adr

A command for drafting an Architecture Decision Record, a short document that records an important technical choice and its reasons.

In plain words
What is it for?
Use it when proposing a significant codebase or system decision, especially when the project stores decisions in an ADR or decision-document folder.
Why use it?
It creates a consistent record of the context, alternatives, trade-offs, and consequences behind decisions that future developers may need to understand.

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/dshakes/compass/adr
Clone the repo
git clone --depth 1 https://github.com/dshakes/compass
Per session 10 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 236 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 $0.00010 $0.00236
Opus 5 $0.00005 $0.00118
Sonnet 5 $0.00002 $0.00047
Haiku 4.5 $0.00001 $0.00024

Measured 2d ago against content hash e52792d62faf, 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/commands/adr.md · 18 lines

What it actually says

Draft an ADR for: $ARGUMENTS

  1. Find where ADRs live (docs/adr/, docs/decisions/, or ask if none) and read the two most recent to match numbering and format.
  2. Write a new ADR with: Title (numbered) · Status (Proposed) · Date (today) · Context (the forces and constraints) · Decision (what we're doing, stated plainly) · Consequences (good and bad, honestly) · Alternatives considered (and why rejected).
  3. Keep it concrete and grounded in this codebase's actual constraints. Reference the invariants in CLAUDE.md it touches.

Show me the draft before writing the file if the decision is contentious.

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 · 18 lines · 10 tokens per session scan A e52792d62faf

Subscribe to this mod's changes

adr is a command published in the GitHub repository dshakes/compass (19 stars, last pushed 8d ago), licensed MIT. It adds 10 tokens to every session and 236 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 2026-08-30.