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/create-areanpx skills add andresanemic/lore-plugin --skill create-areagit 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 | $0.00068 | $0.05665 |
| Opus 5 | $0.00034 | $0.02832 |
| Sonnet 5 | $0.00014 | $0.01133 |
| Haiku 4.5 | $0.00007 | $0.00566 |
Grade A, and why
create-area 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 — 435 lines — stays where its author put it; the contents beside it link to each section on GitHub.
create-area — Start a new work area
You are writing the same rule into a third repository. Not copying it — rewriting it, slightly differently each time, because you half-remember how you phrased it last time. In six months those three versions will disagree and none of them will be marked as the wrong one.
That is the problem an area solves. This skill creates the mother folder of a domain (web,
research, blog, video, apps…) with its own body of criteria (area Lore) that its projects
inherit. It is the "mold of molds": create-project creates projects INSIDE an area; create-area
creates the area.
Startup golden rule: the Lore's content is BORN from a brainstorm, not from a template filled in blind. The template gives the shape; the brainstorm gives the content.
Language rule: write EVERYTHING the skill generates — content AND artifact filenames — in the user's language (the language they speak during the brainstorm), NOT the language this skill is written in. The names used throughout this skill (
identidad.md,principios.md,FASES.md,proyectos/) are the Spanish canonical forms: localize them (e.g. English →identity.md,principles.md,PHASES.md,projects/). Fixed in every language: the selected contract name (CLAUDE.mdorAGENTS.md),lore/,index.md,golden-paths.md,_starter/, the<!-- lore:always-on -->marker pair (literal, never localized — localizing it breaks idempotent stamping silently). English terms of general technical use (workflow, stack, commit, scaffold, starter…) stay in English regardless.
Area model (federated + hybrid)
- The area is a light folder: one instruction contract +
FASES.md+lore/+proyectos/+_starter/. - The area carries its own project scaffold in
_starter/— the templates ({{CONTRACT_FILE}}.template.md,FASES.md, andgolden-paths.template.mdwhen the domain warrants it) tuned to this area's domain, plus any base code scaffold (e.g. a Next.js app for a web area).create-projectstamps new projects from{area}/_starter/, so each area's projects are born in that area's shape. - New projects are born inside
proyectos/(viacreate-project), inheriting the area Lore. - Existing projects are ADOPTED by registration in
FASES.md(with their path), without moving them or touching their git. - This skill does NOT adopt projects: it only creates the area clean. Adopting an existing
project is a later manual step (add its row to
FASES.md). - The area Lore distills the domain's cross-cutting method and standard, NOT one concrete
project's theory. A project consumes and feeds that standard; its own theory lives in the
project's
lore/.
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 · 435 lines · 68 tokens per session scan A c866c64ca3f3
create-area is a skill published in the GitHub repository andresanemic/lore-plugin (6 stars, last pushed 2d ago), licensed MIT. It adds 68 tokens to every session and 5,665 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…