agentmods.dev

remindb CLAUDE.md

remindb CLAUDE.md is an instructions file for coding agents from radimsem/remindb. It costs 2,473 tokens per session, scanned A, original, MIT.

Routing instructions for coding agents working on remindb, a Go-based memory database that stores data in SQLite and exposes it through an MCP server.

In plain words
What is it for?
Finding the parser, transformer, emitter, storage, query, and MCP tool code when diagnosing or changing remindb.
Why use it?
They show which project rules and code areas to read first, helping agents navigate the repository without unnecessary searching or risky changes.

Instructions file

not rated 125 1mo ago A scan 2,473 tokens original MIT
View the source file radimsem/remindb
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/radimsem/remindb/claude-md
Clone the repo
git clone --depth 1 https://github.com/radimsem/remindb

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 remindb CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/radimsem/remindb/claude-md.svg)](https://agentmods.dev/instructions/radimsem/remindb/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/radimsem/remindb/claude-md"><img src="https://agentmods.dev/badge/instructions/radimsem/remindb/claude-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 2,473 This file is loaded in full into every session.
When invoked 2,473 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 $0.02473 $0.02473
Opus 5 $0.01236 $0.01236
Sonnet 5 $0.00495 $0.00495
Haiku 4.5 $0.00247 $0.00247

Measured 4d ago against content hash de9e3069ce77, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

remindb 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 4d 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 · 114 lines

How it starts

The opening of the file, as written. The whole thing — 114 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md

Routing map for Claude. Points at the rule, skill, agent, or file that owns the answer — does not restate them.

Project at a glance

remindb — token-efficient agentic memory database. Single SQLite file, MCP server on top. Go 1.26+. Pre-1.0 beta, solo dev, no compatibility shims. dev is the integration trunk; main is a release-marker branch — one squash commit per published release, signed by GitHub's web-flow key via PR from dev. Topic branches (feat/, fix/, chore/, docs/) off dev, rc tags on dev, stable cuts tag dev then squash-PR dev → main; lazy release/vX.Y branches handle patches to non-current minors; subject-only signed commits everywhere (release squash on main carries the release notes as its body) — see .claude/rules/git-versioning.md.

Pipeline: parser → transformer → emitter → store. Read side: query → mcp/tools. Background: temperature ticker decays/notifies.

Code map

  • pkg/parser/ — file formats → AST nodes
  • pkg/transformer/ — AST → ContextNode tree
  • pkg/emitter/ — node tree → store snapshot
  • pkg/store/ — SQLite layer; queries.go holds SQL constants, methods live in node.go / snapshot.go / search.go / temperature.go
  • pkg/diff/ — snapshot diffing
  • pkg/query/ — search/fetch engine + result formatters (Format, FormatCompact)
  • pkg/compiler/ — full-workspace compile pipeline
  • pkg/mcp/ — MCP server; tools in pkg/mcp/tools/ (one file per tool)
  • pkg/temperature/ — decay/boost/cold-set + cold-node notifier
  • cmd/remindb/ — CLI: serve, compile, inspect, bench, doctor, update
  • migrations/ — 0001_init.sql, 0002_*.sql, applied via embed.FS in migrations.go
  • internal/ — bench, contentid, fileext, ignore, mcptest, tempfile, testutil, tokens
  • skills/{remember,remind,memorize,remindb-setup}/ — public skills shipped to MCP clients (distinct from .claude/skills/): remember is the broad-trigger router, remind the read path + mental model, memorize the write path + Markdown-shape rules, remindb-setup the /remindb-setup [automode] setup wizard. remind, memorize, and remindb-setup push depth into their references/ subdirs (progressive disclosure); SKILL.md stays a compact router/spine. Structural gate: scripts/check-skills.sh (make check-skills)
  • docs/ — public end-user manual: architecture.md / cli.md / configuration.md (reference) plus one deep-dive per feature; editable diagram sources in assets/excalidraw/, exported assets/*.svg
  • plugins/ — per-agent plugin folders (claude-code, gemini-cli, codex, opencode, openclaw)
  • Top-level: integration_test.go, mcp_integration_test.go, bench_test.go

Read the full file on GitHub · 114 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. 4d ago First seen · 114 lines · 2,473 tokens per session scan A de9e3069ce77

Subscribe to this mod's changes

remindb CLAUDE.md is an instructions file published in the GitHub repository radimsem/remindb (125 stars, last pushed 1mo ago), licensed MIT. It adds 2,473 tokens to every session, about $0.0124 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.

DatabasesMemory and contextagent-memoryai-agentsastclaude-codeclicodex
Related

Other instructions, from other repositories

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

pgmnemo AGENTS.md

Instructions for pgmnemo/pgmnemo, covering pgmnemo — agent integration guide, 1. what pgmnemo is — and the problem it solves, the problem, architectural consequences and 2. when to adopt / when not to.

pgmnemo/pgmnemo · 8,496 tokens

infinity-context AGENTS.md

Instructions for 777genius/infinity-context, covering agents.md, project intent, source of truth and implementation rule.

777genius/infinity-context · 284 tokens

auto-knowledge-base CLAUDE.md

Claude Code instructions for guyeyouhun/auto-knowledge-base, covering 自主知识库 (auto knowledge base), 当前状态, 核心设计原则, 知识类型 and 信任级别.

guyeyouhun/auto-knowledge-base · 1,020 tokens

claude-memory-mcp CLAUDE.md

Claude Code instructions for navid-kianfar/claude-memory-mcp, covering memory mcp server, auto-memory behavior, auto-store (triggered by conversation context), auto-search (before answering) and auto-rules check.

navid-kianfar/claude-memory-mcp · 397 tokens

guild CLAUDE.md

Claude Code instructions for mathomhaus/guild, a project described as: Shared context, memory, and task coordination across AI coding agents. Single Go binary, local SQLite, hybrid keyword and semantic search.

mathomhaus/guild · 3 tokens