New: 98,000+ skills indexed from GitHub repos with 100+ stars · every skill safety-checkedBrowse top skillsTop skills
Esc to closeBrowse all skills
Submit a skillBrowse skills
Submit a skillBrowse skills

Agent skill

Agent Carnet Notebook

by yamadashy in yamadashy/repomix

Saves and recalls markdown notes between agent sessions with the agent-carnet CLI, tracking which notes proved useful so stale ones expire and good ones stay.

MITAuto-check passedKnowledge Management

Install Agent Carnet Notebook

skills CLI
$ npx skills add yamadashy/repomix --skill agent-carnet -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install yamadashy/repomix agent-carnet --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/yamadashy/repomix.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.agents/skills/agent-carnet .claude/skills/agent-carnet && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
agent-carnet
GitHub stars
29k
Token cost
~1.2k tokens
SKILL.md length
509 words
Files
3 (incl. references)
Skills in repo
6
Repo updated
First seen
Licence
MIT

At a glance

Saves and recalls markdown notes between agent sessions with the agent-carnet CLI, tracking which notes proved useful so stale ones expire and good ones stay.

  • Saving a gotcha or decision so a later session can find it
  • SKILL.md covers Quick reference, When to save, When to recall and When to call used, plus 3 more sections
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md
  • Checking the notebook for prior findings before starting related work

What it does

Agent Carnet is a small CLI that keeps a shared markdown notebook on disk under a `.carnet/` folder, one file per note grouped by category. Notes have a default lifespan of 30 days that resets whenever they are read or applied, so useful ones survive and stale ones move to a `.trash/` folder on their own. The agent saves proactively when it finds something worth keeping across sessions: costly research findings, non-obvious gotchas, fixes to tricky problems, architectural decisions with their reasoning and in-progress work.

Every save needs a decisive `--summary` and `--agent claude-code`, and the summary should tell the next reader whether to read further. Recall uses `find` for a quick scan of summaries, `list` to browse a category and `show` to read a note, which refreshes its last-used date. After a note actually shaped the work, the agent calls `used`, which also increments a use count that marks load-bearing notes; merely reading does not count. Each subcommand prints its own help with `-h`, and reference files cover a cookbook and the frontmatter format.

When your agent uses it

  • Saving a gotcha or decision so a later session can find it
  • Checking the notebook for prior findings before starting related work
  • Marking a saved note as useful after it solved a problem

Example prompts

  • “Remember this: iconv-esm types are broken, so pin to the previous version.”
  • “What did we discuss about the retry logic? Check the notebook.”
  • “Find anything in carnet about the deployment pipeline.”

Requirements

  • The `agent-carnet` CLI on PATH

What it can do on your machine

Read from SKILL.md and the folder at commit 8d64291. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    No scripts in the folder and no shell commands in SKILL.md (its code samples are bash).

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Agent Carnet Notebook loads about 1.2k tokens when it runs, and up to ~3.9k if it reads all its reference files. Until then it costs about 74 tokens; SKILL.md has 509 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~74
When it runs · the whole SKILL.md, loaded when a task matches
~1.2k
With references · SKILL.md plus every file in references/, read only if the agent opens them
~3.9k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from yamadashy/repomix at commit 8d64291, republished under its MIT licence (© yamadashy). 509 words, ~1,179 tokens.

Download SKILL.mdSave it as .claude/skills/agent-carnet/SKILL.md (or your agent's skills folder). This skill also uses 2 other files; get the full folder from GitHub.
name
agent-carnet
description
Use this skill when the user asks to save, recall, find, or organize notes. Triggers on: 'remember this', 'save this', 'note this', 'what did we discuss about...', 'check the notebook', 'find in carnet'. Also use proactively when discovering findings worth preserving across sessions.
metadata.internal
true

Agent Carnet

A tiny CLI that gives you a shared markdown notebook on disk under .carnet/<category>/<slug>.md. Notes have a 30-day default lifespan that resets every time they are read or applied; useful ones survive, stale ones drift to .trash/ automatically.

Quick reference

bash
# Save (always pass --summary and --agent claude-code)
echo "body content" | agent-carnet save deps/iconv-issue \
  --summary "iconv-esm v0.7 types broken — pin to v0.6" \
  --agent claude-code \
  --tags compat,esm

# Recall
agent-carnet find iconv               # search summaries (does NOT bump lifespan)
agent-carnet list                     # category-grouped overview, sorted by last_used
agent-carnet list --sort use_count    # most-applied notes first
agent-carnet show deps/iconv-issue    # read full content (bumps last_used; weak use signal)

# Mark as actually applied (strong use signal — bumps last_used + use_count)
agent-carnet used deps/iconv-issue

# Maintain
agent-carnet move <from> <to>
agent-carnet rm <path> --yes

When unsure of a subcommand's full flag set, run agent-carnet <command> -h (e.g. agent-carnet save -h, agent-carnet used -h). Each subcommand prints its own focused help — required arguments, options, and examples — without invoking filesystem operations.

