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/agentkitai/lore/claude-mdgit clone --depth 1 https://github.com/agentkitai/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 | $0.00535 | $0.00535 |
| Opus 5 | $0.00267 | $0.00267 |
| Sonnet 5 | $0.00107 | $0.00107 |
| Haiku 4.5 | $0.00053 | $0.00053 |
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 — 55 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Lore — Universal AI Memory
You have access to Lore, a persistent memory system via MCP tools. Use it to remember context across sessions and recall relevant knowledge.
When to Use Lore
Session Start
Call recent_activity(hours=24) to load what happened recently.
This gives you grouped context from the last day — decisions, lessons, work done.
During Work
- Before debugging:
recall("describe the problem")— check if this was solved before - After solving something non-obvious:
remember("what you learned", type="lesson") - Key decisions:
remember("decision and reasoning", type="note") - Preferences discovered:
remember("user prefers X", type="preference")
Pre-Compaction (Automatic)
Lore's session accumulator auto-saves snapshots when your context grows large.
You don't need to manually call save_snapshot — but you can if you want to
preserve specific state before a complex transition:
save_snapshot(content="Current state: ...", title="mid-refactor checkpoint")
Key Tools
| Tool | When |
|---|---|
recall(query) |
Search memories semantically |
remember(content, type) |
Save a memory (types: note, lesson, fact, preference, pattern, convention) |
recent_activity(hours) |
Load recent session context |
save_snapshot(content) |
Manually checkpoint current state |
suggest(context) |
Get proactive memory recommendations based on session context |
topics() |
Browse auto-generated topic summaries |
graph_query(query) |
Explore knowledge graph connections |
entity_map(name) |
Find everything related to an entity |
review_digest() |
Review pending graph connections (with risk scores) |
on_this_day() |
Memories from this date in prior years |
export(format) |
Export all data (json/markdown) |
Types for remember
lesson— Bug fixes, gotchas, things learned the hard wayfact— Objective information (API endpoints, config values, specs)preference— User preferences, style choicespattern— Recurring patterns or anti-patternsconvention— Project conventions, naming rulesnote— General notes, decisions, context
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 · 55 lines · 535 tokens per session scan A 39f4ed6b4069
lore CLAUDE.md is an instructions file published in the GitHub repository agentkitai/lore (7 stars, last pushed 3d ago), licensed MIT. It adds 535 tokens to every session, about $0.0027 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
m_flow AGENTS.md
AGENTS.md instructions for FlowElement-xinliuyuansu/m_flow, covering m-flow — developer & agent reference, 1. repository map, extension points, 2. local development and python backend (requires python 3.10 – 3.13).
open-ontologies CLAUDE.md
Instructions for fabio-rovai/open-ontologies, covering open ontologies, ontology engineering workflow, generate, validate and load and reason.
engraphis CLAUDE.md
Instructions for Coding-Dev-Tools/engraphis, covering claude.md, the one rule that prevents most mistakes, before you say "done" — run the canonical gate, slash commands available here and working style in this repo.
kglite CLAUDE.md
Instructions for kkollsga/kglite, covering kglite — claude code conventions, build & test, architecture, the boundary principle (wrappers vs core) — summary and in-memory is the core product.
tpu_performance_autoresearch_wiki GEMINI.md
Instructions for vlasenkoalexey/tpu_performance_autoresearch_wiki, covering gemini/antigravity operating rules, platform adaptation (claude code → gemini/antigravity), 1. skills — native, no emulation, 2. never-stop hook & retrospectives and 3. session and transcript resolution.
tpu_performance_autoresearch_wiki AGENTS.md
Instructions for vlasenkoalexey/tpu_performance_autoresearch_wiki, covering codex instructions, compatibility, operating rules and codex translation notes.