Borrowing it
Nothing to install: this file belongs to cardstack/boxel. 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/cardstack/boxel/main/.claude/skills/adr/SKILL.mdgit clone --depth 1 https://github.com/cardstack/boxelWrote 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/cardstack/boxel/adr)<a href="https://agentmods.dev/skills/cardstack/boxel/adr"><img src="https://agentmods.dev/badge/skills/cardstack/boxel/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/cardstack/boxel/adr"><img src="https://agentmods.dev/badge/skills/cardstack/boxel/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 | $0.00000 | $0.01718 |
| Opus 5.5 | $0.00000 | $0.00687 |
| Sonnet 5.5 | $0.00000 | $0.00344 |
| Haiku 4.5 | $0.00000 | $0.00172 |
Grade A, and why
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 5d 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 — 119 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Architecture Decision Records
Read docs/adr/001-record-architecture-decisions.md first. It defines the
format, lifecycle, and enforcement, and this skill cites it by section rather
than restating it.
Before changing code an ADR covers
If you are about to reverse, work around, or loosen an established pattern, find the ADRs that govern the files you're touching:
node scripts/adr-for.mts <path>...
Read each accepted or proposed ADR it lists. Follow its MUST requirements. If the change can't, tell the user
which requirement it breaks ("ADR 004 §1.2"). For an accepted ADR, the change
needs a superseding ADR. For a proposed ADR, it needs a reviewed edit to the
ADR's Decision (ADR 001 §1.6). Departing from a SHOULD needs a reason stated
in the PR (ADR 001 §1.9).
A proposed ADR binds new code the same way, including in the PR that adds
it. Code listed under its Remediation section is a known gap: you may leave it
as it is, but don't copy it into new code (ADR 001 §1.9). If your change
closes a gap, remove its entry in the same PR. If you find a gap that isn't
listed, add it.
Writing a new ADR
- Check the bar (ADR 001 §1.1). If the decision doesn't meet it, the PR's "Key decisions" section is the right home. If you're unsure, ask the user.
- Number it.
ls docs/adr/[0-9]*.md | tail -1gives the highest number. Use the next one, with three digits. - Copy
docs/adr/template.mdand fill it in (ADR 001 §1.2–§1.4):- Set
status: proposed. Never setaccepted(§1.6). - Write
scopeas a YAML list, one glob per line, precise enough thatscripts/adr-for.mtsfinds this ADR from the code it governs. Check it by running the script on a file the ADR governs. - Write the summary paragraph last, once you know what the ADR says.
- In the Decision, write one requirement per sentence with a BCP 14 key word. Use MUST only for what a reviewer should block on. Use SHOULD for a default that can be departed from with a stated reason.
- In Considered options, name the alternatives a newcomer or an agent would reach for, and say why each lost. This section is what stops a rejected design from being proposed again.
- Survey the scope for gaps (ADR 001 §1.6). Search the code the
scopeglobs cover for places that break a MUST or MUST NOT. List each under Remediation, the last section, by file (and symbol, when the gap is narrower) with the requirement it breaks. Don't fix them in the ADR's PR unless the fix is small. The ADR can merge first, and the remediation follows in separate PRs. If a gap is in a file outsidescope, widenscopeto cover it. If there are no gaps, write "No known gaps." Never leave the section out: a proposed ADR without one can't be told apart from one nobody surveyed.
- Set
- Make the deletion pass (§1.5). Reread the draft only to cut: restated mechanics a linked doc or skill already covers, Consequences that repeat the Decision, and hedges. Expect a page or less.
- Add the index row in
docs/adr/README.md.
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.
- 5d ago First seen · 119 lines · 0 tokens per session scan A 001ed3b34b47
adr is a skill published in the GitHub repository cardstack/boxel (27 stars, last pushed today), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,718 tokens. 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 2026-10-21.
Other skills, from other repositories
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…
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
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…
chronicle
Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
component-fixtures
Use when creating or updating component fixtures for screenshot testing or their shared infrastructure, or when designing UI components to be fixture-friendly. Covers fixture file structure, theming, service setup, CSS scoping, async rendering, validation, and common pitfalls.