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 5.5 | $0.00013 | $0.00198 |
| Sonnet 5.5 | $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 2mo 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.
- 2mo 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 (558 stars, last pushed 4mo ago), licensed MIT. It adds 33 tokens to every session and 494 once invoked, about $0.0001 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.
adr-writer compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| adr-writeroxbshw/LLM-Agents-Ecosystem-Handbook | Skill | 558 | 4mo ago | MIT | A | 33 | Claude Code, Codex |
| fine-tuning-serving-openpiOrchestra-Research/AI-Research-SKILLs | Skill | 14k | 26d ago | MIT | A | 87 | Claude Code |
| fine-tuning-openvla-oftOrchestra-Research/AI-Research-SKILLs | Skill | 14k | 26d ago | MIT | A | 103 | Claude Code |
| together-ai-inferencesynthetic-sciences/openscience | Skill | 4.3k | 2d ago | Apache-2.0 | A | 55 | Claude Code, Codex |
| tinker-fine-tuningsynthetic-sciences/openscience | Skill | 4.3k | 2d ago | Apache-2.0 | A | 62 | Claude Code, Codex |
| tinker-training-costsynthetic-sciences/openscience | Skill | 4.3k | 2d ago | Apache-2.0 | A | 55 | Claude Code, Codex |
| transformerssynthetic-sciences/openscience | Skill | 4.3k | 2d ago | Apache-2.0 | A | 63 | Claude Code, Codex |