What is server-memory CLAUDE.md?

A set of instructions for the agentage/server-memory project, which provides local vaults for storing and retrieving memory through an MCP server.

It helps maintain the server, keep its schemas and registrations consistent, and test the actual tools exposed to agents.

It documents the project layout and protects the fixed six-tool interface, including how to verify the live tool definitions.

server-memory CLAUDE.md — Instructions file by agentage

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 instructions/agentage/server-memory/claude-md

Clone the repo

git clone --depth 1 https://github.com/agentage/server-memory

Per session 465 This file is loaded in full into every session.

When invoked 465 The same file — it is already loaded in full.

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	$0.00465	$0.00465
Opus 5	$0.00233	$0.00233
Sonnet 5	$0.00093	$0.00093
Haiku 4.5	$0.00047	$0.00047

Measured yesterday against content hash e501105003c4, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

server-memory CLAUDE.md 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.md · 24 lines

What it actually says

@agentage/server-memory — CLAUDE.md

The stdio MCP server for agentage Memory: exposes local vaults as the frozen 6 memory__* tools. Deliberately tiny — just the MCP definition. All memory logic (backends, git, search, routing) lives in @agentage/memory-core; don't add it here.

Layout (src/)

server/memory-tools.schema.ts + .mcpc.json — the frozen 6-tool contract (Zod source + CI snapshot).
server/register-tools.ts — wires the schema to memory-core's router.
server/render-markdown.ts — the text channel renderer (pure; list=outline, read=raw doc).
server/create-memory-server.ts — createMemoryServer(registry, opts), transport-agnostic.
server/local-server.ts — loadLocalServer() (reads ~/.agentage/vaults.json).
bin/server-memory.ts — ~15-line stdio entry.

Rules

The 6-tool memory__* contract is frozen. Schema + .mcpc.json must stay in sync.
.mcpc.json is a CI snapshot (z.toJSONSchema, draft-2020-12) — it disagrees with the live tools/list (SDK, draft-07). Verify contract claims against a dumped live tools/list, never the snapshot — snapshot-only checks go false-green.
Descriptions flow to BOTH serializers — the safe cross-model lever (the model routes on the description, not just the schema).
Transport-agnostic by design: stdio bin here; the CLI daemon reuses createMemoryServer over Streamable HTTP. Keep it that way.
@agentage/memory-core is a file: link until both publish — build core first (the e2e does this automatically).

Verify

npm run verify (type-check + lint + format:check + test + build). Tests: contract (tools/list = 6) + tools (in-memory) + e2e (init → spawned bin → round-trip).

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.

yesterday First seen · 24 lines · 465 tokens per session scan A e501105003c4

Subscribe to this mod's changes

server-memory CLAUDE.md is an instructions file published in the GitHub repository agentage/server-memory (2 stars, last pushed 3d ago), licensed MIT. It adds 465 tokens to every session, about $0.0023 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 Testing

spec-kit AGENTS.md

AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.

github/spec-kit · 7,104 tokens

codex AGENTS.md

AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.

openai/codex · 5,182 tokens

vscode buildNext.instructions.md

Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).

microsoft/vscode · 6,785 tokens

server-memory CLAUDE.md