agentleFS
TheKontextCoTheKontextCo/kontext-claude-plugin/skills/log-decision/SKILL.md

log-decision

Skill1 starsChanged 3 months agoMITView on GitHub

Record a technical decision in Kontext with its rationale and rejected alternatives

7 other projects use a version of this.

Adopted by

Most recently taken up by

The file

We split this skill into the rules it gives an agent

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

  • 0

    Common

    Most of the 7 edited versions we read keep these.

  • 1

    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:

    Use only what the conversation or the records you actually read support.

    line 27
  2. Very specific:

    When the decision bears on a specific task or document, link it with manage_relationship and a concise rationale for the link itself.

    line 38

“Common” is measured: kept by at least 6 in 10 of the 7 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

Log a decision

Record this decision in Kontext: $ARGUMENTS

With no argument, use the decision this session just reached. If the session reached more than one, ask which — do not log all of them as a batch.

What makes it worth reading later

The decision alone has almost no value in six months. The reasoning does. Capture:

  • Decision — what was chosen, in one line.
  • Context — what forced the choice. The constraint, the bug, the scaling limit.
  • Alternatives rejected — what else was on the table and why it lost. This is the part a future session cannot reconstruct from the code.
  • Consequences — what this now commits the project to, and what it rules out.
  • Status — settled, or provisional and worth revisiting under what condition.

Use only what the conversation or the records you actually read support. Do not invent a rationale to fill out the shape, and do not upgrade a guess into a stated reason. If the "why" was never established in this session, ask the user for it rather than fabricating it.

Write it

  1. search_context first — if this supersedes an earlier decision, update that record and note what changed rather than leaving two contradictory entries in the Space.
  2. list_projects and set projectId so the decision lands in the right workstream.
  3. manage_document with a title that states the decision, not the topic: "Postgres over schema-per-tenant for isolation", not "Database notes".
  4. When the decision bears on a specific task or document, link it with manage_relationship and a concise rationale for the link itself.

Report back with the markdownLink.

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.