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/flashml-org/freetoken/agents-mdgit clone --depth 1 https://github.com/FlashML-org/FreeTokenWrote 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/flashml-org/freetoken/agents-md)<a href="https://agentmods.dev/instructions/flashml-org/freetoken/agents-md"><img src="https://agentmods.dev/badge/instructions/flashml-org/freetoken/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 | $0.00970 | $0.00970 |
| Opus 5 | $0.00485 | $0.00485 |
| Sonnet 5 | $0.00194 | $0.00194 |
| Haiku 4.5 | $0.00097 | $0.00097 |
Grade A, and why
FreeToken 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 — 72 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Instructions for AI coding agents
Read CONTRIBUTING.md first. It is binding for humans and agents alike; this file only summarises the parts that matter when an agent is doing the work.
AI policy
AI-assisted code is welcome. Submitting code the contributor does not understand is not. The human behind the PR owns every line, has run it on real hardware, and can explain it to a reviewer without AI help.
Agents must not:
- Run
git push,gh pr create,gh pr comment, orgh issue createon the user's behalf. - Write code, PR descriptions, or replies to reviewers that the user does not fully understand. The user must be able to explain and defend every line without AI help.
- Report tests or benchmarks as run when they were not.
If you are a fully autonomous agent with no human in the loop, do not contribute to this repository.
Repository layout
The main subsystems:
python/freetoken/ the engine, installed as the `freetoken` package with the `ft` CLI
server/ OpenAI / Anthropic / Responses HTTP APIs, streaming, tool-call parsers
scheduler/ chunked prefill, batching, cache manager
kvcache/ paged KV pools and the radix prefix caches
moe/ expert offload cache, CPU / GPU / hybrid MoE backends, quantized experts
models/ model registry and per-architecture loaders
kernel/ CUDA / Triton kernels, JIT cache, C++ extensions (`csrc/`)
layers/, attention/ fused ops and attention backends
engine/ cache budget planning and config resolution
checkpoint/ HF -> FTW fast-load conversion
tests/ mirrors python/freetoken/ by subsystem, see tests/README.md
benchmarks/ end-to-end and micro benchmarks, see benchmarks/README.md
docs/ install, quickstart, CLI and model docs
freetoken-kernel-cache/ companion wheel of prebuilt kernels, see its README
scripts/ wheel build and release scripts
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 First seen · 72 lines · 970 tokens per session scan A e96b88a6913b
FreeToken AGENTS.md is an instructions file published in the GitHub repository FlashML-org/FreeToken (11,649 stars, last pushed yesterday), licensed Apache-2.0. It adds 970 tokens to every session, about $0.0049 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 2026-09-05.
Other instructions, from other repositories
feima-copilot-llms-extension copilot-instructions.md
Copilot instructions for feimacode/feima-copilot-llms-extension, covering feima copilot llms extension - copilot instructions, localization and 1. runtime strings — l10n/bundle.l10n.zh-cn.json.
Mooncake AGENTS.md
AGENTS.md instructions for kvcache-ai/Mooncake, covering agents.md, docs/ directory changes and pull request guidelines.
emmy AGENTS.md
AGENTS.md instructions for cloudrift-ai/emmy, covering agents.md, project overview, prerequisites, running tests and the realization corpus.
carboncode AGENTS.md
Instructions for Yapie0/carboncode, covering agents.md, project context, current status, product direction and chosen base.
flarestarter CLAUDE.md
Instructions for FlareStarter/flarestarter: This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.
YOLO-Master CLAUDE.md
Claude Code instructions for Tencent/YOLO-Master, covering claude.md, 首先阅读, 关键约定, 变更前必做 and 变更后必做.