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.
npx agentmods add skills/mbeacom/adrkit/decision-memorynpx skills add mbeacom/adrkit --skill decision-memorygit clone --depth 1 https://github.com/mbeacom/adrkitWhat 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 | $0.00071 | $0.02176 |
| Opus 5 | $0.00036 | $0.01088 |
| Sonnet 5 | $0.00014 | $0.00435 |
| Haiku 4.5 | $0.00007 | $0.00218 |
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.
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:
- Planning against decisions nobody loaded → re-litigation.
- Treating a
proposeddecision as settled → planning on an open question. - Ignoring
rejectedandsupersededrecords → 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: superseded — only 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.
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.
- 2d ago First seen · 200 lines · 71 tokens per session scan A aa693280f866
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.
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.…
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…
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.
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.
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.
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.