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 skills add hyunjae-labs/lore --skill lore-indexgit clone --depth 1 https://github.com/hyunjae-labs/loreWrote 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.
[](https://agentmods.dev/skills/hyunjae-labs/lore/lore-index)<a href="https://agentmods.dev/skills/hyunjae-labs/lore/lore-index"><img src="https://agentmods.dev/badge/skills/hyunjae-labs/lore/lore-index/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/hyunjae-labs/lore/lore-index"><img src="https://agentmods.dev/badge/skills/hyunjae-labs/lore/lore-index.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00143 | $0.00970 |
| Opus 5 | $0.00072 | $0.00485 |
| Sonnet 5 | $0.00029 | $0.00194 |
| Haiku 4.5 | $0.00014 | $0.00097 |
Grade A, and why
lore-index 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 10d 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 — 76 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Lore Indexing & Project Management
Lore uses an opt-out (blacklist) model: ALL projects are indexed by default. Users can exclude specific projects they don't want indexed.
Two source agents are indexed in the same DB:
- Claude Code sessions from
~/.claude/projects/(override withCLAUDE_PROJECTS_DIR) - OpenAI Codex CLI sessions from
~/.codex/sessions/(override withCODEX_SESSIONS_DIR)
Codex sessions are grouped by cwd (read from each file's session_meta line) and surfaced as virtual projects with a codex- dirName prefix. The same project working directory may appear twice in the list — once as a Claude Code project (no prefix) and once as a Codex project (codex- prefix). They are independent rows; excluding one does not affect the other.
First-Time Setup
If the user has never used lore indexing before, or asks to index without context, walk them through:
- Check current state first -- call
statusto see if anything is indexed, thenmanage_projects(action: "list")to see available projects. - Explain what they're looking at:
- How many projects exist, how many are excluded. By default, all are indexed.
- Ask what they want:
- Index everything (just run
index())? Exclude certain projects first?
- Index everything (just run
- Execute based on their answer.
Do not skip the explanation step. The user needs to understand what's happening.
Index Options
| User intent | Tool call | Existing data |
|---|---|---|
| Index everything (default) | index() -- incremental index for all non-excluded projects |
Preserved |
| Index a specific project | index(project: "/full/path/to/project") -- indexes that project (even if excluded) |
Preserved |
| Start fresh | index(mode: "rebuild") -- deletes ALL indexed data and re-indexes from scratch |
Deleted |
| Stop running index | index(mode: "cancel") |
-- |
Important: Always use full project paths, not fuzzy names. Never summarize or drop rows from tool results when presenting to the user.
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.
- 10d ago First seen · 76 lines · 143 tokens per session scan A 1bfc92e07cc6
lore-index is a skill published in the GitHub repository hyunjae-labs/lore (8 stars, last pushed 3mo ago), licensed MIT. It adds 143 tokens to every session and 970 once invoked, about $0.0007 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 skills, from other repositories
media-ingest
Ingest video, audio, PDF, book, screenshot, and GitHub repo content into the brain. Multi-format handling with entity extraction and backlink propagation. Covers video-ingest, youtube-ingest, and book-ingest subtypes.
mem0-oss-to-platform
Plan and then execute a migration of a project from the mem0 open-source / self-hosted SDK (the local Memory class) to the mem0 Platform / hosted / managed SDK (the MemoryClient class). Use this whenever a developer wants to move, switch, or migrate their mem0 usage off OSS/self-hosted to the hosted API — e.g.…
Cortex
Operate Cortex, the LifeOS memory system — the typed Knowledge Archive (People, Companies, Ideas, Research with typed related: links) plus recall of prior work sessions, ISAs, and conversations. Search, add, harvest, develop, ingest, distill, graph-navigate, recall. USE WHEN cortex, knowledge, knowledge base, search…
memory
Use when the user asks to remember, recall, forget, update, search, or inspect durable OpenSquilla memory, including profile facts in USER.md and long-term notes in MEMORY.md or memory//.md.
ha-data-stores
Map of Hope Agent's local data stores and safe read-only query workflow. Use when the user asks where Hope Agent stores data, wants to inspect sessions/messages/memory/logs/background jobs/knowledge indexes/settings, asks the model to query local app data, or debugging requires checking persisted state. Trigger…
establishing-project-context
Use when the user asks to establish shared project language, or project work exposes a conflicting, renamed, or deprecated domain term that needs active semantic modeling. Routine small tasks stay on the fast path.