promote-to-adr

promote-to-adr is a command for Claude Code, Cursor from codeready-toolchain/tarsy. It costs 0 tokens per session (771 once invoked), scanned A, original, Apache-2.0.

A command that turns an implemented proposal into an Architecture Decision Record, or ADR. An ADR is a short record of an important technical choice and the reasons behind it.

In plain words
What is it for?
Use it to move completed proposals from docs/proposals/ to docs/adr/ and summarize what was decided and why.
Why use it?
It preserves the decisions made during development without keeping a full proposal as the permanent record. It also gives architectural choices a consistent place and number.

Command for Claude CodeCursor

Written for Cursor and Claude Code: installed under .cursor/, but also a Claude Code command (commands/*.md).

Good fit Use it to move completed proposals from docs/proposals/ to docs/adr/ and summarize what was decided and why.

Compare 6 commands from other repositories ↓
Install with agentmods
npx agentmods add commands/codeready-toolchain/tarsy/promote-to-adr
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.

Clone the repo
git clone --depth 1 https://github.com/codeready-toolchain/tarsy

Made for: Claude Code, Cursor.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for promote-to-adr

README.md
[![agentmods](https://agentmods.dev/badge/commands/codeready-toolchain/tarsy/promote-to-adr/github.svg)](https://agentmods.dev/commands/codeready-toolchain/tarsy/promote-to-adr)
Your own site
<a href="https://agentmods.dev/commands/codeready-toolchain/tarsy/promote-to-adr"><img src="https://agentmods.dev/badge/commands/codeready-toolchain/tarsy/promote-to-adr/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for promote-to-adr

Your own site · 80×15
<a href="https://agentmods.dev/commands/codeready-toolchain/tarsy/promote-to-adr"><img src="https://agentmods.dev/badge/commands/codeready-toolchain/tarsy/promote-to-adr.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
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 771 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.00000 $0.00771
Opus 5 $0.00000 $0.00385
Sonnet 5 $0.00000 $0.00154
Haiku 4.5 $0.00000 $0.00077

Measured 10d ago against content hash 4d4dc52eba79, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

promote-to-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 10d 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.

.cursor/commands/promote-to-adr.md · 67 lines

How it starts

The opening of the file, as written. The whole thing — 67 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Promote Proposal to ADR

Move an implemented proposal from docs/proposals/ to docs/adr/ as a numbered Architecture Decision Record.

The user will specify which proposal to promote (by name or file path). If unclear, ask.


Steps

  1. Determine the next ADR number. List docs/adr/ and find the highest existing NNNN- prefix. The new ADR gets the next sequential number, zero-padded to 4 digits (e.g., 0001, 0002).

  2. Read the design document (docs/proposals/{name}-design.md) in full.

  3. Check for a companion questions document (docs/proposals/{name}-questions.md). If it exists, read it and extract any decision rationale not already present in the design doc.

  4. Create the ADR at docs/adr/{NNNN}-{name}.md.

    Do NOT copy the proposal verbatim. Distill it into an architectural decision record. The ADR should capture what was decided and why, not how it was implemented file-by-file.

    Header:

    • Title: # ADR-{NNNN}: {Title} (use the existing title, drop suffixes like "— Design Document")
    • Status: Implemented
    • Date: today's date
    • Remove any references to the questions document

    What to KEEP (the decision record):

    • Overview / problem statement
    • Design principles
    • Decisions tables with rationale — this is the core of the ADR. If the design doc has a Decisions table, add a Rationale column with compact reasoning from the questions doc (if available)
    • Architecture: conceptual descriptions, ASCII diagrams, behavioral contracts, data flow
    • Configuration YAML examples (user-facing contract)
    • Conceptual tables (e.g., type mappings, enum values, API endpoints)
    • High-level migration strategy (e.g., "data-preserving migration with enum renames")
    • Future considerations
    • References to other ADRs

    What to REMOVE (implementation detail):

    • "Affected Files" tables and file-level change lists
    • "Implementation Plan" / "Implementation Phases" step-by-step checklists
    • Go/SQL/TypeScript/Python code snippets (struct definitions, function bodies, ent schemas)
    • File path references (e.g., pkg/agent/controller/factory.go) — use component names instead
    • Line number references
    • PR-level breakdowns
    • Risk assessments
    • Testing strategy sections

Read the full file on GitHub · 67 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. 10d ago First seen · 67 lines · 0 tokens per session scan A 4d4dc52eba79

Subscribe to this mod's changes

promote-to-adr is a command published in the GitHub repository codeready-toolchain/tarsy (10 stars, last pushed today), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 771 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 2026-08-31.