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/instructions/shihabshahrier/manim-coding-skill/copilot-instructions)<a href="https://agentmods.dev/instructions/shihabshahrier/manim-coding-skill/copilot-instructions"><img src="https://agentmods.dev/badge/instructions/shihabshahrier/manim-coding-skill/copilot-instructions.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 | $0.00257 | $0.00257 |
| Opus 5 | $0.00129 | $0.00129 |
| Sonnet 5 | $0.00051 | $0.00051 |
| Haiku 4.5 | $0.00026 | $0.00026 |
Grade A, and why
manim-coding-skill copilot-instructions.md 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 5d 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.
What it actually says
When user says /test-manim or asks to create a STEM animation, follow the skill at skills/test-manim/SKILL.md.
Invocation: /test-manim "topic" [--duration 30|60|90|120] [--model name]
5 phases (never skip, never reorder):
- Scaffold project:
manim-{model}/{topic_slug}/scenes/ output/ assets/ SCENE_PLAN.md render.sh merge.sh - Write SCENE_PLAN.md (narrative arc: hook → build → resolution) before any code
- Batch-write all
scenes/chunk_NN_name.pyfiles using ManimGL - Run render.sh (manimgl, -w -q --hd, per chunk)
- Run merge.sh (ffmpeg concat) → final video + report
ManimGL only — from manimlib import *, ShowCreation, TexText, Tex. Never ManimCE names (Create, Text, MathTex).
Load skills/test-manim/references/manim-gl-api.md when writing scene code.
Load skills/test-manim/references/storytelling.md when planning narrative.
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.
- 5d ago First seen · 16 lines · 257 tokens per session scan A 27c262fa48b5
manim-coding-skill copilot-instructions.md is an instructions file published in the GitHub repository shihabshahrier/manim-coding-skill (2 stars, last pushed 2mo ago), licensed MIT. It adds 257 tokens to every session, about $0.0013 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 2026-08-31.
Other instructions, from other repositories
aurora-agent AGENTS.md
AGENTS.md instructions for AURORA-NEURO/aurora-agent, covering aurora agent, what we can never compromise on, 1. honest labelling is the product, 2. invariants belong in the type system, not in comments and 3. determinism, byte for byte.
Eureka GEMINI.md
Instructions for jeonnoin-alt/Eureka, a project described as: Scientific TDD for AI coding agents: pre-registration before data, claims audit before submission, external novelty gate, reproducibility. Claude Code + 4 platforms.
daily_arxiv_digest CLAUDE.md
Instructions for yang3kc/daily_arxiv_digest, a project described as: Daily digest of interesting arXiv papers — an unattended LLM pipeline for cron, plus a zero-dependency agent skill your AI agent runs itself.
douchebag CLAUDE.md
Claude Code instructions for Stronger197/douchebag, covering claude.md — douchebag, what douchebag is, two key design decisions, 1. levels are scope, not strength and repo structure and what owns what.
douchebag AGENTS.md
AGENTS.md instructions for Stronger197/douchebag: @./skills/douchebag/SKILL.md @./skills/douchebag-commit/SKILL.md @./skills/douchebag-review/SKILL.md @./skills/douchebag-help/SKILL.md.
douchebag GEMINI.md
Gemini CLI instructions for Stronger197/douchebag: @./skills/douchebag/SKILL.md @./skills/douchebag-commit/SKILL.md @./skills/douchebag-review/SKILL.md @./skills/douchebag-help/SKILL.md.