An Architecture Decision Record assistant for RHDH projects. An Architecture Decision Record is a short document that records an important technical choice, its context, alternatives, and trade-offs.

It helps structure a problem, draft an ADR, critique an existing ADR, suggest alternatives, and refine individual sections.

It turns a loosely described technical problem into a decision that the team can review and preserve. This reduces missing context and makes alternatives easier to compare.

adr — Skill by redhat-developer

Install

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.

agentmods

npx agentmods add skills/redhat-developer/rhdh-adr/adr

Any agent

npx skills add redhat-developer/rhdh-adr --skill adr

Clone the repo

git clone --depth 1 https://github.com/redhat-developer/rhdh-adr

Made for: Claude Code, Codex.

Per session 12 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 1,968 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. Scan, not verified.

Origin original No closer match found in the catalogue.

Token cost

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	$0.00012	$0.01968
Opus 5	$0.00006	$0.00984
Sonnet 5	$0.00002	$0.00394
Haiku 4.5	$0.00001	$0.00197

Measured 2d ago against content hash 5e1b2b85cb12, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

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 2d 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.

.claude/skills/adr/SKILL.md · 266 lines

How it starts

The opening of the file, as written. The whole thing — 266 lines — stays where its author put it; the contents beside it link to each section on GitHub.

ADR Skill

Help write, review, and refine Architecture Decision Records for RHDH projects.

Available Commands

/adr structure - Structure a messy problem into ADR format
/adr draft - Generate complete ADR from your decision
/adr critique - Review and critique an existing ADR
/adr alternatives - Suggest alternative approaches
/adr refine - Improve a specific ADR section

Command Details

/adr structure

Help structure a problem into ADR format.

Process:

Ask user: "What problem are you solving? What's the current state and limitation?"
Optionally ask for project context if needed: "What's your project repository URL and what does it do?"
Read ADR-TEMPLATE.md to understand structure
Analyze the problem and suggest:
- How to frame the Context section
- What decision options to consider
- Key trade-offs to analyze
- What information is missing

Output: Structured outline ready to fill into template

/adr draft

Generate a complete ADR draft from a decision.

Process:

Ask user for:
- What decision have you made?
- What problem does it solve?
- Current state/limitations
- Key requirements or constraints
Optionally ask for project context if needed: "What's your project repository URL and what does it do?"
Read ADR-TEMPLATE.md for structure
Read ADR-GUIDE.md for guidelines
Pull the latest main and re-run the script ./scripts/suggest-next-adr.sh if needed.
Run ./scripts/suggest-next-adr.sh from the repo root to get the next ADR number for filename. Use the output for the filename: decisions/NNN-kebab-case-title.md (Logic matches .github/workflows/adr-number-check.yaml.)
- The script only sees ADR files on your current branch (usually main plus your changes) — not numbers proposed in other open PRs.
- Before finalising the filename, check open PRs on the repo for new decisions/NNN-*.md files (better chance of avoiding conflicts; not guaranteed).
- CI validates on PR; the number is not final until the ADR PR is merged.

Read the full file on GitHub · 266 lines

Changes

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.

2d ago First seen · 266 lines · 12 tokens per session scan A 5e1b2b85cb12

Subscribe to this mod's changes

adr is a skill published in the GitHub repository redhat-developer/rhdh-adr (2 stars, last pushed 29d ago), licensed Apache-2.0. It adds 12 tokens to every session and 1,968 once invoked, about $0.0001 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.

Planning Writing and docs

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

brainstorming

You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.

obra/superpowers · 37 tokens

auto-perf-optimize

Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.

microsoft/vscode · 62 tokens

chat-perf

Run chat perf benchmarks and memory leak checks against the local dev build or any published VS Code version. Use when investigating chat rendering regressions, validating perf-sensitive changes to chat UI, or checking for memory leaks in the chat response pipeline.

microsoft/vscode · 51 tokens

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.

microsoft/vscode · 53 tokens

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…

microsoft/vscode · 71 tokens