agentleFS
theagentplanetheagentplane/tokenops/.claude/skills/adr/SKILL.md

adr

Skill84 starsChanged 29 days agoMITView on GitHub

Write or update an Architecture Decision Record in docs/adr. Use when a decision affects structure, a public interface, a data format, a dependency, or another repository, or when asked to "record a decision" or "write an ADR". Also use before proposing a change that might conflict with an existing ADR.

90 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use fdr, runbook and 10 more.

Other files people use alongside this one.

Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
  • thiagofgfSkill

    fdr

    Use when creating, changing, reviewing, retiring, auditing, or backfilling implemented user-visible feature behavior, permissions, feature-specific rationale, tradeoffs, or relationships to architectural decisions.

    Also in 3 projects that use this

  • AnthropicSkill

    runbook

    Create or update an operational runbook for a recurring task or procedure. Use when documenting a task that on-call or ops needs to run repeatably, turning tribal knowledge into exact step-by-step commands, adding troubleshooting and rollback steps to an existing procedure, or writing escalation paths for when things go wrong.

    Also in 5 projects that use this

  • drewdrewthisSkill

    sweep

    Search for similar patterns, anti-patterns, or issues elsewhere in the codebase after a fix or feature. Use after implementing a fix to catch the same bug in other places, or proactively to audit for a known pattern.

    Also in 4 projects that use this

  • vndeeSkill

    product-spec

    Use when starting a new feature, product, or project — before any architecture or code, to define what to build and why

    Also in 3 projects that use this

  • OpenAISkill

    threat-model

    Use when Codex is already in the threat-modeling phase of a security scan, the user explicitly invokes $threat-model, or the user explicitly asks to create, update, or persist a repository threat model. Do not use as the primary trigger for full PR, commit, branch, patch, or repository scans.

    Also in 6 projects that use this

  • montymiSkill

    tech-spec

    Parse and review Technical Specification documents for completeness, consistency, and implementation readiness

    Also in 3 projects that use this

The file

We split this skill into the rules it gives an agent

5 rules. 0 are common, 4 are distinctive, and 1 is very specific to this project.

  • 0

    Common

    Most of the 74 edited versions we read keep these.

  • 4

    Distinctive

    This author's own choices. Worth a look.

  • 1

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Write one when the decision changes structure, a public interface, a data format or schema, a significant dependency or tool, is hard to …

    line 13
  2. Distinctive:

    Keep it to about one page.

    line 37
  3. Very specific:

    Add a row to the index table in docs/adr/README.md.

    line 49
  4. Distinctive:

    Never rewrite an accepted ADR's content.

    line 53
  5. Distinctive:

    Write a new ADR, set its "Supersedes" field, and in the old ADR change only the status to

    line 54

“Common” is measured: kept by at least 6 in 10 of the 74 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Writing an Architecture Decision Record

ADRs live in docs/adr/. The rules and index are in docs/adr/README.md; the template is docs/adr/template.md. Read the README first.

1. Decide whether an ADR is needed

Write one when the decision changes structure, a public interface, a data format or schema, a significant dependency or tool, is hard to reverse, or affects another repository. Do not write one for a bug fix, a rename or a small refactor. If unsure, ask the user.

2. Check what already exists

List docs/adr/. Read ADRs that touch the same area. If the new decision conflicts with an accepted ADR, it must supersede it explicitly; do not quietly contradict it.

3. Create the file

  • Number: the highest existing NNNN plus one, zero-padded to four digits.
  • Name: docs/adr/NNNN-short-kebab-title.md. The title states the decision in present tense ("Use X for Y"), not the topic ("Y storage").
  • Copy docs/adr/template.md and fill it in.

4. Fill it in honestly

  • Context: verifiable facts only. Read the code or documents rather than guessing.
  • Options considered: the real alternatives, each with honest good and bad points.
  • Decision: one clear sentence, then the reasons that decided it.
  • Consequences: include what gets worse or riskier. An ADR with only benefits is unfinished.
  • Impact on other repositories: list each affected repo (chronicle, primitives, control-plane, tokenops) and what must change there, or write "none".
  • Keep it to about one page; link to longer material.
  • If you do not know the reasoning or the alternatives that were weighed, ask the user. Never invent rationale.

5. Status and people

  • Set status to Proposed. Only set Accepted when the user says the decision has been made, and then record who decided in the Deciders field. Use the names of people, not "Claude".
  • Set the date to today.

6. Update the index

Add a row to the index table in docs/adr/README.md.

7. Superseding or changing a decision

  • Never rewrite an accepted ADR's content. Fixing a typo is fine.
  • Write a new ADR, set its "Supersedes" field, and in the old ADR change only the status to Superseded and add a "Superseded by" link.

8. Report back

Tell the user the file path, the one-sentence decision, and any open question you could not answer without them.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.