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 skills/andresanemic/lore-plugin/use-lorenpx skills add andresanemic/lore-plugin --skill use-loregit clone --depth 1 https://github.com/andresanemic/lore-pluginWhat 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 | $0.00070 | $0.10242 |
| Opus 5 | $0.00035 | $0.05121 |
| Sonnet 5 | $0.00014 | $0.02048 |
| Haiku 4.5 | $0.00007 | $0.01024 |
Grade A, and why
use-lore 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 — 567 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Using Lore
Yesterday you and an agent solved something hard. You argued about the edges, you threw away two approaches, and the thing finally worked. Today, new session, you are explaining it again from the beginning — and the agent is not worse. It simply never received what the two of you worked out. The facts may have survived in a file somewhere. The reason you changed your mind did not.
Lore is a spec-driven development kit built for that gap: it turns scattered, tacit project knowledge into distilled, invariant criteria that constrain every future decision. Where other SDD kits speak in pure engineering terms, this one borrows a linguistic and epistemic vocabulary — lore, identity, principles, transmutation, distillation — to name the same discipline.
This skill is the map. It teaches the model and points at the operating skills. Read it before invoking any other Lore skill.
This skill governs session openings too. A session that opens — including one resumed from a continuity summary, or handed an unfinished task — resolves what Lore governs its tree before continuing, and says so on screen: which bodies it loaded and from where. In a bot, load its canon and routing table first. Do not preload every federated body: load only the bodies selected by the task, leaving the rest reachable through the routing table. A change of territory mid-session (new task type, new tree) re-resolves the same way. "Finishing what was started" is not an exemption: continuing is deciding. Criterion that waits to be remembered is criterion that does not run.
0. Very first use of the kit — a brainstorm, not a menu (threshold)
If this machine has no Lore yet — no area with a lore/, no project carrying the six pieces —
this runs before anything else, and before offering any skill by name. The kit brainstorms to
build every artifact it makes; it would be incoherent for the kit itself to greet its first user
with a list of seven skills.
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 · 567 lines · 70 tokens per session scan A 48bf7bf15bae
use-lore is a skill published in the GitHub repository andresanemic/lore-plugin (6 stars, last pushed 2d ago), licensed MIT. It adds 70 tokens to every session and 10,242 once invoked, about $0.0003 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
init
Initialize a personal Trove, a local file-based knowledge index for Claude Code. Use when the user says start/set up/create my trove, or when they want to remember things but no trove exists yet. Scaffolds the trove directory, INDEX.md and entries/ folder at user scope (/.claude/trove, follows you everywhere) or…
remember
Capture a durable learning into the personal Trove. Use when the user says remember this, note this, save to trove, add to my trove, or when a session surfaces a decision, gotcha, convention/preference, or external reference worth keeping. Writes one atomic entry file and updates INDEX.md.
index
Index the repository into Trove memory layers (symbols, modules, subsystems, architecture). Use when the user asks to index the repo, build the trove index, refresh symbols, or re-index after large changes.
query
Progressive retrieval from the Trove index. Use when the user asks what Trove knows about a subsystem, where code lives, or wants context assembled before editing. Runs architecture -> subsystem -> module -> symbol retrieval with a context budget.
context-ingest
The single entry point for getting anything new into your context architecture. Takes any input (documents, URLs, YouTube, meeting notes, pasted content) and triages it: dump to inbox, park in planned, or integrate into active docs. WHEN TO USE: "Here's a document — integrate it into my context" "Save this for later"…
bcos-wiki
Wiki zone manager for BCOS — the universal long-form and cross-cutting content destination per plugin-storage-contract.md Rule 2. Stores runbooks, SOPs, decision logs, how-tos, glossaries, post-mortems, FAQs, meeting notes, and plugin cross-cutting context (charters, transcripts, research, customer-call notes). Two…