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/cerul-ai/cerul/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.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 | $0.00330 | $0.00330 |
| Opus 5 | $0.00165 | $0.00165 |
| Sonnet 5 | $0.00066 | $0.00066 |
| Haiku 4.5 | $0.00033 | $0.00033 |
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 4d 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 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 public Cerul developer surface. Allowed content is limited to sanitized generated OpenAPI, CLI, MCP and agent integrations, examples, public documentation, and release metadata.
Do not add product Web, Desktop, API, Worker, storage, queue, model, prompt, workflow, ranking, evaluation, billing-provider, or operational admin implementation. Do not commit secrets, data, indexes, internal plans, or production exports.
openapi.json and integrations/mcp/src/generated/schema.ts are generated
from the private platform contract. Do not hand-edit them. Contract changes must begin in the
private platform repository and pass the public-surface generator.
Use the existing boundaries:
apps/cliintegrations/mcpintegrations/claude-codeexamplesdocs
MCP maps advertised capabilities and creates normal Cerul Jobs. It must not implement a planner or invent business objects. All clients must support local and cloud through the same contract and a configurable base URL.
Verify changes with:
corepack pnpm install --frozen-lockfile
corepack pnpm check
cargo test --manifest-path apps/cli/Cargo.toml --locked
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.
- 4d 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 (156 stars, last pushed 5d ago), licensed Apache-2.0. It adds 330 tokens to every session, about $0.0016 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 2026-08-30.
Other instructions, from other repositories
screenpipe AGENTS.md
AGENTS.md instructions for screenpipe/screenpipe, covering agents.md, read on demand, source file header, tooling and hot paths.
screenpipe CLAUDE.md
Claude Code instructions for screenpipe/screenpipe: Conventions live in one file so they cannot drift. Read AGENTS.md.
theartifact-cli CLAUDE.md
Claude Code instructions for beast-bruiser/theartifact-cli, covering claude.md, commands, build, run with local backend and one-shot commands.
gorest AGENTS.md
AGENTS.md instructions for pilinux/gorest, covering agents.md, project overview, build and run commands, build and tidy dependencies.
gmgn-skills CLAUDE.md
Claude Code instructions for GMGNAI/gmgn-skills, covering claude.md, critical rule — read this first, project overview, available skills and quick decision guide.
openrouter-mcp-multimodal AGENTS.md
AGENTS.md instructions for stabgan/openrouter-mcp-multimodal, covering agent instructions, before you ship, releasing (read this before publishing), short version and version files (must all match package.json).