Borrowing it
Nothing to install: this file belongs to Atypical-Consulting/AdrMcp. 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/Atypical-Consulting/AdrMcp/dev/.claude/skills/adr-author/SKILL.mdgit clone --depth 1 https://github.com/Atypical-Consulting/AdrMcpWrote 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/atypical-consulting/adrmcp/adr-author)<a href="https://agentmods.dev/skills/atypical-consulting/adrmcp/adr-author"><img src="https://agentmods.dev/badge/skills/atypical-consulting/adrmcp/adr-author/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/atypical-consulting/adrmcp/adr-author"><img src="https://agentmods.dev/badge/skills/atypical-consulting/adrmcp/adr-author.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 | $0.00113 | $0.00811 |
| Opus 5 | $0.00056 | $0.00405 |
| Sonnet 5 | $0.00023 | $0.00162 |
| Haiku 4.5 | $0.00011 | $0.00081 |
Grade A, and why
adr-author 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 8d 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 — 56 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Authoring an ADR
You help the user turn a real architectural decision into a crisp, durable ADR. The MCP server handles mechanics (numbering, files, frontmatter, validation) — your job is the judgment and prose: is this decision worth recording, and is it framed honestly?
Requires the AdrMcp MCP server (tools
create_adr,validate_adr,list_adrs). If those tools aren't available, tell the user to connect the AdrMcp server first.
Does this decision even warrant an ADR?
Record it when the decision is architecturally significant — it constrains future work and would be expensive to reverse. Good signals:
- It affects structure, dependencies, interfaces, or cross-cutting concerns.
- A future contributor will ask "why is it done this way?" and deserve an answer.
- Reasonable engineers would have chosen differently; there were real alternatives.
Don't write an ADR for reversible, local, or obvious choices (variable names, a one-off bug fix, formatting). If it doesn't constrain the future, skip it and say so.
Workflow
- Check for overlap. Call
list_adrs(orsearch_adrs) so you don't duplicate or silently contradict an existing decision. If one exists, consideradr-revieworadr-supersedeinstead of a new record. - Interview for the four parts (ask only what you can't infer from the codebase/context):
- Context / problem — the forces at play, constraints, what makes this non-trivial.
- Considered options — the real alternatives, not strawmen.
- Decision — the chosen option, stated as a decision ("We will…"), not a discussion.
- Consequences — what becomes easier AND what becomes harder / what we accept.
- Draft with
create_adr(template=madrdefault),previewOnly=truefirst so the user sees the diff. Passtagsfor the architectural area,decidersif known. - Validate with
validate_adron the new id; fix any errors (missing sections, dangling links) before committing. - Commit by re-calling
create_adrwithpreviewOnly=falseonce the user approves. - New ADRs start as
proposed. Useset_statusto move toacceptedonly when the decision is actually adopted.
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.
- 8d ago First seen · 56 lines · 113 tokens per session scan A 75844bc1ed9f
adr-author is a skill published in the GitHub repository Atypical-Consulting/AdrMcp (1 stars, last pushed 18d ago), licensed MIT. It adds 113 tokens to every session and 811 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 2026-08-31.
Other skills, from other repositories
bootstrap
Scaffold or retrofit documentation-led conventions (AGENTS.md, CLAUDE.md, CONVENTIONS.md, ADR catalogue, plan/ queue, agent/ coordination) into a repo. Use when the user asks to "set up conventions", "bootstrap ADRs", "scaffold the documentation-led layout", or "add AGENTS.md and a plan queue". Works on fresh repos…
decision-backfill
Use when auditing an existing codebase, documentation set, plans, RFCs, or git history for architecture decisions that were made but never recorded as ADRs, and when triaging potential records before drafting them.
decision-memory
Use when planning, designing, reviewing, or changing code in a repository that keeps ADRs (usually docs/adr) — to load the decisions that already govern the work, check a plan or diff against them, or record a new decision. Also use when a choice feels already-settled and you cannot find where it was settled.
adr-integration
This skill should be used when the user asks about "ADR integration", "ADR CI/CD", "ADR tooling", "ADR automation", "export ADRs", "ADR documentation site", or needs guidance on integrating ADRs with CI/CD, documentation sites, and other tools.
adr-decision-drivers
This skill should be used when the user asks about "decision drivers", "architectural forces", "quality attributes", "how to identify trade-offs", "non-functional requirements for ADRs", or needs help identifying, documenting, and weighing the forces that influence architectural decisions.
actual
Feature-complete companion for the actual CLI, an ADR-powered CLAUDE.md/AGENTS.md generator. Runs and troubleshoots actual adr-bot, status, auth, config, runners, and models, plus the Actual AI platform surface: login, logout, whoami, and advisor (org-scoped architecture Q&A). Covers all 5 runners (claude-cli…