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 skills add oxbshw/LLM-Agents-Ecosystem-Handbook --skill adr-writergit clone --depth 1 https://github.com/oxbshw/LLM-Agents-Ecosystem-HandbookWrote 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/oxbshw/llm-agents-ecosystem-handbook/adr-writer)<a href="https://agentmods.dev/skills/oxbshw/llm-agents-ecosystem-handbook/adr-writer"><img src="https://agentmods.dev/badge/skills/oxbshw/llm-agents-ecosystem-handbook/adr-writer/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/oxbshw/llm-agents-ecosystem-handbook/adr-writer"><img src="https://agentmods.dev/badge/skills/oxbshw/llm-agents-ecosystem-handbook/adr-writer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00033 | $0.00494 |
| Opus 5 | $0.00016 | $0.00247 |
| Sonnet 5 | $0.00007 | $0.00099 |
| Haiku 4.5 | $0.00003 | $0.00049 |
Grade A, and why
adr-writer 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 11d 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
ADR Writer
When to use
- A non-trivial architecture decision was just made
- Reverse-documenting a decision that wasn't recorded but should have been
- Preparing for a design review
When NOT to use
- Trivial choices (naming, formatting)
- Operational runbooks (those go to
runbooks/) - Product decisions without architectural impact
Inputs
| Name | Type | Required | Notes |
|---|---|---|---|
context |
string | yes | The problem being solved, in 2–4 sentences |
options |
list | yes | Alternatives considered |
decision |
string | yes | Chosen path |
number |
int | no | If omitted, finds next ADR number from memory/decisions/ |
Outputs
A file at memory/decisions/ADR-NNNN-<slug>.md matching the ADR template.
Workflow
- Find the next ADR number (or use
numberinput) - Slugify the decision's main subject
- Fill the template:
- Context, Decision, Alternatives, Consequences (positive + negative)
- Status:
accepted(default),proposed,superseded by ADR-XXXX
- Write to
memory/decisions/ADR-NNNN-<slug>.md - Add a one-line entry to
MEMORY.md#decisions
References
Success criteria
- Each alternative has a one-line "why not"
- Consequences include at least one negative
- File name matches
ADR-\d{4}-[a-z0-9-]+\.md
Failure modes
- Decision is actually a bundle of decisions → split into multiple ADRs
- Context is unclear → ask user for clarification, don't fabricate
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.
- 11d ago First seen · 54 lines · 33 tokens per session scan A 479ff8a4d7ce
adr-writer is a skill published in the GitHub repository oxbshw/LLM-Agents-Ecosystem-Handbook (546 stars, last pushed 2mo ago), licensed MIT. It adds 33 tokens to every session and 494 once invoked, about $0.0002 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 skills, from other repositories
implementing-llms-litgpt
Implements and trains LLMs using Lightning AI's LitGPT with 20+ pretrained architectures (Llama, Gemma, Phi, Qwen, Mistral). Use when need clean model implementations, educational understanding of architectures, or production fine-tuning with LoRA/QLoRA. Single-file implementations, no abstraction layers.
llama-factory
Expert guidance for fine-tuning LLMs with LLaMA-Factory - WebUI no-code, 100+ models, 2/3/4/5/6/8-bit QLoRA, multimodal support.
together-ai-inference
Serverless inference, fine-tuning, embeddings, image generation, and batch processing on 200+ open-source models via an OpenAI-compatible API. Use when you need fast, cost-effective access to open-source LLMs without managing infrastructure.
tinker-fine-tuning
Provides guidance for fine-tuning LLMs using the Tinker cloud training API from Thinking Machines Lab. Use when running supervised fine-tuning, reinforcement learning (GRPO/PPO), or LoRA training on cloud GPUs via Tinker's managed infrastructure instead of local compute.
tinker-training-cost
Calculates training costs for Tinker fine-tuning jobs. Use when estimating costs for Tinker LLM training, counting tokens in datasets, or comparing Tinker model training prices. Tokenizes datasets using the correct model tokenizer and provides accurate cost estimates.
transformers
This skill should be used when working with pre-trained transformer models for natural language processing, computer vision, audio, or multimodal tasks. Use for text generation, classification, question answering, translation, summarization, image classification, object detection, speech recognition, and fine-tuning…