A coding agent for adding separate user workspaces to Akashic Context, an MCP server that gives AI agents persistent memory.

Use it to add user IDs to memory tools, create per-user folders and databases, support working memory in context.json files, and add the memory context tool.

It prevents one user's memories and working notes from being mixed with another user's data.

sprint-0 — Agent by tostechbr

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 agents/tostechbr/memoryclaw/sprint-0

Clone the repo

git clone --depth 1 https://github.com/tostechbr/memoryClaw

Made for: Claude Code.

Per session 47 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 1,102 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	$0.00047	$0.01102
Opus 5	$0.00023	$0.00551
Sonnet 5	$0.00009	$0.00220
Haiku 4.5	$0.00005	$0.00110

Measured 2d ago against content hash 305b2f8c96a2, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

sprint-0 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.

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.

.claude/agents/sprint-0.md · 117 lines

How it starts

The opening of the file, as written. The whole thing — 117 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Sprint 0 Agent — Multi-User Isolation

You are a senior TypeScript engineer implementing Sprint 0 of Akashic Context.

Project Context

Akashic Context is an open-source MCP server that gives AI agents persistent memory. It stores memories as Markdown files + SQLite + FTS5 keyword search.

Stack: TypeScript ESM, Node 18+, better-sqlite3, Vitest, MCP Protocol Package manager: pnpm (monorepo) Test command: pnpm test -- --run Build command: pnpm build

Current State (what already exists)

packages/core/src/memory/manager.ts — MemoryManagerConfig already has userId: string field (uncommitted) packages/core/src/memory/storage.ts — StorageConfig already has userId field (uncommitted) packages/mcp-server/src/index.ts — still hardcodes userId: "mcp-user" (NOT done)

The MCP tools do NOT yet expose userId as a parameter to callers. The per-user workspace path ({dataDir}/users/{userId}/) is NOT yet implemented.

Sprint 0 Deliverables

1. userId in all 4 MCP tools

File: packages/mcp-server/src/index.ts

Add optional userId?: string param to: memory_search, memory_get, memory_store, memory_delete
If not provided, default to "default" (backward compatible)
Pass userId when constructing MemoryManager

2. Per-user workspace

File: packages/core/src/memory/manager.ts

Workspace changes from {workspaceDir}/ to {workspaceDir}/users/{userId}/
MEMORY.md and memory/*.md isolated per user
Auto-create user workspace directory on first use

3. Per-user database

File: packages/core/src/memory/storage.ts

DB path changes from {dataDir}/memory.db to {dataDir}/users/{userId}/memory.db
Full isolation — zero cross-user leakage

4. Working Memory (context.json per user)

New file: packages/core/src/memory/working-memory.ts

Each user has {workspaceDir}/users/{userId}/context.json
Interface: { session_id, active_topic, last_interaction, pending_decisions, entities_seen, updated_at }
Read/write functions: getWorkingMemory(userId), setWorkingMemory(userId, data)

Read the full file on GitHub · 117 lines

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 · 117 lines · 47 tokens per session scan A 305b2f8c96a2

Subscribe to this mod's changes

sprint-0 is an agent published in the GitHub repository tostechbr/memoryClaw (8 stars, last pushed 5mo ago), licensed MIT. It adds 47 tokens to every session and 1,102 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.

Databases LLM Memory and context Project management agent context-engine mcp mcp-server

project-manager-backlog

Use this agent when you need to manage project tasks using the backlog.md CLI tool. This includes creating new tasks, editing tasks, ensuring tasks follow the proper format and guidelines, breaking down large tasks into atomic units, and maintaining the project's task management workflow. Examples: Context: User wants…

MrLesk/Backlog.md · 0 tokens

f1-test-drive

Orchestrate F1 test drives to validate the Cyrus agent system end-to-end. Use this agent to run comprehensive test drives that verify issue-tracker, EdgeWorker, and renderer components.

cyrusagents/cyrus · 43 tokens

lead

Use this agent to orchestrate a full task from the harness backlog: decompose it into a plan, delegate to explorer, builder, and reviewer in sequence, and close the session correctly. Invoke when starting a new work session, picking up a pending task, or when another agent reports a blocker that requires…

enmanuelmag/agent-harness-kit · 67 tokens

sprint-0