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/pyros-projects/limitless/learn-anythingnpx skills add pyros-projects/limitless --skill learn-anythinggit clone --depth 1 https://github.com/pyros-projects/limitlessWrote 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/pyros-projects/limitless/learn-anything)<a href="https://agentmods.dev/skills/pyros-projects/limitless/learn-anything"><img src="https://agentmods.dev/badge/skills/pyros-projects/limitless/learn-anything.svg" alt="Measured on agentmods" 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 | $0.00200 | $0.01844 |
| Opus 5 | $0.00100 | $0.00922 |
| Sonnet 5 | $0.00040 | $0.00369 |
| Haiku 4.5 | $0.00020 | $0.00184 |
Grade A, and why
learn-anything 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 4d 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 — 158 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Learn Anything — Curricula That Earn The Next Tier
Overview
A learn-anything curriculum is a moving target. This skill never dumps a full beginner→expert opus. It web-researches how this domain is taught, locks a domain-shaped structure, and fully formulates only Tier 1 — lessons through the first failable capstone. Later tiers stay as titles/exit-goals until the learner clears the gate; then the next block is authored fresh (new search + learner feedback).
Lesson checks are formative and non-failable (they persist capability notes; they never block within-tier progress). Capstones fail or pass.
Persist learner state under ~/.limitless/learn-anything/<slug>/ by default
(see references/persistence.md). Do not fill the user's project with
training debris unless they ask.
Modes (classify first)
| Mode | Signals | What you do |
|---|---|---|
| Genesis | New topic / "build me a curriculum" | Recon → structure → emit Tier 1 only |
| Continue | "next tier", "I passed the capstone" | Load state → fresh recon → emit one next tier only |
| Report | "progress report", "how am I doing", "what would help me move faster" | Load state → structured report (see references/reporting.md) |
| Lesson/assess | "I'm done with L2", "grade this", "run the formative" | Update capability map; never invent a fail gate on formatives |
If ambiguous, ask one clarifying question, then proceed.
Phase 0 — Preflight
- Derive a stable
slugfrom the topic (e.g.number-theory,deadlift-2x-bw). - Check for existing state:
ls ~/.limitless/learn-anything/<slug>/.- Exists + continue/report → load it; do not reinvent.
- Genesis with existing state → confirm overwrite vs resume.
- Probe web search (SearXNG / available web search tools). Record live or dead.
Phase 1 — Pedagogy recon (mandatory before structure)
Before writing any lesson list, search how this domain is taught and sequenced — not only what the topic is.
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.
- 4d ago First seen · 158 lines · 200 tokens per session scan A e3b90429eb74
learn-anything is a skill published in the GitHub repository pyros-projects/limitless (9 stars, last pushed 21d ago), licensed MIT. It adds 200 tokens to every session and 1,844 once invoked, about $0.0010 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
memory-protocol
Universal protocol for total-agent-memory MCP server. Activate at session start, before any non-trivial task, after every significant action, on errors, and at session end. Relevant whenever the user mentions: memory, recall, past context, decisions history, conventions, lessons learned, "продолжаем", "сохранись"…
new-feedback
Log a harness lesson / post-incident so the SYSTEM improves, not just this one bug — fires on "log a harness lesson", "post-incident", "we should make this less likely", System-Evolution moments. Part of the Agentsmith harness; scaffolds a numbered docs/feedback/NNNN-.md with the five-stage template (R9 — numbers are…
memory
Activate this skill when starting a new session, beginning a new task, saving knowledge, recalling past decisions, or after completing significant work. Also activate on errors to log them for pattern analysis. Relevant when the user asks about memory, past context, lessons learned, decisions history, project…
beamer-academic
Generate high-quality academic Beamer slides from a thesis/paper (PDF, Word, or LaTeX source). Compatible with Claude Code and Codex. Supports thesis defense, proposal presentations, and conference talks. Built-in layout library with 13 professional page types, 5 color schemes, and interactive editing loop. Use when…
教程类H5-小红书小工具
用 AI 生图 + SPA 课程架构 + 离线 H5 zip = 在小红书"创作者中心 → 小工具"发布的多课程 H5 互动产品。讲清楚 4 层栈 / 5 步流程 / 7 节课程都适用。触发词：「做教程类 H5」「小红书小工具」「H5 课程」「离线 H5 课程」「多节课 H5」。.
prompt-decorators-usage
Use when a user's prompt would clearly benefit from a reasoning, structure, tone, or verification decorator - or when they ask "what decorators should I use?". Teaches when and how to suggest inline ::Name(params) sigils instead of repeating verbose prompt-engineering instructions manually.