Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/cyborg-garden/hermes-agent-mtnpx agentmods add skills/cyborg-garden/hermes-agent-mt/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/skills/cyborg-garden/hermes-agent-mt/axolotl)<a href="https://agentmods.dev/skills/cyborg-garden/hermes-agent-mt/axolotl"><img src="https://agentmods.dev/badge/skills/cyborg-garden/hermes-agent-mt/axolotl/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/skills/cyborg-garden/hermes-agent-mt/axolotl"><img src="https://agentmods.dev/badge/skills/cyborg-garden/hermes-agent-mt/axolotl.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 | $0.00024 | $0.01186 |
| Opus 5 | $0.00012 | $0.00593 |
| Sonnet 5 | $0.00005 | $0.00237 |
| Haiku 4.5 | $0.00002 | $0.00119 |
Grade A, and why
axolotl 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 7d 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.
This is a copy
97% identical to axolotl — 2 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 167 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Axolotl Skill
What's inside
Expert guidance for fine-tuning LLMs with Axolotl — YAML configs, 100+ models, LoRA/QLoRA, DPO/KTO/ORPO/GRPO, multimodal support.
Comprehensive assistance with axolotl development, generated from official documentation.
When to Use This Skill
This skill should be triggered when:
- Working with axolotl
- Asking about axolotl features or APIs
- Implementing axolotl solutions
- Debugging axolotl code
- Learning axolotl best practices
Quick Reference
Common Patterns
Pattern 1: To validate that acceptable data transfer speeds exist for your training job, running NCCL Tests can help pinpoint bottlenecks, for example:
./build/all_reduce_perf -b 8 -e 128M -f 2 -g 3
Pattern 2: Configure your model to use FSDP in the Axolotl yaml. For example:
fsdp_version: 2
fsdp_config:
offload_params: true
state_dict_type: FULL_STATE_DICT
auto_wrap_policy: TRANSFORMER_BASED_WRAP
transformer_layer_cls_to_wrap: LlamaDecoderLayer
reshard_after_forward: true
Pattern 3: The context_parallel_size should be a divisor of the total number of GPUs. For example:
context_parallel_size
Pattern 4: For example: - With 8 GPUs and no sequence parallelism: 8 different batches processed per step - With 8 GPUs and context_parallel_size=4: Only 2 different batches processed per step (each split across 4 GPUs) - If your per-GPU micro_batch_size is 2, the global batch size decreases from 16 to 4
context_parallel_size=4
Pattern 5: Setting save_compressed: true in your configuration enables saving models in a compressed format, which: - Reduces disk space usage by approximately 40% - Maintains compatibility with vLLM for accelerated inference - Maintains compatibility with llmcompressor for further optimization (example: quantization)
save_compressed: true
Pattern 6: Note It is not necessary to place your integration in the integrations folder. It can be in any location, so long as it’s installed in a package in your python env. See this repo for an example: https://github.com/axolotl-ai-cloud/diff-transformer
What ships with it
4 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 7d ago First seen · 167 lines · 24 tokens per session scan A 180458a8fbe7
axolotl is a skill published in the GitHub repository cyborg-garden/hermes-agent-mt (13 stars, last pushed 3d ago), licensed MIT. It adds 24 tokens to every session and 1,186 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 0 findings. It is 97% identical to axolotl, differing in 2 lines, and is treated as a copy.
Other skills, from other repositories
hermes-memory-providers
Install and configure Mnemosyne as a Hermes Agent memory provider — local SQLite with vector search, episodic consolidation, and temporal knowledge graphs.
mnemosyne
Persistent cross-session memory via Mnemosyne — store, recall, and consolidate facts, preferences, and context.
mnemosyne-memory-override
Hard rule override that forces Mnemosyne for all durable memory storage. The legacy memory tool is DEPRECATED for user preferences, credentials, and project conventions. Use memory ONLY for ephemeral session state.
rag-local-lancedb
Build, query, and manage local vector embeddings and semantic search pipelines using LanceDB and HuggingFace/SentenceTransformers embeddings without cloud dependencies.
polymorph
This spell is about representation change, not: Naming changes (same structure, different identifiers) Execution changes (same code, different runtime) Architecture changes (new system design) Duplication (same thing, different place) The key test: Can you point to a source artifact and a target artifact where the…
locate-object
In D&D, Locate Object senses the direction to a specific object within range. The real-world version is artifact search: finding that config file you know exists somewhere, locating a document someone mentioned but did not link, tracking down the source of a data value through a pipeline, or finding where a specific…