A note-taking tool that saves observations, decisions, and other context in ChromaDB, a database designed for searching by meaning. It can assign IDs, timestamps, categories, and tags to each note.

Use it to record discoveries, user preferences, decisions, and lessons learned, then search or list those notes later.

It prevents useful project knowledge from being lost between sessions and makes past notes easier to find than scattered text files.

take-note — Skill by ssube

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods

npx agentmods add skills/ssube/conclave/take-note

Any agent

npx skills add ssube/conclave --skill take-note

Clone the repo

git clone --depth 1 https://github.com/ssube/conclave

Made for: Claude Code, Codex.

Per session 45 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 747 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. Scan, not verified.

Origin original No closer match found in the catalogue.

Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

Model	Per session	Once invoked
Fable 5	$0.00045	$0.00747
Opus 5	$0.00023	$0.00374
Sonnet 5	$0.00009	$0.00149
Haiku 4.5	$0.00005	$0.00075

Measured 2d ago against content hash 2a4b764e55e0, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

take-note scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.

The scan reads SKILL.md. This mod also ships 1 executable file (note.py), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

pi/skills/take-note/SKILL.md · 110 lines

How it starts

The opening of the file, as written. The whole thing — 110 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Take Note Skill

Quickly capture notes, learnings, observations, and context. Builds a searchable knowledge base over time.

Requirements

pip install chromadb

Usage

Capture a quick note

python3 {baseDir}/note.py "Learned that Flux models respond better to natural language prompts"

Auto-generates ID with timestamp: note-2026-02-10-213045-abc123

Add note with category/tags

python3 {baseDir}/note.py "User prefers dark fantasy aesthetics with purple and green color schemes" \
  --category user-preferences \
  --tags "color,style,fantasy"

Add note with custom ID

python3 {baseDir}/note.py "Important discovery about training parameters" \
  --id important-training-discovery

Search notes

python3 {baseDir}/note.py --search "training parameters" --limit 5

List recent notes

python3 {baseDir}/note.py --list [--limit 10]

What Gets Stored

Each note includes:

Content: Your note text (embedded for semantic search)
ID: Auto-generated note-YYYY-MM-DD-HHMMSS-hash or custom
Timestamp: ISO 8601 timestamp
Category: Optional category for filtering (default: "general")
Tags: Comma-separated tags for filtering
Source: "agent" to distinguish from imported notes

Environment Variables

CHROMADB_HOST: ChromaDB server host (default: localhost)
CHROMADB_PORT: ChromaDB server port (default: 8000)

Examples

# Quick learning capture
python3 {baseDir}/note.py "The scratching LoRA works best at weight 0.8-1.0 for sketch effects"

# User preference with tags
python3 {baseDir}/note.py "User avoids overly bright colors, prefers muted/dark palettes" \
  --category user-preferences \
  --tags "color,palette,style"

# Technical decision with category
python3 {baseDir}/note.py "Switched to cosine scheduler for all future training - smoother results" \
  --category decision \
  --tags "training,scheduler"

# Search for relevant context
python3 {baseDir}/note.py --search "user color preferences"

# List recent notes
python3 {baseDir}/note.py --list --limit 5

Read the full file on GitHub · 110 lines

Files

What ships with it

1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

note.py 5.3 KB runs code

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

2d ago First seen · 110 lines · 45 tokens per session scan A 2a4b764e55e0

Subscribe to this mod's changes

take-note is a skill published in the GitHub repository ssube/conclave (2 stars, last pushed 6mo ago), licensed MIT. It adds 45 tokens to every session and 747 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Memory and context ai-agents chromadb claude claude-code codex coding-assistant

mine

Mine a project or conversation into your MemPalace — extract and store memories for later retrieval.

MemPalace/mempalace · 21 tokens

search

Search your MemPalace — semantic search across all mined memories, projects, and conversations.

MemPalace/mempalace · 20 tokens

tool-prompt-optimization

Optimize the description prompts an AI agent reads to learn its built-in tools (the .md files under prompts/tools/). Two halves: (1) measure how much of a prompt is already inferable from the tool's JSON parameter schema + name, to prune redundancy with evidence; (2) house authoring rules for what belongs in a tool…

can1357/oh-my-pi · 0 tokens

mempalace-recall

Recall protocol for MemPalace — search the palace before answering about past work, people, projects, or prior decisions. Apply when the user asks what was decided, what happened before, who someone is, what was discussed last time, or anything that may already be filed in their memory palace; or when mempalace-recall…

MemPalace/mempalace · 94 tokens

docker-extend

Use when: User wants to extend Docker with custom tools, personalize the Docker environment, or set up user-specific Docker customization. Triggers: 'extend docker', 'docker-extend', 'add tools to docker', 'customize docker', 'add my tools to the container', 'personalize docker setup', 'docker user setup', 'install…

coleam00/Archon · 118 tokens

runjam-defaults

Default constraints for every RunJam session. Defines output path conventions, dependency checking rules, fallback strategies, and file management discipline. This skill is auto-injected into every session — do not remove. Current session working directory: /Users/guizhan/work/code/runjam.

peintune/runjam · 59 tokens

take-note