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

Ruminate

by poteto in poteto/brainmaxxing

Mine past Claude Code conversations for uncaptured patterns, corrections, and knowledge.

MITAuto-check passed

Install Ruminate

skills CLI
$ npx skills add poteto/brainmaxxing --skill ruminate -a claude-code

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

GitHub CLI
$ gh skill install poteto/brainmaxxing ruminate --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/poteto/brainmaxxing.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.agents/skills/ruminate .claude/skills/ruminate && 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
ruminate
GitHub stars
320
Token cost
~1.1k tokens
SKILL.md length
548 words
Files
2 (incl. scripts)
Skills in repo
5
Repo updated
First seen
Licence
MIT

At a glance

Mine past Claude Code conversations for uncaptured patterns, corrections, and knowledge.

  • Works in 7 steps: Read the brain → Locate conversations → Extract conversations → …
  • SKILL.md covers Process and Guidelines
  • Runs Python scripts from its folder; calls python3 and sh

What it does

Ruminate is an agent skill from poteto/brainmaxxing. Mine past Claude Code conversations for uncaptured patterns, corrections, and knowledge. Cross-references with existing brain content. Triggers: "ruminate", "mine my history".

Its SKILL.md is about 1.1k tokens, which your agent loads only when the skill is triggered. The skill folder holds 2 other files, including scripts (for example `scripts/extract-conversations.py`).

The repository describes itself as: stupid simple persistent memory and skill improvement. The licence is MIT.

Example prompts

  • “ruminate”
  • “mine my history”
  • “/ruminate”

Requirements

  • Python 3

Workflow steps

7 steps, taken from the step headings in SKILL.md.

  1. Read the brain
  2. Locate conversations
  3. Extract conversations
  4. Spawn analysis team
  5. Synthesize
  6. Present and apply
  7. Clean up

What it can do on your machine

Read from SKILL.md and the folder at commit ec4d8e4. 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

    Ships 1 file in scripts/ (Python), which the agent can run.

    Shell commands in SKILL.md call:

    • python3
    • sh

    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

Ruminate loads about 1.1k tokens when it runs. Until then it costs about 46 tokens; SKILL.md has 548 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~46
When it runs · the whole SKILL.md, loaded when a task matches
~1.1k

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); the scripts in this folder are not scanned.

SKILL.md

The full file from poteto/brainmaxxing at commit ec4d8e4, republished under its MIT licence (© poteto). 548 words, ~1,117 tokens.

Download SKILL.mdSave it as .claude/skills/ruminate/SKILL.md (or your agent's skills folder). This skill also uses 1 other file; get the full folder from GitHub.
name
ruminate
description
Mine past Claude Code conversations for uncaptured patterns, corrections, and knowledge. Cross-references with existing brain content. Triggers: "ruminate", "mine my history".

Ruminate

Mine conversation history for brain-worthy knowledge that was never captured. Complements reflect (current session) and meditate (brain vault audit) by looking at the full archive of past conversations.

Process

1. Read the brain

Build a brain snapshot: sh .agents/skills/meditate/scripts/snapshot.sh brain/ /tmp/brain-snapshot-ruminate.md. Pass the snapshot path to each analysis agent. This avoids loading the full brain into the ruminate orchestrator's context.

2. Locate conversations

Find the project conversation directory:

~/.claude/projects/-<cwd-with-dashes-replacing-slashes>/
3. Extract conversations

Run the extraction script to parse JSONL conversation files into readable text and split into batches:

bash
python3 .agents/skills/ruminate/scripts/extract-conversations.py "$CONV_DIR" "$OUT_DIR" --batches N

Choose N based on the number of conversations found: ~1 batch per 20 conversations, minimum 2, maximum 10.

4. Spawn analysis team

Create an agent team (TeamCreate) with N agents (one per batch), each with subagent_type: general-purpose and model: opus. Run all N in parallel.

Each agent's prompt should include:

  • The batch manifest path ($OUT_DIR/batches/batch_N.txt)
  • The output path ($OUT_DIR/findings_N.md)
  • The list of topics already captured in the brain (compiled from step 1) — so agents skip known knowledge
  • Instructions to extract from each conversation:
    • User corrections: times the user corrected the assistant's approach, code, or understanding
    • Recurring preferences: things the user explicitly asked for or pushed back on repeatedly
    • Technical learnings: codebase-specific knowledge, gotchas, patterns discovered
    • Workflow patterns: how the user prefers to work
    • Frustrations: friction points, wasted effort, things that went wrong
    • Skills wished for: capabilities the user expressed wanting

Agents write structured findings to their output files.

5. Synthesize

After all agents complete, read all findings files. Cross-reference with existing brain content. Deduplicate across batches.

Filter by frequency and impact. Most findings won't be worth adding. Apply these filters before presenting:

  • Frequency: Did this come up in multiple conversations, or was the user correcting the same mistake repeatedly? One-off corrections are usually not worth a brain entry — the brain should capture patterns, not incidents.
  • Factual accuracy: Is something in the brain now wrong? These are always worth fixing regardless of frequency.
  • Impact: Would failing to capture this cause repeated wasted effort in future sessions?

Discard aggressively. It's better to present 3 high-signal findings than 9 that include noise.

Show full SKILL.md (201 more words)Show less
6. Present and apply

Present findings to the user in a table with columns: finding, frequency/evidence, and proposed action. Be honest about which findings are one-offs vs. recurring patterns — let the user decide what's worth adding.

Route skill-specific learnings. Check if any findings are about how a specific skill should work — its process, prompts, edge cases, or troubleshooting. Update the skill's SKILL.md directly. Read the skill first to avoid duplicating or contradicting existing content.

