akashic-codebase-map

A reference map of the Akashic Context codebase, showing its main packages, files, types, and implementation conventions. Akashic Context is a memory system built around stored text, search, and user context.

In plain words
What is it for?
Use it to locate memory management, SQLite and keyword search, text chunking, embeddings, MCP server code, and related tests.
Why use it?
It gives agents a shared view of the project before they change code, reducing the need to rediscover its structure.

Skill for Claude CodeCodex

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/tostechbr/memoryclaw/akashic-codebase-map
Any agent
npx skills add tostechbr/memoryClaw --skill akashic-codebase-map
Clone the repo
git clone --depth 1 https://github.com/tostechbr/memoryClaw

Made for: Claude Code, Codex.

Per session 38 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,326 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.

ModelPer sessionOnce invoked
Fable 5 $0.00038 $0.01326
Opus 5 $0.00019 $0.00663
Sonnet 5 $0.00008 $0.00265
Haiku 4.5 $0.00004 $0.00133

Measured yesterday against content hash b99da3a20e83, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

akashic-codebase-map 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 yesterday.

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/skills/akashic-codebase-map/SKILL.md · 137 lines

How it starts

The opening of the file, as written. The whole thing — 137 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Akashic Context — Codebase Map

Project Structure

packages/
├── core/src/
│   ├── types.ts              <- Core interfaces: Message, MemoryConfig, MemoryChunk, Session
│   ├── index.ts              <- Main exports
│   ├── memory/
│   │   ├── manager.ts        <- MemoryManager class (orchestrates everything)
│   │   ├── storage.ts        <- MemoryStorage class (SQLite + FTS5)
│   │   ├── chunking.ts       <- chunkMarkdown() (~400 tokens, 80 overlap)
│   │   ├── hybrid.ts         <- mergeHybridResults() (70% vec + 30% keyword)
│   │   ├── manager.test.ts   <- Unit tests for MemoryManager
│   │   └── providers/
│   │       └── openai.ts     <- createOpenAIEmbeddingProvider()
│   └── utils/
│       ├── hash.ts           <- hashText(content): string
│       └── files.ts          <- listMemoryFiles(), exists(), ensureDir()
│
└── mcp-server/src/
    ├── index.ts              <- MemoryMcpServer class (4 MCP tools)
    ├── cli.ts                <- CLI entry point (env vars + args)
    └── index.test.ts         <- Unit tests for MCP server

Key Classes and Interfaces

MemoryManagerConfig (manager.ts)

interface MemoryManagerConfig {
  dataDir: string;       // Where DBs are stored
  userId: string;        // User identifier
  sessionId?: string;    // Optional session scope
  workspaceDir: string;  // Where MEMORY.md + memory/*.md live
  memory: MemoryConfig;
  vectorExtensionPath?: string;
}

StorageConfig (storage.ts)

interface StorageConfig {
  dataDir: string;
  userId: string;
  sessionId?: string;
}
// Current DB path: {dataDir}/memory_{userId}.db
// Sprint 0 target: {dataDir}/users/{userId}/memory.db

MemoryStorage constructor (storage.ts:85-92)

constructor(config: StorageConfig) {
  const sessionPart = config.sessionId ? `_${config.sessionId}` : "";
  const dbName = `memory_${config.userId}${sessionPart}.db`;
  this.dbPath = path.join(ensureDir(config.dataDir), dbName);
  // ...
}

Read the full file on GitHub · 137 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.

  1. yesterday First seen · 137 lines · 38 tokens per session scan A b99da3a20e83

Subscribe to this mod's changes

akashic-codebase-map is a skill published in the GitHub repository tostechbr/memoryClaw (8 stars, last pushed 5mo ago), licensed MIT. It adds 38 tokens to every session and 1,326 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.