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-botnpx skills add andresanemic/lore-plugin --skill create-botgit 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 | $0.00107 | $0.15955 |
| Opus 5 | $0.00053 | $0.07977 |
| Sonnet 5 | $0.00021 | $0.03191 |
| Haiku 4.5 | $0.00011 | $0.01596 |
Grade A, and why
create-bot 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 — 994 lines — stays where its author put it; the contents beside it link to each section on GitHub.
create-bot — Build a bot: one place to work
One question, and answering it means opening four repositories — because the criteria that decides it is spread across all four and none of them knows about the others. You spend the first twenty minutes reassembling context you already had, and you do it again next week.
A bot is one place to open that session. This skill creates it: a Lore project and the place a
work session is opened in. A bot does
not answer questions about the projects — it works in them. The instruction goes in, the bot
executes it against real files, the result comes back. Packaging is crystallization, not a
plugin wrap: transmute-lore CRYSTALLIZE writes one Markdown; unpacking it rebuilds the folder,
including lore-ecosistema/. That is how the work travels to someone who does not have your tree.
The north, and the only test that matters: a short instruction is enough. If the project had to be explained to the bot to get the result, criteria were missing from the load.
From an idea to a bot that can work
In nuevo mode, the user's declaration is a primary source even when no prior Lore or source
document exists. Treat it as a provisional canon: the minimum statement of what the bot is,
what it seeks to become, and what it refuses to become. Do not inflate it with model knowledge.
Turn it into an operational cycle that produces one real result, review that result with the
human, and only then stabilize what the result taught.
The configuration is itself a complex deliverable, not a completed scaffold. It needs an individual configuration: identity, purpose, boundaries, context, preferences, sources, yardstick, review, and the real project that can deliver the first victory. Ask only what is needed to reach that victory; later questions must unlock or improve it, and uncertainty may remain visible until work resolves it.
An interface may be an honest prototype of that cycle. Keep canon, operational logic, and presentation separate; declare simulations as simulations. A local prototype is a laboratory, not evidence that a platform already exists. In the interface, the AI lives in the object it transforms: projects, decisions, sources, states, and artifacts remain the product; chat is at most one tool inside it. Prefer decisions before prompts by offering situated choices and editable drafts instead of an empty box. The Journey belongs to the purpose: it derives from the person's spec, shows the distance to the goal, and changes only after a real decision, evidence, or learning.
What ships with it
3 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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 · 994 lines · 107 tokens per session scan A 3cf16e7d449f
create-bot is a skill published in the GitHub repository andresanemic/lore-plugin (6 stars, last pushed 2d ago), licensed MIT. It adds 107 tokens to every session and 15,955 once invoked, about $0.0005 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
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.
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…
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.
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…
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"…