Apply only the changes the user approves. Follow brain writing conventions:

  • One topic per file, organized in directories
  • Use [[wikilinks]] to connect related notes
  • Update brain/index.md after all changes
  • Default to updating existing notes over creating new ones
7. Clean up

Remove the temporary extraction directory:

bash
rm -rf "$OUT_DIR"

Guidelines

  • Filter aggressively. Most conversations will have low signal — automated tasks, trivial exchanges, already-captured knowledge. Only surface what's genuinely new and impactful.
  • Prefer reduction. If a finding is a special case of an existing brain principle, update the existing note rather than creating a new one.
  • Quote the user. When a finding stems from a direct user correction, include the user's words — they carry the most signal about what matters.
  • Shut down agents when analysis is complete. Don't leave them idle.

© poteto, 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 1 other file (scripts) in .agents/skills/ruminate of poteto/brainmaxxing.

  • SKILL.md
  • scripts/extract-conversations.py

Open the folder on GitHubat commit ec4d8e4

Compare with similar skills

Ruminate 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.

Ruminate compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Ruminate this skillpoteto/brainmaxxing320—~1.1kAutomated safety check: PassMIT
Modeling Conversion MetricsPostHog/posthog40k—~1.4kAutomated safety check: PassCustom licence
Correctcursor/plugins10k3 repos~612Automated safety check: PassNone
CorrectionNxcoreAI/EverRoom3k—~290Automated safety check: PassCustom licence
Ruminatepoteto/noodle437—~1.4kAutomated safety check: PassMIT
Paste Inputsthedaviddias/Front-End-Checklist74k—~443Automated safety check: PassMIT

Similar skills

  • Modeling Conversion Metrics

    PostHog/posthog

    Official

    Build reusable conversion models — funnel/step conversion rates, drop-off, and time-to-convert — on either PostHog data-warehouse views (HogQL) or an external dbt project.

    40k GitHub stars~1.4k tokensUpdated today
    Data & AnalyticsAuto-check passed

  • Correct

    cursor/plugins

    Official

    Find the mistakes agents keep repeating in this repo and make each one impossible.

    10k GitHub starsUsed in 3 repos~612 tokens
    Auto-check passed

  • Correction

    NxcoreAI/EverRoom

    Compute Room overview corrections—citation corrections as per-claim edits and general corrections as a single proposal.

    3k GitHub stars~290 tokensUpdated today
    Research & ScienceAuto-check passed

  • Ruminate

    poteto/noodle

    Mine past Claude Code and Codex conversations for uncaptured patterns, corrections, and knowledge.

    437 GitHub stars~1.4k tokensUpdated 6 mo ago
    Auto-check passed

  • Paste Inputs

    thedaviddias/Front-End-Checklist

    A skill your agent uses when reviewing rendered HTML, interactive components, or design-system patterns related to Allow pasting into form inputs.

    74k GitHub stars~443 tokensUpdated 2 days ago
    Frontend & DesignAuto-check passed

  • Cost Conversation

    ruvnet/ruflo

    Per-conversation cost view — list every session in cost-tracking with started-at, message count, top model, and total cost

    74k GitHub stars~407 tokensUpdated today
    AI & LLM EngineeringAuto-check: notes

More from poteto/brainmaxxing

  • Meditate

    poteto/brainmaxxing

    Audit and evolve the brain vault — prune outdated content, discover cross-cutting principles, review skills for structural encoding opportunities.

    320 GitHub stars~858 tokensUpdated 7 mo ago
    Auto-check passed

  • Brain

    poteto/brainmaxxing

    Read/write brain files (Obsidian vault at brain/). An agent skill from poteto/brainmaxxing.

    320 GitHub stars~635 tokensUpdated 7 mo ago
    Auto-check passed

  • Plan

    poteto/brainmaxxing

    Break down medium-to-large tasks into phased plans in brain/plans/.

    320 GitHub stars~1.7k tokensUpdated 7 mo ago
    Auto-check passed

  • Review

    poteto/brainmaxxing

    Principle-grounded review of code changes, PRs, or plans. An agent skill from poteto/brainmaxxing.

    320 GitHub stars~1.3k tokensUpdated 7 mo ago
    Auto-check passed

Questions about Ruminate

What does Ruminate do?

Mine past Claude Code conversations for uncaptured patterns, corrections, and knowledge. Ruminate is an agent skill from poteto/brainmaxxing. Mine past Claude Code conversations for uncaptured patterns, corrections, and knowledge.

How do I install Ruminate in Claude Code?

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

How do I install Ruminate in Codex?

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

Can I use Ruminate 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 poteto/brainmaxxing --skill ruminate -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/ruminate, .gemini/skills/ruminate, .github/skills/ruminate and .opencode/skills/ruminate in your project.

What does Ruminate need to run?

Going by SKILL.md and its folder, Ruminate needs Python for the scripts in its folder and the command-line tools its instructions call (python3 and sh). Our summary lists: Python 3.

Does Ruminate 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 Ruminate 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. The check reads SKILL.md only: the scripts in the folder are not scanned, so read them before running anything.

What licence does Ruminate use?

Ruminate 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 Ruminate use?

About 1.1k tokens (SKILL.md is roughly 4.5k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Ruminate?

Skills that share tags, products or a category with Ruminate: Modeling Conversion Metrics (PostHog/posthog, 40k stars), Correct (cursor/plugins, 10k stars), Correction (NxcoreAI/EverRoom, 3k stars) and Ruminate (poteto/noodle, 437 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Ruminate?

poteto (a GitHub user) maintains it in poteto/brainmaxxing, which has 320 GitHub stars. The repository holds 5 skills in this directory. The repository was last updated on February 27, 2026.

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