A command that records a technical decision as an Architecture Decision Record, or ADR: a document explaining what was decided and why. It also updates the project's automated rules when those rules enforce the decision.

Use it to create a new ADR from a technical decision or refine an existing one. It writes the decision to the project's decisions folder and synchronizes its related rules when needed.

It preserves the reasoning behind an important choice so future work does not depend on someone remembering a conversation. Keeping the decision and its enforcement rule together reduces drift.

adr — Command by AInsteinsBR

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 commands/ainsteinsbr/renata/adr

Clone the repo

git clone --depth 1 https://github.com/AInsteinsBR/renata

Or install renata, the plugin that ships this one along with the rest of its 3 skills, 33 commands, 6 agents, 2 hooks.

Per session 24 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

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	$0.00024	$0.01968
Opus 5	$0.00012	$0.00984
Sonnet 5	$0.00005	$0.00394
Haiku 4.5	$0.00002	$0.00197

Measured 3d ago against content hash b20cec49eb71, 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 3d 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.

commands/adr.md · 136 lines

How it starts

The opening of the file, as written. The whole thing — 136 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/renata:adr — Formalize an ADR from a decision

You are a senior architect. You receive the description of a technical decision in $ARGUMENTS and formalize it in the Nygard format, writing it to docs/decisions/ADR-NNN-<slug>.md.

Respond to the user and generate document content in the user's language (the language they are writing in).

Clear ownership before you start:

The ADR file (docs/decisions/ADR-NNN-*.md) is project content — you write here.
The .claude/rules.yaml is also project content — when the ADR's enforcement is via an automated hook, you add the YAML block directly to it, not just suggest it.
The template (rules.yaml.template, shipped with RENATA) belongs to the framework — don't touch it.

An ADR and its rules.yaml block are twins: they are born together, live together, and change together.

Operating mode: create vs refine

Before any question, identify the mode:

CREATE mode (default): $ARGUMENTS describes a new decision → next free number, ADR from scratch.
REFINE mode: $ARGUMENTS contains "refine ADR-NNN" or similar → load the existing ADR, validate each section, fill gaps, and sync with rules.yaml.
ADOPT-MCP mode (a variation of CREATE): $ARGUMENTS describes adopting an MCP for a capability (e.g., "use Jira for tasks"). Beyond the normal Nygard ADR, you write the corresponding entry into the integrations: block of .claude/rules.yaml:
- Form: <capability>: { mcp: <name-in-.mcp.json>, adr: ADR-NNN, mirror: <true|false> }.
- Canonical capabilities: tasks, pr, db, research (extensible). (research = web search source for /renata:landscape, e.g. a Perplexity MCP.)
- mirror: true when the MCP receives a mirrored write after confirmation; false when it is read/action only.
- The ADR and the entry in integrations: are twins (same principle as the adrs: block): they are born together and disappear together if the ADR becomes superseded.
- Confirm the <name-in-.mcp.json> with the user (it must match the server declared in .mcp.json).

Read the full file on GitHub · 136 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.

3d ago First seen · 136 lines · 24 tokens per session scan A b20cec49eb71

Subscribe to this mod's changes

adr is a command published in the GitHub repository AInsteinsBR/renata (10 stars, last pushed 12d ago), licensed MIT. It adds 24 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.

Writing and docs adr claude-code claude-plugin prd product-management

adr

Getting it into your agent

What it costs to keep this loaded

Grade A, and why

Nothing flagged

How it starts

/renata:adr — Formalize an ADR from a decision

Operating mode: create vs refine

What this file has done since we first saw it

Other commands, from other repositories

issue-review

issue-closeout

prd-review

prd-triage

prd-archive

issue-start