agentleFS
Sign inStart free
AN0099AN0099/toothpaste-kit/skills/jot/SKILL.md

jot

Skill1 starsChanged 20 days agoApache-2.0View on GitHub

Agent-callable micro-capture at a clean boundary; appends one short marked entry of decisions, corrections and findings to the day's capture file. Costs about one reply. Does not replace or satisfy session-log or session-close.

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

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈1

    Distinctive · estimate

    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:

    Read any file to confirm what it writes.

    line 29
  2. Very specific:

    Run when compaction is near.

    line 32

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “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

When to Use

Right after a commit, a dispatch, or a closed decision, when something from the stretch just finished would be lost to compaction and the person is not about to run session-log. Called by the agent. The shared rules, marker and placement are in docs/partial-captures.md; read that first.

What to write

One entry, fifteen lines at most, under ## HH:MM [jot] <what the stretch was>, time from date. Answer only these, and skip any with nothing in it:

  1. Decisions and the alternative rejected.
  2. Corrections. What was stated as fact and turned out wrong, and what corrected it.
  3. Findings the tree does not hold. Established by evidence, recorded by no file.

These are session-log's first, second and fourth questions. Its open questions and its where-the-work-stands paragraph are left out on purpose: open questions belong in the flag register, where touch can put them, and the restart paragraph is only worth writing when a restart is near, which is session-log's moment.

What it must not do

  • Read any file to confirm what it writes. If unsure, write the uncertainty.
  • Restate what a file on disk already says.
  • Edit anything other than appending its entry. Standing files are touch's.
  • Run when compaction is near. Prompt the person to run session-log instead.

Scope Pointer

  • session-log: the person-run capture this is the small sibling of. A jot does not satisfy it.
  • touch: the other partial. It records facts in standing files; this records reasoning.
  • session-close: resets the partial count. Nothing here substitutes for any part of it.
<!-- SPDX-FileCopyrightText: 2026 Aidan Naveja SPDX-License-Identifier: Apache-2.0 -->

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.

Check your setup, free