Borrowing it
Nothing to install: this file belongs to cerul-ai/cerul. 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/cerul-ai/cerul/main/AGENTS.mdgit clone --depth 1 https://github.com/cerul-ai/cerulWrote 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/cerul-ai/cerul/agents-md)<a href="https://agentmods.dev/instructions/cerul-ai/cerul/agents-md"><img src="https://agentmods.dev/badge/instructions/cerul-ai/cerul/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/cerul-ai/cerul/agents-md"><img src="https://agentmods.dev/badge/instructions/cerul-ai/cerul/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 | $0.00573 | $0.00573 |
| Opus 5.5 | $0.00229 | $0.00229 |
| Sonnet 5.5 | $0.00115 | $0.00115 |
| Haiku 4.5 | $0.00057 | $0.00057 |
Grade A, and why
cerul 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 1mo 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.
How it starts
The opening of the file, as written. The whole thing — 52 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Repository guidelines
Communicate with the repository owner in Chinese by default. Public docs, code, identifiers, comments, commit messages, and API fields are English.
This repository is the open-source Cerul video processing core and CLI. DESIGN.md is the implementation baseline. The core owns local media processing, endpoint clients, embedded OCR, annotations, sidecars, and rebuildable indexes. Product UI and hosted services are outside this repository's scope.
Do not add product Web or Desktop UI, cloud Workers, billing-provider or operational admin implementations. Do not commit secrets, user media, indexes, or production exports. Embedded OCR weights and small licensed test fixtures must include provenance and license information.
Core schemas are generated from Rust types. Do not reintroduce retired platform
client schemas such as openapi.json. HTTP and MCP serving are not implemented
and must not be advertised as available.
Use one root Rust crate with a library and a thin CLI. Library code must not parse process arguments, print progress, or terminate the process. Model endpoints are configurable. Sidecars are authoritative; indexes are caches. Preserve integer-microsecond episode time, content-aware invalidation, atomic publication, and zero-model-call index rebuilds.
Verify with cargo fmt --check, cargo clippy --all-targets --locked -- -D warnings,
and cargo test --locked.
Each implementation step needs focused behavioral verification. Release acceptance requires
macOS arm64 and Linux x86_64 builds, real OCR inference, model endpoint smoke
checks, interruption recovery, and sidecar round-trips. Robotics owns hand inference and official LeRobot loader gates.
Do not replace these gates with mock-only or schema-only evidence. See
developer validation for reproducible checks.
Retain LICENSE, Git history, existing tags, and all ffmpeg-vendor-* release
assets. Remove obsolete tracked files explicitly; never delete local worktrees
or untracked user artifacts during repository maintenance.
Use main as the only long-lived branch and codex/ for agent branches.
Public merges go through a ready-for-review PR unless the user explicitly asks
for a draft.
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.
- 1mo ago Changed · +9 tokens per session 6548ef1b1461
- 1mo ago Changed · +11 lines · +119 tokens per session 915fd56d8149
- 1mo ago Changed · -10 tokens per session f0c412fc302b
- 1mo ago Changed · -1 lines · +125 tokens per session 269f4f1ae1fb
- 2mo ago First seen · 42 lines · 330 tokens per session scan A 47470d1c0e20
cerul AGENTS.md is an instructions file published in the GitHub repository cerul-ai/cerul (166 stars, last pushed 15d ago), licensed Apache-2.0. It adds 573 tokens to every session, about $0.0023 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 2026-08-30.
cerul AGENTS.md compared with instructions from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| cerul AGENTS.mdcerul-ai/cerul | Instructions file | 166 | 15d ago | Apache-2.0 | A | 573 | Codex, OpenCode |
| vscode buildNext.instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 9,719 | GitHub Copilot |
| next.js AGENTS.mdvercel/next.js | Instructions file | 143k | today | MIT | A | 7,461 | Codex, OpenCode |
| langchain AGENTS.mdlangchain-ai/langchain | Instructions file | 149k | yesterday | MIT | A | 4,680 | Codex, OpenCode |
| vscode oss-third-party-notices.instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 5,516 | GitHub Copilot |
| vscode copilot-instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 3,093 | GitHub Copilot |
| deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness | Instructions file | 274k | 2d ago | MIT | A | 4,313 | Codex, OpenCode |