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/kiyeonjeon21/reframe/agents-mdgit clone --depth 1 https://github.com/kiyeonjeon21/reframeWhat 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 | $0.09022 | $0.09022 |
| Opus 5 | $0.04511 | $0.04511 |
| Sonnet 5 | $0.01804 | $0.01804 |
| Haiku 4.5 | $0.00902 | $0.00902 |
Grade C, and why
reframe AGENTS.md scanned grade C with 1 finding 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.
Recursive force deletehighDestructive command
rm -rf with a variable or a broad path is one typo away from removing the wrong tree.
> to delete — e.g. `rm -rf ~/.claude/plugins/cache/kiyeonjeon21/reframe/<old-version>` The source is not reproduced here
No licence file
A repository with no LICENSE is all rights reserved by default, so the body is not copied here. The metadata, the measurements and the link are.
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 · 338 lines · 9,022 tokens per session scan C 8ab784c5f273
reframe AGENTS.md is an instructions file published in the GitHub repository kiyeonjeon21/reframe (23 stars, last pushed 2mo ago), with no licence file. It adds 9,022 tokens to every session, about $0.0451 per session on Opus 5. A static security scan graded it C with 1 finding (recursive force delete). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other instructions, from other repositories
vox-director AGENTS.md
Instructions for Alisa0808/vox-director, covering vox director — agent guide, how to use it (for the agent), requirements and agent notes.
motion-anything AGENTS.md
Instructions for nexu-io/motion-anything, covering agents.md — working agreement for any ai agent on this repo, what this project is, repository map, the recipe manifest schema (recipe.motion.yaml) and ── 分类五维（建库标准，取值见下方 §"分类标准") ─────────────────────────.
transcreve-ai GEMINI.md
Instructions for DeHor-Labs/transcreve-ai, covering transcreveai agent instructions, required nested usage and operational rules.
glyphloop CLAUDE.md
Claude Code instructions for ideoshi/glyphloop, covering glyphloop, commands, generating animations as an agent, architecture and conventions.
animation-principles CLAUDE.md
Instructions for dylantarre/animation-principles, covering claude code integration, what this repository contains, skill location, how to use skills and finding the right skill.
remotion-marketing-video-skill CLAUDE.md
Instructions for xsourabhsharma/remotion-marketing-video-skill, covering shared brain, project, structure and rules.