Getting it into your agent
This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.
/plugin marketplace add musingfox/cc-plugins/plugin install adrWrote 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/musingfox/cc-plugins/adr)<a href="https://agentmods.dev/skills/musingfox/cc-plugins/adr"><img src="https://agentmods.dev/badge/skills/musingfox/cc-plugins/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/musingfox/cc-plugins/adr"><img src="https://agentmods.dev/badge/skills/musingfox/cc-plugins/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 | $0.00141 | $0.02441 |
| Opus 5.5 | $0.00056 | $0.00976 |
| Sonnet 5.5 | $0.00028 | $0.00488 |
| Haiku 4.5 | $0.00014 | $0.00244 |
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 10d 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 — 264 lines — stays where its author put it; the contents beside it link to each section on GitHub.
ADR Lifecycle Management
Manage Architecture Decision Records using MADR 4.0 format with full cross-reference consistency enforcement.
Directory Detection
Auto-detect the ADR directory by scanning (in order):
docs/decisions/docs/adr/adr/decisions/
Use Glob: {docs/decisions,docs/adr,adr,decisions}/[0-9][0-9][0-9][0-9]-*.md
If no directory found and user wants to create an ADR, ask which location to use.
MADR 4.0 Format
Frontmatter
---
status: proposed
date: YYYY-MM-DD
decision-makers: ""
---
Status values: proposed | rejected | accepted | deprecated | superseded by [ADR-NNNN](file)
File Naming
- Pattern:
NNNN-kebab-case-title.md - 4-digit zero-padded number
- Scan existing files to determine next number
Template
Read ${CLAUDE_PLUGIN_ROOT}/skills/adr/references/madr-template.md for the full MADR 4.0 template.
Decision Warrant Test
An ADR earns its place only when all three conditions hold. One missing and the answer is: do not write one.
- Hard to reverse — changing your mind later carries a real cost.
- Confusing without context — a future reader will ask "why was it done this way?"
- A genuine trade-off existed — alternatives were actually on the table, and one was chosen for a stated reason.
Write ADRs sparingly. When a decision is borderline, it fails.
Where a failed decision goes instead:
- Fails 1 or 2 — the decision is cheap to undo, or its reason is self-evident. No record needed; a plain doc if someone still wants it written down.
- Fails 3 — nothing was ever weighed, so this is a constraint that must hold, not a choice that was made. Use
spec.
Conditions adapted from mattpocock/skills domain-modeling (MIT).
Operations
1. Create New ADR
- Apply the Decision Warrant Test. If a condition fails, name which one, point to where the decision belongs instead, and stop — continue only if the user reaffirms. The bootstrap ADR in step 3 is exempt: it records the format itself, not a decision under review.
- Detect ADR directory (or ask user to choose if none exists)
- If this is the first ADR in the directory, create the bootstrap ADR first (see below)
- Scan existing
[0-9][0-9][0-9][0-9]-*.mdfiles, determine next number - Generate kebab-case filename from the title
- Read the template from
${CLAUDE_PLUGIN_ROOT}/skills/adr/references/madr-template.mdand apply with today's date - Search existing ADR titles for keyword overlap and suggest related ADRs
- Present the created file path
What ships with it
3 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.
- 10d ago Changed · -44 lines 246dc1d97a00
- 1mo ago Changed · +38 lines · +102 tokens per session 8b373e9185a7
- 1mo ago Changed · -1 lines · -15 tokens per session 383eb1ef3831
- 1mo ago First seen · 271 lines · 54 tokens per session scan A b438b0d8f790
adr is a skill published in the GitHub repository musingfox/cc-plugins (2 stars, last pushed yesterday), licensed MIT. It adds 141 tokens to every session and 2,441 once invoked, about $0.0006 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 2026-08-31.
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…
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.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
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…