Borrowing it
Nothing to install: this file belongs to songod0906/open-video-guide. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/songod0906/open-video-guide/main/AGENTS.mdgit clone --depth 1 https://github.com/songod0906/open-video-guideWrote 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/songod0906/open-video-guide/agents-md)<a href="https://agentmods.dev/instructions/songod0906/open-video-guide/agents-md"><img src="https://agentmods.dev/badge/instructions/songod0906/open-video-guide/agents-md/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/instructions/songod0906/open-video-guide/agents-md"><img src="https://agentmods.dev/badge/instructions/songod0906/open-video-guide/agents-md.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00406 | $0.00406 |
| Opus 5.5 | $0.00162 | $0.00162 |
| Sonnet 5.5 | $0.00081 | $0.00081 |
| Haiku 4.5 | $0.00041 | $0.00041 |
Grade A, and why
open-video-guide AGENTS.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 2mo 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
Repository Instructions
These instructions apply to all files in this repository.
Language
Write technical text in ASD-STE100 Simplified Technical English, Issue 9.
Use the project terms in docs/TERMINOLOGY.md.
Use active voice. Use one term for one meaning. Use a maximum of 20 words in a procedural sentence. Use a maximum of 25 words in a descriptive sentence. Put only one instruction in each procedural sentence. Do not use a technical abbreviation before you define it.
Do not change legal license text or exact source text. Do not claim full compliance from an automated language check.
Product truth
Describe the product as local-first and open source. Do not describe the product as a free hosted service. Do not claim that the video pipeline works before tests prove the claim. Do not claim support for a platform before an integration test passes.
Scope
Keep the core engine independent from user interfaces and AI clients. Put platform code in an adapter. Keep model weights, input videos, screenshots, logs, and generated guides out of Git.
Quality
Run these checks before a commit:
python scripts/check_ste.py
python -m pytest
python -m ruff check .
Add an architecture decision record for a change to a major technical decision. Add test evidence for each product capability. Update the risk register when a change adds a material risk.
Shared project handoff
Run this command at the start of each work session:
python scripts/project_context.py
Read .project-context/PROJECT_CONTEXT.md before you plan work.
Use docs/PROJECT_STATE.json as the semantic project record.
Update docs/PROJECT_STATE.json when capability, priority, status, or limits change.
Do not store conversation transcripts in the project state.
Run this command before a handoff:
make handoff
Give the next agent the repository path. The next agent must refresh the project context before work.
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.
- 2mo ago First seen · 69 lines · 406 tokens per session scan A f633cbe4970b
open-video-guide AGENTS.md is an instructions file published in the GitHub repository songod0906/open-video-guide (0 stars, last pushed 19d ago), licensed Apache-2.0. It adds 406 tokens to every session, about $0.0016 per session on Opus 5.5. 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.
open-video-guide AGENTS.md compared with instructions from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| open-video-guide AGENTS.mdsongod0906/open-video-guide | Instructions file | 0 | 19d ago | Apache-2.0 | A | 406 | Codex, OpenCode |
| vscode buildNext.instructions.mdmicrosoft/vscode | Instructions file | 195k | today | MIT | A | 9,719 | GitHub Copilot |
| next.js AGENTS.mdvercel/next.js | Instructions file | 143k | today | MIT | A | 7,461 | Codex, OpenCode |
| vscode oss-third-party-notices.instructions.mdmicrosoft/vscode | Instructions file | 195k | today | MIT | A | 5,685 | GitHub Copilot |
| langchain AGENTS.mdlangchain-ai/langchain | Instructions file | 149k | yesterday | MIT | A | 4,680 | Codex, OpenCode |
| vscode copilot-instructions.mdmicrosoft/vscode | Instructions file | 195k | today | MIT | A | 3,093 | GitHub Copilot |
| vscode model-prompts.instructions.mdmicrosoft/vscode | Instructions file | 195k | today | MIT | A | 2,022 | GitHub Copilot |