decision-memory

A set of instructions for working with architecture decision records (ADRs), written notes that explain important technical choices in a repository.

In plain words
What is it for?
Use it when planning, designing, reviewing, or changing code in a repository that stores ADRs, commonly in a docs/adr folder.
Why use it?
It keeps agents from planning against decisions they have not read or treating proposed, rejected, or replaced decisions as settled.

Skill for Claude CodeCodex

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 skills/mbeacom/adrkit/decision-memory
Any agent
npx skills add mbeacom/adrkit --skill decision-memory
Clone the repo
git clone --depth 1 https://github.com/mbeacom/adrkit

Made for: Claude Code, Codex.

Per session 71 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,176 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 $0.00071 $0.02176
Opus 5 $0.00036 $0.01088
Sonnet 5 $0.00014 $0.00435
Haiku 4.5 $0.00007 $0.00218

Measured 2d ago against content hash aa693280f866, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

decision-memory 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/skills/decision-memory/SKILL.md · 200 lines

How it starts

The opening of the file, as written. The whole thing — 200 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Decision memory

A repository's architecture decisions are usually written down once and then never read again, so every new plan re-litigates settled questions and every review discovers the conflict late. This skill closes that loop: read the decision record before planning, check the produced plan against it, and write a new record when the plan actually decides something.

The corpus is markdown with typed frontmatter under docs/adr (override with ADRKIT_DIR). Records carry a status, affects matchers binding them to code paths, and supersession edges.

The load-bearing idea

A decision you cannot find is a decision you will make again. Three failure modes follow, and each step below exists to prevent one:

  1. Planning against decisions nobody loaded → re-litigation.
  2. Treating a proposed decision as settled → planning on an open question.
  3. Ignoring rejected and superseded records → re-proposing something the team already tried and abandoned.

Retrieval: prefer the MCP tools, fall back to the CLI

If the adrkit MCP server is connected, use its tools — they are read-only and already scoped to this repository:

Tool Use it for
search_decisions Filtered search across the corpus, including status: ["rejected"]
get_decision One record by id
get_decision_context(files[]) The decisions governing a set of files
list_superseded Records with status: supersededonly those

list_superseded is narrower than the word "graveyard" suggests: it returns records whose status is superseded and never returns a rejected one. Use search_decisions with status: ["rejected"] for the "did we already rule this out?" check. Reaching for list_superseded there gets you a well-formed, empty answer and a re-proposed decision the team already rejected.

If the server is not connected, every retrieval below has a CLI equivalent. Do not silently skip the step because the tools are absent.

Read the full file on GitHub · 200 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. 2d ago First seen · 200 lines · 71 tokens per session scan A aa693280f866

Subscribe to this mod's changes

decision-memory is a skill published in the GitHub repository mbeacom/adrkit (11 stars, last pushed 3d ago), licensed Apache-2.0. It adds 71 tokens to every session and 2,176 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.

Related

Other skills, from other repositories

bootstrap

Scaffold or retrofit documentation-led conventions (AGENTS.md, CLAUDE.md, CONVENTIONS.md, ADR catalogue, plan/ queue, agent/ coordination) into a repo. Use when the user asks to "set up conventions", "bootstrap ADRs", "scaffold the documentation-led layout", "add AGENTS.md and a plan queue", or invokes /bootstrap.…

EvolveHQ/docflow · 118 tokens

actual

Feature-complete companion for the actual CLI, an ADR-powered CLAUDE.md/AGENTS.md generator. Runs and troubleshoots actual adr-bot, status, auth, config, runners, and models, plus the Actual AI platform surface: login, logout, whoami, and advisor (org-scoped architecture Q&A). Covers all 5 runners (claude-cli…

actual-software/actual-skill · 157 tokens

adr-integration

This skill should be used when the user asks about "ADR integration", "ADR CI/CD", "ADR tooling", "ADR automation", "export ADRs", "ADR documentation site", or needs guidance on integrating ADRs with CI/CD, documentation sites, and other tools.

zircote-plugins/adr · 59 tokens

adr-format-structured-madr

This skill should be used when the user asks about "structured MADR", "structured-madr", "frontmatter ADR", "comprehensive ADR", "auditable ADR", or needs guidance on creating ADRs using the Structured MADR format with YAML frontmatter and audit sections.

zircote-plugins/adr · 63 tokens

adr-decision-drivers

This skill should be used when the user asks about "decision drivers", "architectural forces", "quality attributes", "how to identify trade-offs", "non-functional requirements for ADRs", or needs help identifying, documenting, and weighing the forces that influence architectural decisions.

zircote-plugins/adr · 60 tokens

adr-format-madr

This skill should be used when the user asks about "MADR format", "MADR template", "Markdown Architectural Decision Records", "MADR 4.0", "MADR sections", or needs guidance on creating ADRs using the MADR (Markdown Architectural Decision Records) format.

zircote-plugins/adr · 63 tokens