When to save

Save proactively when you discover something worth preserving across sessions:

  • Research findings that took effort to derive
  • Non-obvious patterns / gotchas in the codebase
  • Solutions to tricky problems
  • Architectural decisions and the reasoning behind them
  • In-progress work that may be resumed later

When to recall

Before starting related work or when context might exist:

  • agent-carnet find <topic> — quick scan of summaries
  • agent-carnet list <category> — browse a folder
  • agent-carnet show <path> — actually read (resets last_used; only use when the content matters)

When to call used

Call agent-carnet used <path> after a carnet actually shaped your work:

  • You applied the recorded fix and it solved the bug.
  • You consulted the carnet before retrying a hypothesis and skipped a dead-end.
  • You used the canonical name from a vocab carnet in new code instead of inventing your own.

used increments use_count — a durable importance signal that survives across sessions and lets future readers (and agent-carnet list --sort use_count) surface load-bearing notes.

Reading a carnet does NOT count. show already keeps it alive (weak signal); used records that the note was worth keeping for a real reason (strong signal).

Show full SKILL.md (246 more words)Show less

Hard rules

  • --summary is required. Make it decisive — reading the summary in isolation tells the next reader (or the next agent) whether to read further.
  • --agent claude-code is required.
  • find does NOT bump anything. show bumps last_used. used bumps last_used AND increments use_count.
  • updated tracks content modification only (save, save --update). It is independent of last_used and is not the lifespan driver.
  • The 30-day expiry is automatic — do not manually clean up. keep: true pins permanent notes.
  • Auto-prune runs on every CLI invocation; deleted carnets land in .carnet/.trash/ for 7 days before hard delete.

Path conventions

  • <category>/<slug> — kebab-case, no leading slash, no ...
  • Categories are folders; create new ones freely as needed.
  • Subcategories are allowed: deps/esm/iconv-issue works.

When to read references/

This SKILL.md is enough for everyday note-keeping. Open the references/ files only when one of these specific cases applies — they are not always-on context, so do not load them speculatively.

Read this fileWhen
references/cookbook.mdYou are about to use (or are being asked about) a tag-based pattern such as tags: [vocab] for project terminology or tags: [hypothesis] for debugging dead-ends. The file shows the full pattern, including how to structure the body and meta: for that pattern.
references/frontmatter.mdYou need to write or read the meta: extension namespace, set a non-trivial lifespan / keep, or understand why an unfamiliar frontmatter field is or is not preserved on save.

If neither case applies, do not read references/. The base of this file already covers daily save/find/show/touch/move/rm flows.

© yamadashy, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 2 other files (references) in .agents/skills/agent-carnet of yamadashy/repomix.

  • SKILL.md
  • references/cookbook.md
  • references/frontmatter.md

Open the folder on GitHubat commit 8d64291

Compare with similar skills

Agent Carnet Notebook next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Agent Carnet Notebook compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Agent Carnet Notebook this skillyamadashy/repomix29k—~1.2kAutomated safety check: PassMIT
AI BrainOotto-AI/claude-content-skills130—~1.1kAutomated safety check: PassMIT
Obsidian Project Memorybrycewang-stanford/Auto-Empirical-Research-Skills4.6k—~2.4kAutomated safety check: PassCustom licence
Using LWC Memory and Graphssickn33/agentic-awesome-skills47k1 repos~2kAutomated safety check: PassApache-2.0
Basic Memory Onboardingbasicmachines-co/basic-memory4.1k—~3.4kAutomated safety check: PassAGPL-3.0
Memory Reflectbasicmachines-co/basic-memory4.1k1 repos~763Automated safety check: PassAGPL-3.0

Similar skills

  • AI Brain

    Ootto-AI/claude-content-skills

    Give Claude a permanent, searchable long-term memory using an Obsidian vault as the store.

    130 GitHub stars~1.1k tokensUpdated 2 days ago
    Knowledge ManagementAuto-check passed

  • Obsidian Project Memory

    brycewang-stanford/Auto-Empirical-Research-Skills

    This skill should be used when the user asks to maintain an Obsidian knowledge base for a research project, import an existing research repository into Obsidian, keep project memory or daily notes…

    4.6k GitHub stars~2.4k tokensUpdated 5 days ago
    Knowledge ManagementAuto-check passed

  • Using LWC Memory and Graphs

    sickn33/agentic-awesome-skills

    Keeps project decisions, research and verified results available across coding-agent sessions through LWC memory, a document Wiki graph and a CodeGraph code index.

    47k GitHub starsUsed in 1 repo~2k tokens
    Agent WorkflowsAuto-check passed

  • Basic Memory Onboarding

    basicmachines-co/basic-memory

    Guides a newcomer to Basic Memory through designing a personal knowledge system, then teaches its use and sets up their assistant to load it each session.

