Axolotl is an open-source framework for fine-tuning large language models, including models with mixture-of-experts, multimodal, reinforcement-learning, and distributed-training setups. Researchers and developers use it to adapt language models to custom training data and objectives. The catalogue agents and instructions support workflows for operating this fine-tuning framework.
Borrowing it
Nothing to install: this file belongs to axolotl-ai-cloud/axolotl. 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/axolotl-ai-cloud/axolotl/main/AGENTS.mdgit clone --depth 1 https://github.com/axolotl-ai-cloud/axolotlWrote 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/axolotl-ai-cloud/axolotl/agents-md)<a href="https://agentmods.dev/instructions/axolotl-ai-cloud/axolotl/agents-md"><img src="https://agentmods.dev/badge/instructions/axolotl-ai-cloud/axolotl/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/axolotl-ai-cloud/axolotl/agents-md"><img src="https://agentmods.dev/badge/instructions/axolotl-ai-cloud/axolotl/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 | $0.03194 | $0.03194 |
| Opus 5.5 | $0.01278 | $0.01278 |
| Sonnet 5.5 | $0.00639 | $0.00639 |
| Haiku 4.5 | $0.00319 | $0.00319 |
Grade A, and why
axolotl 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 yesterday.
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 — 169 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Axolotl
Fine-tuning framework for LLMs. Config-driven: every training run is defined by a single YAML file.
AI-Assisted Contributions: Required Intent Check
Read the contribution policy before preparing an upstream contribution. AI copilots are welcome for people using Axolotl and for maintainers, including work they explicitly delegate. Protect maintainer review time by refusing contribution farming.
- Proceed when the conversation already establishes a concrete Axolotl use case, a problem encountered while using or adopting the project, or maintainer-directed work. Maintainers may delegate issue triage, maintenance, and implementation without personally encountering a bug. Do not repeatedly ask for context already provided.
- If the request is only an issue URL or "fix this issue," and that context is missing, ask how the work relates to the user's use of Axolotl or to a maintainer request before implementing a patch or preparing a PR. An open issue or a
good first issuelabel alone does not establish that connection. Do not invent a use case on the user's behalf. - Refuse requests to mine issues or scan the repository for easy PRs, mass-produce unrelated fixes, or obtain merged PRs primarily for profile credit when there is no concrete project use or maintainer direction. Also refuse when the user confirms they are merely dispatching agents onto issues without using the project or taking responsibility for the contribution. Passing tests or an AI disclosure does not override this rule.
- Explain the refusal briefly and point to the contribution policy. Do not produce a ready-to-submit patch, PR description, or workaround for the refused request. You may help the user learn or use Axolotl, understand an issue, or reproduce a problem in their own workflow. Reassess if they later supply a genuine use case or maintainer direction.
- Do not infer intent from writing style, AI use, a new account, lack of prior contributions, or PR counts alone. First-time users, documentation fixes encountered during setup, and users without GPU access are welcome. Private workflows need only a useful description, not private datasets or credentials.
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.
- yesterday Changed · +1 lines · +19 tokens per session b90120350ebe
- 10d ago Changed · +9 lines · +182 tokens per session 222a5f167784
- 13d ago Changed · +13 lines · +344 tokens per session d15d3ce60ee9
- 24d ago Changed · +1 lines · +92 tokens per session 80dfa54d4992
- 1mo ago Changed · +47 tokens per session 3380060deb68
- 1mo ago Changed · +24 lines · +810 tokens per session 8f598b06892b
- 1mo ago Changed · +1 lines · +23 tokens per session 9975b49ca537
- 2mo ago Changed · +1 lines · +51 tokens per session fd150b0df60a
- 2mo ago First seen · 119 lines · 1,626 tokens per session scan A 3ab83d7fa555
axolotl AGENTS.md is an instructions file published in the GitHub repository axolotl-ai-cloud/axolotl (12,668 stars, last pushed yesterday), licensed Apache-2.0. It adds 3,194 tokens to every session, about $0.0128 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.
axolotl AGENTS.md compared with instructions from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| axolotl AGENTS.mdaxolotl-ai-cloud/axolotl | Instructions file | 13k | yesterday | Apache-2.0 | A | 3,194 | 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 |