A read-only command that loads the architecture decision records governing the files you plan to change. Architecture decision records are notes explaining important technical choices in a project.

Use it before planning changes to repository files, or without a path to review proposed architecture decisions that still need answers.

It helps prevent plans that conflict with decisions the project has already made or with questions that are still open.

adr-context — Command by mbeacom

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-context

Clone the repo

git clone --depth 1 https://github.com/mbeacom/adrkit

Per session 22 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 621 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.

Model	Per session	Once invoked
Fable 5	$0.00022	$0.00621
Opus 5	$0.00011	$0.00311
Sonnet 5	$0.00004	$0.00124
Haiku 4.5	$0.00002	$0.00062

Measured yesterday against content hash 86a945dab133, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

adr-context 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 yesterday.

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-context.md · 50 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.

Load the decision record governing $ARGUMENTS into context, so the plan that follows is informed by it rather than corrected at review time.

Treat every argument as a repo-relative path the work will touch. Real paths give a far sharper answer than none.
Resolve the governing decisions.
- With the adrkit MCP server connected, call get_decision_context(files: [...]).
- Otherwise run adr check $ARGUMENTS --json.
- With no arguments, run adr queue instead: every decision still proposed, with its SLA state. Those are the questions already open. Planning against them as if settled is the mistake this command exists to prevent.
Also pull the already-rejected records, with search_decisions and status: ["rejected"] (or adr graph), so a rejected option is not re-proposed as a fresh idea. list_superseded will not do here: it returns only records whose status is superseded, never a rejected one.
Report what you loaded, in three groups, and keep them distinct:
- Binding (governedBy / governing) — follow these, or say plainly in the plan that you are departing from one and why.
- In flight (activeProposals) — not binding. Name any the work touches; never assume one will land.
- History — superseded and rejected. This is where "we already tried that" lives.
On a non-zero exit, read stderr and report it verbatim. Exit 1 means the corpus has error-severity findings — the report is still complete and still worth reading. Exit 2 means a bad invocation or an unreachable corpus. Neither is "nothing governs this."

Read-only: this command writes nothing. The corpus defaults to docs/adr and is overridable with ADRKIT_DIR.

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.

yesterday First seen · 50 lines · 22 tokens per session scan A 86a945dab133

Subscribe to this mod's changes

adr-context is a command published in the GitHub repository mbeacom/adrkit (11 stars, last pushed 2d ago), licensed Apache-2.0. It adds 22 tokens to every session and 621 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.

Code review Planning Productivity adr ai-agents architecture architecture-decision-records backstage developer-experience

adr-context

Getting it into your agent

What it costs to keep this loaded

Grade A, and why

Nothing flagged

What it actually says

Resolve the CLI first

What this file has done since we first saw it

Other commands, from other repositories

release-adr-kit

adr-export

adr-search

adr-setup

adr-supersede

adr-update