Memory

What it does

When your agent uses it

• User asks to remember something
• Search past conversations
• Recall what was done before
• Save context for later

Example prompts

• “/memory”

Requirements

• Python 3
• Compatibility (from SKILL.md): opencode
• Pre-approved tools (allowed-tools): Read, Bash, Write

Workflow steps

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

1. 1Start memory server (if not running)
2. 2Save context during session
3. 3Search past memory at session start
4. 4Get full session summary

What it can do on your machine

Read from SKILL.md and the folder at commit 4c68e5b. It shows what the files ask for, not the result of running them.

• Tool permissions

  Pre-approves these tools, so the agent can use them without asking each time:

  • Read
  • Bash
  • Write

  From allowed-tools in the SKILL.md frontmatter.

• Runs code

  Shell commands in SKILL.md call:

  • pip
  • python

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

• Network

  No URLs in SKILL.md. Its commands use pip, which can reach the network depending on how they are called.

  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.

• Compatibility

  opencode

  From compatibility in the SKILL.md frontmatter.

Context cost

Memory loads about 2.3k tokens when it runs. Until then it costs about 91 tokens; SKILL.md has 747 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it

~91

When it runs · the whole SKILL.md, loaded when a task matches

~2.3k

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

• NotePre-approves every shell command (allowed-tools: Bash)SKILL.md

  allowed-tools: Read, Bash, Write

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 EliasOulkadi/shokunin at commit 4c68e5b, republished under its MIT licence (© EliasOulkadi). 747 words, ~2,255 tokens.

name

memory

description

Persistent memory across AI sessions using ChromaDB vector database. Stores and retrieves context from past conversations, decisions, and code. Use when user asks to remember something, search past conversations, recall what was done before, save context for later, or find information from previous sessions. Do NOT use for git history or file-based notes.

allowed-tools

Read, Bash, Write

compatibility

opencode

triggers

remember, search past, recall, what was done, previous session, save context, remember that, memory, ChromaDB, vector memory, persistent memory

negatives

git history, file system, file notes, backup, database, memory admin (use chromadb), backup memory (use chromadb)

license

MIT

metadata.workflow

productivity

metadata.audience

developers

metadata.version

1.0.0

metadata.author

shokunin

store_context with:
  text: "Summary of what was done, key decisions, code patterns"
  tags: ["project-name", "feature", "language"]
  project: "project-name"
  session_id: "current-session-id"

search_context with:
  query: "what we discussed about auth"
  project: "current-project"

get_session_summary with:
  session_id: "session-id"

/remember [text]     → Save an important piece of context
/search [query]      → Search past memory
/whatdidwe [topic]   → What did we discuss about X before?
/forget [id]         → Remove a specific memory entry

# List collections
collections = client.list_collections()
for c in collections: print(c.name, c.count())

# Create collection with custom embedding function
from chromadb.utils import embedding_functions
ef = embedding_functions.OpenAIEmbeddingFunction(api_key="...", model_name="text-embedding-3-small")
collection = client.create_collection(name="custom", embedding_function=ef)

# Delete by metadata filter
collection.delete(where={"project": "test-project"})

# Peek at stored data
sample = collection.peek(limit=5)

# Batch inserts (100x faster than single inserts)
batch_size = 100
for i in range(0, len(documents), batch_size):
    collection.add(
        documents=documents[i:i+batch_size],
        metadatas=metadatas[i:i+batch_size],
        ids=ids[i:i+batch_size]
    )

# Limit query results
results = collection.query(query_texts=["query"], n_results=10)

# Get with limit (prevents OOM)
all_data = collection.get(limit=500, include=["documents", "metadatas"])

import os

db_path = "~/.shokunin/memory/chroma_db"
size = sum(os.path.getsize(os.path.join(root, f)) for root, _, files in os.walk(db_path) for f in files)
print(f"Database size: {size / 1024 / 1024:.1f} MB")
print(f"Collection count: {collection.count()}")

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

Files

Just SKILL.md in .pack/skills/memory of EliasOulkadi/shokunin.

Open the folder on GitHubat commit 4c68e5b