agentmods.dev

linggen-memory CLAUDE.md

linggen-memory CLAUDE.md is an instructions file for coding agents from linggen/linggen-memory. It costs 728 tokens per session, scanned A, original, MIT.

Project instructions and technical documentation for linggen-memory, a Rust program that stores and searches memories using meaning-based retrieval. They define the project's purpose, scope, design decisions, command-line interface, and release process.

In plain words
What is it for?
Use them when developing the memory database, command-line commands, embedding pipeline, release binaries, or documentation for linggen-memory.
Why use it?
They give contributors a shared reference for how the memory system should work and which responsibilities belong in this repository. They also explain what is handled by the related Linggen project.

Instructions file

not rated 108 2d ago A scan 728 tokens original MIT
View the source file linggen/linggen-memory
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/linggen/linggen-memory/claude-md
Clone the repo
git clone --depth 1 https://github.com/linggen/linggen-memory

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for linggen-memory CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/linggen/linggen-memory/claude-md.svg)](https://agentmods.dev/instructions/linggen/linggen-memory/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/linggen/linggen-memory/claude-md"><img src="https://agentmods.dev/badge/instructions/linggen/linggen-memory/claude-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 728 This file is loaded in full into every session.
When invoked 728 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.

ModelPer sessionOnce invoked
Fable 5 $0.00728 $0.00728
Opus 5 $0.00364 $0.00364
Sonnet 5 $0.00146 $0.00146
Haiku 4.5 $0.00073 $0.00073

Measured 3d ago against content hash 0540558caba0, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

linggen-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 3d 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.md · 46 lines

How it starts

The opening of the file, as written. The whole thing — 46 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Claude Code Instructions

Purpose

linggen-memory is the default memory-skill backend for Linggen — a standalone Rust binary (ling-mem) that implements the Memory_* tool family (add, search, list, update, delete, forget) over a LanceDB store with semantic retrieval.

Specs for this repo:

  • doc/product-spec.md — features, user-facing behavior, scenarios
  • doc/tech-spec.md — schema, storage, CLI contract, release process
  • DESIGN.md — rolling locked-decisions log (what was chosen and why)

The main Linggen repo owns the integration side (see ../linggen/doc/memory-spec.md and ../linggen/doc/skill-spec.md for the contract this binary must satisfy).

Status

  • Branch: main — commit & push directly on main, never branch. The archived code-indexing tool is preserved at the v0-legacy tag.

Scope

In scope for this repo:

  • LanceDB store + embedding pipeline
  • CLI subcommands on ling-mem
  • (out-of-scope: HTTP daemon + webpage — lives in the memory skill wrapper)
  • Platform release binaries (cross-compile via GitHub Actions)
  • All docs under doc/ about the binary itself

Out of scope (lives in ../linggen/):

  • Linggen core's provides: field and Memory_* tool dispatch
  • Core-prompt injection (the engine loads tier=core rows at session start — there is no identity.md/style.md markdown substrate; that cutover shipped)
  • Spec docs for the Linggen-memory integration contract (linggen/doc/memory-spec.md)

Working rules

  • Single-crate discipline. Don't re-introduce a workspace or sub-crates. Modules under src/<name>/ are the unit of organization.
  • Commit per sub-step. Each checklist item / sub-step in ~/.claude/plans/memory-system-rebuild.md gets its own commit (e.g. the Phase 1a substeps each landed as one commit: add updated_at field, bump on update, episodic evict + tier-core query, retune dedup threshold). Build + relevant cargo test green before each commit.
  • Don't edit v0-legacy. Tag is immutable; legacy source is git checkout v0-legacy away.
  • Preserve release tooling. scripts/build-*.sh, signing config, and CI live through the refactor.
  • Dependency policy. Use current major versions; thiserror is 2.x. LanceDB + Arrow must be a compatible triple — track the lance 0.39 × rustc 1.94 recursion-limit issue separately.
  • CLI is primary. All features must be reachable via ling-mem subcommands. The Memory_* tool-namespace dispatch in Linggen is sugar; the CLI must be complete on its own so Claude Code (Bash-only) can use it.

Read the full file on GitHub · 46 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. 3d ago First seen · 46 lines · 728 tokens per session scan A 0540558caba0

Subscribe to this mod's changes

linggen-memory CLAUDE.md is an instructions file published in the GitHub repository linggen/linggen-memory (108 stars, last pushed 2d ago), licensed MIT. It adds 728 tokens to every session, about $0.0036 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 2026-08-30.

Memory and contextagent-memoryaiai-memoryclaude-codecontext-windowdeveloper-tools
Related

Other instructions, from other repositories

plur CLAUDE.md

Instructions for plur-ai/plur, covering claude.md, what is plur, development, package dependency and version bumps.

plur-ai/plur · 4,509 tokens

mentedb copilot-instructions.md

Instructions for nambok/mentedb, covering mentedb development instructions, project overview, workspace structure, build, test, and lint and key types.

nambok/mentedb · 997 tokens

dense-mem AGENTS.md

Instructions for markhuangai/dense-mem, covering dense-mem repository guidance, project context, architecture decision records, current stack and target architecture.

markhuangai/dense-mem · 2,447 tokens

EGC copilot-instructions.md

Copilot instructions for Fmarzochi/EGC, covering copilot instructions for egc, repository conventions, readme and translations, code review priorities and egc project memory.

Fmarzochi/EGC · 512 tokens

dakera-cli CLAUDE.md

Instructions for Dakera-AI/dakera-cli, covering dakera-cli, key commands, architecture and conventions.

Dakera-AI/dakera-cli · 282 tokens

pos CLAUDE.md

Instructions for xcota/pos, covering personal os, rules, memory, budget and hard rules.

xcota/pos · 899 tokens