lorekeeper-dev

An engineering guide for developing the Lorekeeper memory server, including its code structure, storage systems, scoring rules, and verification practices.

In plain words
What is it for?
Use it when fixing bugs, adding features, writing tests, or reviewing changes to the Lorekeeper source code.
Why use it?
It explains project-specific decisions and known issues that a general coding guide would not cover, reducing mistakes when changing the code.

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/jessinra/lorekeeper/lorekeeper-dev
Any agent
npx skills add Jessinra/Lorekeeper --skill lorekeeper-dev
Clone the repo
git clone --depth 1 https://github.com/Jessinra/Lorekeeper

Made for: Claude Code, Codex.

Per session 76 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,570 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 $0.00076 $0.01570
Opus 5 $0.00038 $0.00785
Sonnet 5 $0.00015 $0.00314
Haiku 4.5 $0.00008 $0.00157

Measured 2d ago against content hash a3468508bad8, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

lorekeeper-dev 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.

.hermes/skills/lorekeeper-dev/SKILL.md · 155 lines

How it starts

The opening of the file, as written. The whole thing — 155 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Lorekeeper Dev

Practices and conventions for developing the Lorekeeper MCP server.

Architecture

Two vector store backends (switch via LORE_VECTOR_STORE):

  • LanceDB (default) — concurrent multi-process, no lock files. LanceDBEngine in lancedb_engine.py. Uses sentence-transformers directly, no Mem0 for vectors.
  • Chroma (fallback, LORE_VECTOR_STORE=chroma) — Mem0-backed ChromaDBEngine in chromadb_engine.py. Single-process only.
  • SQLite sidecar — memory metadata (score, confidence, soft_deleted, usage_count), all MemoryLink rows, BM25 index source. Shared by both backends.

Engine factory: engine_factory.pybuild_engine(). Orchestrator: MemoryService in orchestrator.py.

Canonical identity: lore_id UUID lives in the vector store's metadata. All app logic uses lore_id.

Hybrid Scoring Formula

combined = 0.45·semantic + 0.30·keyword + 0.15·(score/10) + 0.10·log_usage_norm

Weights are env-configurable (LORE_W_*). Dedup threshold: 0.6·semantic + 0.4·keyword >= 0.85.

Known Quirks

Chroma distance vs. similarity (critical): Mem0 v2 score_and_rank receives Chroma cosine distances but treats them as similarities. Fix: bypass mem0 pipeline — embed directly with SentenceTransformer, query directly, return score = 1.0 - distance.

LanceDB: Always returns cosine distance (lower=better). normalize_score() converts to similarity: 1.0 - distance.

infer=False on every mem0.add() call — text stored verbatim, no LLM extraction.

stdout reserved for MCP protocol — all logging to stderr via structlog.

Tooling

uv run pytest                          # run tests
uv run pytest tests/ -x -q            # fail-fast
uv run ruff check src tests            # lint (Python)
uv run ruff check src tests --fix      # auto-fix lint
uv run mypy src                        # type check (run before push)
npx @biomejs/biome check src/lorekeeper/dashboard/static/js/    # lint (JS)
uv run lorekeeper                      # start server

Read the full file on GitHub · 155 lines

Files

What ships with it

4 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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. 2d ago First seen · 155 lines · 76 tokens per session scan A a3468508bad8

Subscribe to this mod's changes

lorekeeper-dev is a skill published in the GitHub repository Jessinra/Lorekeeper (4 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 76 tokens to every session and 1,570 once invoked, about $0.0004 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.

Related

Other skills, from other repositories

hs-release

Cut a core Hindsight release (vX.Y.Z) and open the changelog + blog PR. Use when asked to cut/start a release, bump the version, or publish a new Hindsight version.

vectorize-io/hindsight · 45 tokens

create-modal

Create declarative modals using the modal library API. Covers modal types (confirm, input, select, form), sections (Text, Buttons, Input, Textarea, Checkbox, List, Combo, When, Custom), rendering with OverlayModal, and keyboard/mouse handling. Use when adding modals or dialogs to the application.

marcus/sidecar · 69 tokens

create-plugin

Create new sidecar plugins implementing the plugin.Plugin interface, rendering views with Bubble Tea, handling keyboard input via keymap contexts, and integrating with the app shell (footer hints, event bus, adapters). Use when creating a new plugin, modifying plugin architecture, or debugging plugin…

marcus/sidecar · 74 tokens

merge-strategy

Git merge strategies, conflict resolution approaches, merge vs rebase recommendations, and branch integration patterns in sidecar. Covers pull strategy menu, direct merge workflow, squash merge, commit message templates, configurable defaults, and protected branches. Use when working on git merge features or making…

marcus/sidecar · 63 tokens

sidecar-website

Writing and maintaining the Sidecar Docusaurus documentation site, including page structure, doc authoring, blog posts, styling, images, and deployment workflow. Use when writing documentation, updating the docs site, adding pages or blog posts, or working with Docusaurus configuration.

marcus/sidecar · 60 tokens

worktree-switching

Git worktree support in sidecar: worktree detection, switching between worktrees, worktree state management, and plugin reinitialization. Covers the full lifecycle of worktree context switching including registry reinit, per-worktree state persistence, deleted worktree detection and fallback. Use when working on git…

marcus/sidecar · 74 tokens