Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/mhylle/claude-skills-collectionnpx agentmods add skills/mhylle/claude-skills-collection/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/mhylle/claude-skills-collection/adr)<a href="https://agentmods.dev/skills/mhylle/claude-skills-collection/adr"><img src="https://agentmods.dev/badge/skills/mhylle/claude-skills-collection/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/mhylle/claude-skills-collection/adr"><img src="https://agentmods.dev/badge/skills/mhylle/claude-skills-collection/adr.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 | $0.00075 | $0.03224 |
| Opus 5 | $0.00037 | $0.01612 |
| Sonnet 5 | $0.00015 | $0.00645 |
| Haiku 4.5 | $0.00007 | $0.00322 |
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 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 — 453 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Architectural Decision Records (ADR)
Document significant architectural and technical decisions in a standardized, searchable format optimized for LLM context efficiency.
Design Principles
Context Conservation
ADRs are designed for efficient LLM consumption:
- Small, focused files - One decision per ADR, minimal content
- Quick Reference block - First 5 lines summarize the entire ADR
- Central INDEX.md - Single file listing all ADRs with one-line summaries
LLM Reading Strategy
When consulting ADRs, follow this tiered approach:
TIER 1: Read INDEX.md (one file, all summaries)
↓ Identify potentially relevant ADRs
TIER 2: Read Quick Reference block only (first 10 lines of candidate ADRs)
↓ Confirm relevance
TIER 3: Read full ADR content (only when details are needed)
Implementation:
# Tier 1: Scan index
Read("docs/decisions/INDEX.md")
# Tier 2: Quick reference only (use limit parameter)
Read("docs/decisions/ADR-0001-title.md", limit=10)
# Tier 3: Full content (only if needed)
Read("docs/decisions/ADR-0001-title.md")
When to Use This Skill
Directly invoked when:
- Making a significant technical decision
- Choosing between architectural approaches
- Establishing patterns or conventions
- Documenting why a particular technology was selected
Automatically invoked by other skills when:
- create-plan: Design decision is made in Phase 4
- implement-plan: Mismatch discovered or architectural choice made during implementation
- brainstorm: Key decisions identified during analysis
ADR Location and Naming
Directory: docs/decisions/
Naming Convention: ADR-NNNN-short-title.md
NNNN: Zero-padded sequential number (0001, 0002, etc.)short-title: Lowercase, hyphenated description (max 50 chars)
Examples:
ADR-0001-use-jwt-for-authentication.mdADR-0002-postgresql-over-mongodb.mdADR-0003-event-sourcing-for-audit.md
Getting the Next ADR Number
What ships with it
2 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 · 453 lines · 75 tokens per session scan A eddd29ec2686
adr is a skill published in the GitHub repository mhylle/claude-skills-collection (18 stars, last pushed 8d ago), licensed MIT. It adds 75 tokens to every session and 3,224 once invoked, about $0.0004 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…