write-adr

A command for creating an Architecture Decision Record, or ADR: a short document that explains an important technical choice and its consequences.

In plain words
What is it for?
It is for gathering decision details, creating a numbered ADR in docs/adr, and updating an existing ADR index.
Why use it?
It gives the team a shared record of why a decision was made, what alternatives were considered, and which trade-offs were accepted.

Command

Part of the adr-writer plugin — 2 commands shipped together

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/rohitg00/awesome-claude-code-toolkit/write-adr
Clone the repo
git clone --depth 1 https://github.com/rohitg00/awesome-claude-code-toolkit

Or install adr-writer, the plugin that ships this one along with the rest of its 2 commands.

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 324 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 $0.00324
Opus 5 $0.00000 $0.00162
Sonnet 5 $0.00000 $0.00065
Haiku 4.5 $0.00000 $0.00032

Measured 3d ago against content hash 92e03564ef1c, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

write-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.

plugins/adr-writer/commands/write-adr.md · 29 lines

What it actually says

/write-adr - Write Architecture Decision Record

Create a new Architecture Decision Record documenting a technical decision.

Steps

  1. Ask the user for the decision title and context
  2. Determine the next ADR number by scanning existing ADRs in the docs/adr directory
  3. Ask about the decision context: what problem is being solved and why now
  4. Gather the options considered with pros and cons for each
  5. Document the chosen option and the reasoning behind the decision
  6. Identify consequences: what changes, what trade-offs are accepted
  7. Note the decision status: proposed, accepted, deprecated, or superseded
  8. Link to related ADRs if this decision supersedes or relates to previous ones
  9. Format the ADR using the standard template: Title, Status, Context, Decision, Consequences
  10. Save the ADR as docs/adr/NNNN-title-slug.md with zero-padded number
  11. Update the ADR index file if one exists
  12. Report the created ADR path and number

Rules

  • Follow the Michael Nygard ADR format (Title, Status, Context, Decision, Consequences)
  • Number ADRs sequentially with zero-padded 4-digit numbers (0001, 0002)
  • Keep the title concise and descriptive of the decision, not the problem
  • Include at least two alternatives that were considered
  • Document consequences honestly, including negative trade-offs
  • Never modify existing accepted ADRs; create a new one that supersedes
  • Create the docs/adr directory if it does not exist
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. 3d ago First seen · 29 lines · 0 tokens per session scan A 92e03564ef1c

Subscribe to this mod's changes

write-adr is a command published in the GitHub repository rohitg00/awesome-claude-code-toolkit (2,578 stars, last pushed 3mo ago), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 324 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.