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.
npx agentmods add instructions/jafreck/lore/claude-mdgit clone --depth 1 https://github.com/jafreck/LoreWhat 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 | $0.00690 | $0.00690 |
| Opus 5 | $0.00345 | $0.00345 |
| Sonnet 5 | $0.00138 | $0.00138 |
| Haiku 4.5 | $0.00069 | $0.00069 |
Grade A, and why
Lore 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 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.
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.md
What Lore Is
Lore is a code intelligence tool that enables AI agents and API consumers to understand large codebases more correctly, at a wider scale, and with less context usage. It indexes source code, relationships, documentation, and git history into a structured SQL database exposed via MCP (Model Context Protocol), so agents can query precise, pre-computed knowledge instead of re-reading files from scratch.
Core Value Proposition
- Correctness: Pre-resolved symbols, call graphs, type relationships, and import edges give agents accurate structural facts rather than heuristic guesses.
- Scale: Lore indexes entire repositories — across 23 languages — into a compact database that agents query surgically, avoiding full-file reads.
- Efficiency: Across 6 benchmark repos (390 runs), Lore-enabled agents achieve up to +10pp higher correctness, up to 84% fewer tokens, and up to 62% faster wall-clock time compared to grep + file-read baselines.
How It Works
- Indexing: A SCIP-first strategy (with tree-sitter fallback) extracts symbols, imports, call refs, type refs, annotations, and documentation from source files. Git history (commits, diffs, refs) is indexed alongside.
- Storage: Everything is persisted to a normalized SQLite database with optional vector embeddings for semantic search.
- Serving: An MCP server exposes the database through purpose-built tools (
lore_lookup,lore_search,lore_graph,lore_trace,lore_dependents, etc.) that any MCP-compatible client can call. - Freshness: The index dynamically updates based on local changes via watch mode, poll mode, or git hooks — each refresh only re-processes files whose content hash has changed. A baseline index is built for every commit.
Pre-Release Software
Lore is pre-release software. This means:
- No backwards compatibility obligation. Breaking changes to APIs, schemas, CLI flags, MCP tool signatures, or internal interfaces are expected and acceptable.
- No legacy code retention. Dead code, deprecated paths, compatibility shims, and migration layers should be removed rather than maintained. If something is superseded, delete the old version.
- Prefer clean breaks over gradual migration. When a better approach exists, adopt it fully rather than supporting both old and new patterns side by side.
- Ship the simplest correct thing. Don't over-engineer for hypothetical future compatibility — the interfaces will change again before 1.0.
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.
- 2d ago First seen · 46 lines · 690 tokens per session scan A 3b8e2a3bd6f4
Lore CLAUDE.md is an instructions file published in the GitHub repository jafreck/Lore (7 stars, last pushed 16d ago), licensed MIT. It adds 690 tokens to every session, about $0.0034 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.
Other instructions, from other repositories
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).
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.
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.
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).
next.js AGENTS.md
Instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.