adr-queue

A read-only command that lists proposed architecture decisions still waiting for review, along with their service-level-agreement (SLA) status.

In plain words
What is it for?
Use it to see which decisions are open, how urgent they are, and whether planned work depends on an unresolved proposal.
Why use it?
It makes unanswered questions visible before current work quietly depends on them.

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/mbeacom/adrkit/adr-queue
Clone the repo
git clone --depth 1 https://github.com/mbeacom/adrkit
Per session 29 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 484 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 $0.00029 $0.00484
Opus 5 $0.00015 $0.00242
Sonnet 5 $0.00006 $0.00097
Haiku 4.5 $0.00003 $0.00048

Measured 2d ago against content hash 5ffb37a01f93, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

adr-queue 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.

packages/adapters/agent-plugin/commands/adr-queue.md · 44 lines

What it actually says

Resolve the CLI first

Try, in order: $ADRKIT_CLI, then ./node_modules/.bin/adr, then adr on PATH. @adrkit/cli is normally a dev dependency, so a bare adr is not on PATH in most projects — trying only that and concluding "no CLI is available" is a false negative. If all three fail, say so and tell the user to install @adrkit/cli. Never fall back to reading ADR frontmatter by hand: it cannot expand glob matchers, cannot read inbound @adr markers, and has no exit code, so it produces an answer that looks complete and is not.

Show the decisions still awaiting review.

adr queue $ARGUMENTS

--as-of YYYY-MM-DD computes SLA state as of a chosen UTC date (default: today). --format json emits QueueReport v1 instead of markdown. Identical inputs produce byte-for-byte identical output, so this is safe to diff across runs.

Report:

  1. What is open, ordered by SLA urgency — overdue first. Each entry is a question the team has not answered yet.
  2. What that means for current work. Any proposal touching what is being planned right now is a dependency on an unmade decision. Name it. Do not plan as though it will land.
  3. Corpus findings. corpus.file-skipped warnings mean records discovery could not see — misnamed, or nested below the corpus root. Those are proposed decisions that would otherwise vanish from the queue silently, so surface them rather than passing over them. Being warn, they do not change the exit code.

Exit codes: 0 report with no error-severity corpus findings; 1 report emitted complete, with one or more; 2 usage error or unreachable corpus directory. A 1 is still a full report — read it.

Read-only.

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 · 44 lines · 29 tokens per session scan A 5ffb37a01f93

Subscribe to this mod's changes

adr-queue is a command published in the GitHub repository mbeacom/adrkit (11 stars, last pushed 2d ago), licensed Apache-2.0. It adds 29 tokens to every session and 484 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.