v-adr

A command for recording one genuine architecture decision in an ADR, a short document describing the context, chosen option, alternatives, and consequences.

In plain words
What is it for?
Use it to draft and, after human confirmation, commit a numbered decision record with verified references under the project’s architecture-decision directory.
Why use it?
It preserves why an important technical choice was made, including what was given up, so the reasoning can be found later.

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/procoders/superpowers-v/v-adr
Clone the repo
git clone --depth 1 https://github.com/procoders/superpowers-v
Per session 73 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 469 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 $0.00073 $0.00469
Opus 5 $0.00036 $0.00234
Sonnet 5 $0.00015 $0.00094
Haiku 4.5 $0.00007 $0.00047

Measured 2d ago against content hash e6af814a61d1, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

v-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/v-adr.md · 31 lines

What it actually says

You are running /v:adr — thin ADR capture. The decision to record is {{args}}.

Branch on {{args}}:

  • Empty → ask: "What architecture decision should I capture? Name the choice, at least one alternative you weighed, and what it trades away." Then proceed.
  • A decision description → capture it per the discipline below.

The authoritative flow lives in skills/compound-v/adr-capture.md — read it and apply it. In short:

  1. Litmus test. Only capture a genuine decision — a real alternative existed and something was traded away. If not, decline and say why; do not manufacture an ADR.
  2. Draft the context / decision / consequences record in-message, with the target path docs/superpowers/adr/NNNN-slug.md (next unused number).
  3. References MUST exist. Verify every cited path/section/URL before confirming — drop any you can't vouch for. A fabricated citation is worse than none.
  4. Human-confirm. Write nothing until the human approves the draft. No auto-write.
  5. Commit with the two-command discipline (git add then a separate git commit, no &&, check each exit code) — an uncommitted ADR is invisible to recall and can be lost on worktree cleanup.
  6. Then it's FTS5-recallable: python3 scripts/compound-v-memory.py refresh and confirm with search.

Out of scope: C4 diagrams and SAD / full-architecture documents. This captures an ADR and nothing else — if asked for a diagram or an architecture write-up, say so and stop at the ADR.

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 · 31 lines · 73 tokens per session scan A e6af814a61d1

Subscribe to this mod's changes

v-adr is a command published in the GitHub repository procoders/superpowers-v (35 stars, last pushed 3d ago), licensed MIT. It adds 73 tokens to every session and 469 once invoked, about $0.0004 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.