adr

A conversational command for creating an Architecture Decision Record, or ADR—a document that records why a technical choice was made.

In plain words
What is it for?
Use it to discuss the project, status, context, decision, and alternatives, then create a filled-in record for the project.
Why use it?
It preserves the reasoning behind a decision so future developers can understand the situation, chosen approach, and rejected alternatives.

Command

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/eddiebelaval/squire/adr
Clone the repo
git clone --depth 1 https://github.com/eddiebelaval/squire
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 710 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.

ModelPer sessionOnce invoked
Fable 5 $0.00000 $0.00710
Opus 5 $0.00000 $0.00355
Sonnet 5 $0.00000 $0.00142
Haiku 4.5 $0.00000 $0.00071

Measured 2d ago against content hash d090d52ca757, 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.

commands/adr.md · 73 lines

How it starts

The opening of the file, as written. The whole thing — 73 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/adr - Architecture Decision Record

You are helping create a new ADR (Architecture Decision Record). This is a conversational process — you interview the user about the decision, then create a filled-in record. ADRs capture the WHY behind technical choices so future-you understands the reasoning.

Arguments

  • $ARGUMENTS: Decision title or topic (can be rough)
  • Flags: --project <name>

Conversational Flow

Phase 1: Project Context (use AskUserQuestion if needed)

  1. Project — Which project? (if not auto-detected)
  2. Status — Options: Proposed (still deciding), Accepted (decided, moving forward)

Phase 2: The Decision Interview (conversational)

Walk through these naturally — don't dump all questions at once:

  1. Context: "What's the situation? What problem or need led to this decision?"

    • Get the background: what exists today, what's not working, what changed
  2. Decision: "What did you decide (or are you proposing)?"

    • Get the specific choice: which technology, which pattern, which approach
  3. Why this over alternatives: "What else did you consider? Why not those?"

    • For each alternative: what was it, what was good about it, why you didn't pick it
    • This is the most valuable part of an ADR — the rejected alternatives
  4. Consequences: "What are the trade-offs? What does this enable, and what does it cost?"

    • Positive: what gets better
    • Negative: what gets harder or what you lose
    • Neutral: side effects that are neither good nor bad

Phase 3: Create and Fill

  1. Run ~/.claude/generators/new-adr.sh with the title and project
  2. Read the created file
  3. Fill in ALL sections from the conversation — Context, Decision, Consequences, Alternatives
  4. Write the completed file
  5. Show a summary

Example Conversation

User: /adr Use Supabase RLS instead of API middleware for auth

Claude: Which project is this for?

User: Homer

Claude: What led to this decision? What's the current auth setup?

User: Right now we check user_id in every API route manually. It's repetitive and we already missed one route which caused the IDOR bug last week.

Claude: That's a clear motivator. Did you consider anything besides RLS?

User: Yeah, we thought about a middleware wrapper function, but RLS means the database itself enforces it so even if we forget in the API layer, data is still protected.

Claude: What's the downside of RLS?

User: Harder to debug when queries return empty — you don't know if it's a data issue or a policy issue. Also more complex SQL.

Claude: [Creates ADR-0002-use-supabase-rls-instead-of-api-middleware.md with everything filled in]

Read the full file on GitHub · 73 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.

  1. 2d ago First seen · 73 lines · 0 tokens per session scan A d090d52ca757

Subscribe to this mod's changes

adr is a command published in the GitHub repository eddiebelaval/squire (21 stars, last pushed 17d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 710 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 2026-08-30.

Related

Other commands, from other repositories

promote

Refine scv/raw/ material into a scv/promote/ - - / folder with PLAN.md + TESTS.md. Optionally updates the docs knowledge graph. Interactive; no files written without user approval. Use whenever the user wants a change planned, specced, or broken down before implementation — 'plan this', 'write a spec', 'what should we…

wookiya1364/scv-claude-code · 126 tokens

work

Implement a scv/promote/ / plan. Reads PLAN.md + TESTS.md, proposes/loads Related Documents as needed, runs the tests, and optionally archives on success. Use whenever the user wants an existing plan implemented — 'build it', 'implement the plan', 'let's do it' — not only when they type /scv:work. Never implement a…

wookiya1364/scv-claude-code · 101 tokens

codegen

TDD-first codegen for a scv/promote/ / plan. Verifies TESTS fail first (Red), then iteratively writes the minimum code to pass each case (Green). Hands off archive/PR/regression to /scv:work. Use whenever the user wants a plan implemented test-first — 'TDD', 'tests first', 'red-green' — not only when they type…

wookiya1364/scv-claude-code · 102 tokens

routine

Execute one maintenance routine defined in scv/routines/ .md (task + guardrails + exit-criteria contract), or list defined routines. SCV never schedules — pair with host features like /loop or cron yourself. Use whenever the user asks to run a recurring maintenance task, or asks what routines exist — not only when…

wookiya1364/scv-claude-code · 75 tokens

status

Show raw changes since last index + list of active promote plans. Use whenever the user asks what is in flight, what changed, or where things stand — not only when they type /scv:status. Never summarize project state from memory; this command reads it.

wookiya1364/scv-claude-code · 54 tokens

workspace

Set up or change this repo's place in a multi-repo SCV workspace: join an umbrella as a child, create an umbrella (root), check status, or detach. Friendly — no long flags to remember. Use whenever the user asks how this repo relates to sibling repos, or wants to join, create, or leave a multi-repo workspace — not…

wookiya1364/scv-claude-code · 83 tokens