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 emiliosheinz/agent-skills --skill create-adrgit clone --depth 1 https://github.com/emiliosheinz/agent-skillsWrote 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/emiliosheinz/agent-skills/create-adr)<a href="https://agentmods.dev/skills/emiliosheinz/agent-skills/create-adr"><img src="https://agentmods.dev/badge/skills/emiliosheinz/agent-skills/create-adr/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/emiliosheinz/agent-skills/create-adr"><img src="https://agentmods.dev/badge/skills/emiliosheinz/agent-skills/create-adr.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 | $0.00127 | $0.01092 |
| Opus 5 | $0.00063 | $0.00546 |
| Sonnet 5 | $0.00025 | $0.00218 |
| Haiku 4.5 | $0.00013 | $0.00109 |
Grade A, and why
create-adr 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.
How it starts
The opening of the file, as written. The whole thing — 97 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Create ADR
Produce one ADR per invocation. An ADR records a decision that has already
been made; if the decision is still open, use /create-rfc. Follow the
five-step process — do not skip Step 2 (validate mandatory fields) or draft
before every mandatory field is present.
Hard rules
- Never invent facts. If a mandatory field is missing, ask. Never fill Context, Decision, or Consequences with plausible-sounding filler.
- Never edit an existing ADR to change the decision. Supersede with a new ADR and link back. ADRs are historical records.
- Never skip trade-offs. Consequences must be honest — include what becomes harder, not just what becomes easier.
- Never write in a language other than the user's. Match the language the user is using in this session.
Dispatch
Run the process in order. Read the matching reference file fully before acting — it is the playbook for that step.
| Step | Read | Purpose |
|---|---|---|
| 1 — Gather context | references/process.md |
Ask for decision, format, status, supersedes |
| 2 — Validate mandatory fields | references/process.md |
Ensure title, date, status, context, decision, consequences are present |
| 3 — Pick format | references/formats.md |
MADR (default) / Nygard / Y-Statement |
| 4 — Assign number | references/numbering.md |
Scan directory, assign next sequential number |
| 5 — Generate + place | references/process.md + one of templates/adr-{madr,nygard,y-statement}.md |
Fill template, run quality checklist, confirm file location |
Run the quality checklist (references/quality.md) before finalizing —
titles, honest trade-offs, options actually compared, naming convention.
Templates
Pure markdown scaffolds; load only the one for the chosen format:
| Format | Template |
|---|---|
| MADR (default) | templates/adr-madr.md |
| Nygard | templates/adr-nygard.md |
| Y-Statement | templates/adr-y-statement.md |
Universal rules
- Honesty. Record trade-offs, unknowns, and open questions honestly.
Never cover a gap with an invented answer. If a field cannot be filled,
ask or leave an italicized placeholder (
*to be confirmed*). - Immutability. ADRs are historical records. Never edit the decision
after the fact — supersede with a new ADR and link
Superseded by ADR-{NNN}on the old one. - Short is better. 200–500 words is ideal. If longer, move detail to a linked design doc or RFC.
- Date everything. What seems obvious now will not be in three years.
- Language adaptation. Always write the ADR in the user's language.
- Confirm before writing. Suggest the file path in Step 5; write only after the user confirms placement.
What ships with it
8 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.
- 11d ago First seen · 97 lines · 127 tokens per session scan A a4ce7484c946
create-adr is a skill published in the GitHub repository emiliosheinz/agent-skills (18 stars, last pushed 1mo ago), licensed MIT. It adds 127 tokens to every session and 1,092 once invoked, about $0.0006 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
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…