    4.1k GitHub stars~3.4k tokensUpdated today
    Knowledge ManagementAuto-check passed

  • Memory Reflect

    basicmachines-co/basic-memory

    Sleep-time memory reflection: review recent conversations and daily notes, extract insights, and consolidate into long-term memory.

    4.1k GitHub starsUsed in 1 repo~763 tokens
    Knowledge ManagementAuto-check passed

  • Trusty Memory

    bobmatnyc/claude-mpm

    Persistent memory palace system with hierarchical storage (palace/wing/room/closet/drawer), progressive retrieval (L0-L3), and temporal knowledge graph for cross-session context

    156 GitHub stars~2k tokensUpdated 1 mo ago
    Agent WorkflowsAuto-check passed

More from yamadashy/repomix

  • Contextual Commit Messages

    yamadashy/repomix

    Writes Conventional Commits whose bodies carry action lines recording the intent, decisions and constraints behind a change, not only what changed.

    29k GitHub starsUsed in 1 repo~2.7k tokens
    Auto-check passed

  • Repomix Codebase Packer

    yamadashy/repomix

    Packs a local directory or remote GitHub repository into one AI-friendly file with Repomix, then searches it to explore structure, find patterns and count tokens.

    29k GitHub stars~1.3k tokensUpdated today
    Auto-check: notes

  • Repomix Browser Extension Developer

    yamadashy/repomix

    Use this skill when developing or maintaining browser extension code in the `browser/` directory, including Chrome/Firefox/Edge compatibility, content…

    29k GitHub starsUsed in 1 repo~288 tokens
    Auto-check passed

  • Repomix Codebase Explorer

    yamadashy/repomix

    Packs a local or remote repository into a single AI-friendly file with the Repomix CLI, then reads and searches that output to explain structure, find patterns or report metrics.

    29k GitHub stars~2.7k tokensUpdated today
    Auto-check passed

  • Repomix Website Maintainer

    yamadashy/repomix

    Guides edits to the Repomix documentation site's VitePress configuration, per-language content, and translation workflow across 14 languages.

    29k GitHub starsUsed in 1 repo~342 tokens
    Auto-check passed

Categories

Questions about Agent Carnet Notebook

What does Agent Carnet Notebook do?

Saves and recalls markdown notes between agent sessions with the agent-carnet CLI, tracking which notes proved useful so stale ones expire and good ones stay. carnet/` folder, one file per note grouped by category.trash/` folder on their own.

When should I use Agent Carnet Notebook?

Agent Carnet Notebook fits situations like: saving a gotcha or decision so a later session can find it; checking the notebook for prior findings before starting related work; marking a saved note as useful after it solved a problem.

How do I install Agent Carnet Notebook in Claude Code?

Run `npx skills add yamadashy/repomix --skill agent-carnet -a claude-code`. Or copy the skill folder (.agents/skills/agent-carnet in yamadashy/repomix) into .claude/skills/agent-carnet in your project. Claude Code loads it when a task matches its description.

How do I install Agent Carnet Notebook in Codex?

Run `npx skills add yamadashy/repomix --skill agent-carnet -a codex`. Or copy the skill folder (.agents/skills/agent-carnet in yamadashy/repomix) into .agents/skills/agent-carnet in your project. Codex loads it when a task matches its description.

Can I use Agent Carnet Notebook in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add yamadashy/repomix --skill agent-carnet -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/agent-carnet, .gemini/skills/agent-carnet, .github/skills/agent-carnet and .opencode/skills/agent-carnet in your project.

What does Agent Carnet Notebook need to run?

SKILL.md names no scripts, command-line tools or credentials: Agent Carnet Notebook is instructions for the agent only. Our summary lists: The `agent-carnet` CLI on PATH.

Does Agent Carnet Notebook access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Agent Carnet Notebook safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Agent Carnet Notebook use?

Agent Carnet Notebook is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Agent Carnet Notebook use?

About 1.2k tokens (SKILL.md is roughly 4.7k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 2.7k tokens, read only when the agent opens those files.

What are the alternatives to Agent Carnet Notebook?

Skills that share tags, products or a category with Agent Carnet Notebook: AI Brain (Ootto-AI/claude-content-skills, 130 stars), Obsidian Project Memory (brycewang-stanford/Auto-Empirical-Research-Skills, 4.6k stars), Using LWC Memory and Graphs (sickn33/agentic-awesome-skills, 47k stars) and Basic Memory Onboarding (basicmachines-co/basic-memory, 4.1k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Agent Carnet Notebook?

yamadashy (a GitHub user) maintains it in yamadashy/repomix, which has 28,780 GitHub stars. The repository holds 6 skills in this directory. The repository was last updated on October 10, 2026.

Source: yamadashy/repomix on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.