agentleFS
Sign inStart free
CitabilityCitability/claude-code-adhd-skills/AGENTS.md

claude-code-adhd-skills

AGENTS.md0 starsChanged 2 months agoMITView on GitHub

This file is the map for a coding agent asked to install or change claude-code-adhd-skills. Read it after cloning. It explains where the skills live, how they are loaded, and how to verify an install. It does not replace the rules inside each SKILL.md. Preferred path, plugin marketplace: Fallback path, plain copy (works on any Claude Code version that reads ~/.claude/skills/): Project-only install: copy the two directories into the repo's .claude/skills/ instead. After either path, tell the user to restart…

  • Where files are headingNew AGENTS.md files have more rules about keeping secrets out of the code, and fewer about code style.

    Of the AGENTS.md files we read, the 31,774 first seen in the last six months, against the older ones: the kind of rule that gained most share, and the kind that lost most. About files like this in general, not this one, and an estimate, since a kind is a pattern in the words.

  • In this repository3 other files it gives its agents.

The file

We split this AGENTS.md into the rules it gives an agent

3 rules. About 0 are common, 0 are distinctive, and 3 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈0

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 3

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    After either path, tell the user to restart Claude Code, then type /mirror.

    line 24
  2. Very specific:

    Do not modify shell profiles, global git config, or any file outside ~/.claude/skills/ (or the project's .claude/skills/).

    line 26
  3. Very specific:

    Keep name: in each SKILL.md frontmatter equal to its directory name.

    line 49

≈ “Common” is an estimate: at least 1 in 5 of the 40,246 AGENTS.md 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
AGENTS.md

Agent guide

This file is the map for a coding agent asked to install or change claude-code-adhd-skills. Read it after cloning. It explains where the skills live, how they are loaded, and how to verify an install. It does not replace the rules inside each SKILL.md.

Install for the user (Claude Code)

Preferred path, plugin marketplace:

claude plugin marketplace add Citability/claude-code-adhd-skills
claude plugin install adhd-skills@adhd-skills

Fallback path, plain copy (works on any Claude Code version that reads ~/.claude/skills/):

git clone https://github.com/Citability/claude-code-adhd-skills.git
mkdir -p ~/.claude/skills
cp -r claude-code-adhd-skills/mirror claude-code-adhd-skills/librarian ~/.claude/skills/

Project-only install: copy the two directories into the repo's .claude/skills/ instead.

After either path, tell the user to restart Claude Code, then type /mirror.

Do not modify shell profiles, global git config, or any file outside ~/.claude/skills/ (or the project's .claude/skills/). Do not run anything else from this repository on the user's behalf.

Verify the install

test -f ~/.claude/skills/mirror/SKILL.md && test -f ~/.claude/skills/librarian/SKILL.md && echo ok

For the plugin path, claude plugin list should show adhd-skills.

Repository map

AreaLocationPurpose
mirrormirror/SKILL.mdEvidence-based reflection of what the user actually shipped. Reads git log, git diff, and the conversation. Standalone.
librarianlibrarian/SKILL.mdWalks a project knowledge graph at docs/codex/ and returns a three-line readback with an evidence label. Needs a codex.
Plugin metadata.claude-plugin/plugin.json, .claude-plugin/marketplace.jsonClaude Code plugin and marketplace manifests.
DocsREADME.md, this fileUser-facing overview and this agent map.

Source-of-truth rules

  • The two SKILL.md files are copied unedited from the author's live ~/.claude/skills/. Changes land there first, then here, the same day.
  • librarian reads docs/codex/INDEX.json, docs/codex/nodes/*.md, and docs/codex/PRINCIPLES.md. It does not create a codex. If the repo has none, it says so and stops.
  • Keep name: in each SKILL.md frontmatter equal to its directory name; Claude Code uses it as the slash command.

Verification before proposing a change

claude plugin validate .

Report the exact command and its output. Do not treat reading a file as running a check.

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