Borrowing it
Nothing to install: this file belongs to kryptobaseddev/cleo. 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/kryptobaseddev/cleo/main/AGENTS.mdgit clone --depth 1 https://github.com/kryptobaseddev/cleoWrote 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/kryptobaseddev/cleo/agents-md)<a href="https://agentmods.dev/instructions/kryptobaseddev/cleo/agents-md"><img src="https://agentmods.dev/badge/instructions/kryptobaseddev/cleo/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/kryptobaseddev/cleo/agents-md"><img src="https://agentmods.dev/badge/instructions/kryptobaseddev/cleo/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 | $0.10245 | $0.10245 |
| Opus 5.5 | $0.04098 | $0.04098 |
| Sonnet 5.5 | $0.02049 | $0.02049 |
| Haiku 4.5 | $0.01025 | $0.01025 |
Grade A, and why
cleo 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 today.
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 — 292 lines — stays where its author put it; the contents beside it link to each section on GitHub.
@~/.agents/AGENTS.md @.cleo/project-context.json
Run: cleo memory digest
CLEO Project Rules (MANDATORY)
Rules below are NON-NEGOTIABLE for this repo. Protocol surface (sessions, tasks, memory, orchestration, evidence gates) is in CLEO-INJECTION.md and not duplicated here.
Instruction architecture
Protocol source: packages/core/templates/CLEO-INJECTION.md (installed to the CLEO templates dir; ~/.agents/AGENTS.md points there). This file owns repo rules; CAAMP owns managed blocks; provider adapters own delivery; packages/skills/skills/ ct-* skills own workflow detail. A literal @path is not proof a file loaded — unverified delivery needs a self-contained managed bootstrap. Keep user text outside managed blocks unchanged. When changing instruction behavior, check packaged, installed, global, project, provider, skill, bridge and spawn surfaces, run command-existence and delivery regressions, and mark live Codex/Claude/Kimi evaluations unverified unless run.
Code Quality
Type safety (zero tolerance). NEVER any, unknown as a shortcut, as unknown as X casting chains, or inline/mocked types. Use packages/contracts/src/ — build new contracts if genuinely missing.
DRY + SOLID. Read existing code first. Search for existing utilities before writing new ones. Centralize shared logic into lib modules. Match existing style, naming, and structure. Keep imports sorted (biome enforces).
Documentation. Add TSDoc (/** ... */) on ALL exported functions, classes, types, constants. Update existing docs — never create new ones unless necessary. Validate with forge-ts when available.
Anti-patterns (instant rejection). Claiming "tests pass" without running them. Workarounds instead of root-cause fixes. Skipping biome/lint. Creating new files when extension would do. catch (err: unknown). console.log in production. Imports without circular-dep check. Modifying test expectations to match broken code.
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.
- today Changed · +2 lines · +213 tokens per session 61c606008a02
- 11d ago Changed 5eb04bdc35c0
- 13d ago Changed 166e09fd43c5
- 15d ago Changed · +37 tokens per session 4dc25f75bc90
- 18d ago Changed · +43 tokens per session 106228dfcec2
- 21d ago Changed · +9 tokens per session 993c0ca34be6
- 22d ago Changed · -1 lines · +29 tokens per session 28bec4186f47
- 23d ago Changed · +164 tokens per session 542563ea9834
- 24d ago Changed · +3 lines · +420 tokens per session 0d882911ae8a
- 25d ago First seen · 288 lines · 9,330 tokens per session scan A 9e1d1d781089
cleo AGENTS.md is an instructions file published in the GitHub repository kryptobaseddev/cleo (159 stars, last pushed today), licensed MIT. It adds 10,245 tokens to every session, about $0.0410 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 2026-09-03.
Other instructions, from other repositories
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, cache eligibility and rollout and applying the notice (cutover).
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
vscode copilot-instructions.md
Copilot instructions for microsoft/vscode, covering vs code copilot instructions, project overview, root folders, core architecture (src/ folder) and built-in extensions (extensions/ folder).
vscode model-prompts.instructions.md
Model-specific prompt authoring and registry guidelines.