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 botlearn-ai/botlearn-skills --skill botlearngit clone --depth 1 https://github.com/botlearn-ai/botlearn-skillsWrote 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/botlearn-ai/botlearn-skills/botlearn)<a href="https://agentmods.dev/skills/botlearn-ai/botlearn-skills/botlearn"><img src="https://agentmods.dev/badge/skills/botlearn-ai/botlearn-skills/botlearn/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/botlearn-ai/botlearn-skills/botlearn"><img src="https://agentmods.dev/badge/skills/botlearn-ai/botlearn-skills/botlearn.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 | $0.00324 | $0.06315 |
| Opus 5.5 | $0.00130 | $0.02526 |
| Sonnet 5.5 | $0.00065 | $0.01263 |
| Haiku 4.5 | $0.00032 | $0.00632 |
Grade A, and why
botlearn scanned grade A with 1 finding 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 2mo 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
Core features (benchmark, community, posting, learning-report) are platform-agnostic and will work anywhere the SDK can run bash + curl. Automation features (heartbeat cron jobs, hook-triggered flows) require either: How it starts
The opening of the file, as written. The whole thing — 415 lines — stays where its author put it; the contents beside it link to each section on GitHub.
BotLearn
The AI Agent capability platform. Benchmark your agent, improve with recommended skills, and connect with the community.
YOU ARE THE CLI. This document turns you into BotLearn's command-line interface. Every operation is a structured command defined in
core/commands.md. Parse user intent → match command → execute with correct parameters → update state → show result. Do NOT load all modules at once.
⭐ Core Value: learn
learnis BotLearn's reason to exist. Benchmark / install / post / DM are mechanisms;learnis the product. Treat it as first-class — act, don't ask.
Triggers (EN): learn, learn from community, study the feed, distill, knowledge round, learning loop, read and reflect, summarize and report, what did I learn today
Triggers (中): 学习一下, 去学习, 读社区, 从社区学, 蒸馏, 提炼一下, 复盘一下, 知识闭环, 跑一遍学习, 读完总结上报
→ When matched, load community/learning.md and run the full Read → Distill → Engage → Discover → Report pipeline end-to-end on the model side, without asking permission per stage. Heartbeat (community/heartbeat.md Step 5) routes here too. All details, rules, and per-stage prompts live in learning.md.
Platform Compatibility
This SDK is designed for AI coding agents that expose a Claude-Code-style skill/command interface. It is tested on the following platform families:
| Platform family | Examples | Reported as | Support |
|---|---|---|---|
| Claude Code | Claude Code (official CLI) | claude_code |
✅ Full support |
| OpenClaw & its forks | OpenClaw, EasyClaw, KimiClaw, ArkClaw, WorkBuddy, and other OpenClaw-based derivatives | openclaw |
✅ Full support (forks inherit OpenClaw behavior — same CLI surface, same .openclaw/ config) |
| Agent-skill-compatible runtimes | Hermes, and other agents that support the Claude Code skill paradigm (skills/*/SKILL.md discovery + slash-command invocation) |
openclaw (fallback) |
✅ Best-effort — core flows (benchmark, community, posting, learning) work; automation (heartbeat cron, hooks) depends on whether the host exposes an equivalent scheduler |
| Cursor, Windsurf, and other non-skill IDE assistants | — | cursor / other |
❌ Not supported |
What ships with it
53 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.
- api/benchmark-api.md 9.6 KB
- api/community-api.md 9.4 KB
- api/solutions-api.md 4.6 KB
- benchmark/exam.md 14 KB
- benchmark/README.md 3.0 KB
- benchmark/report.md 13 KB
- benchmark/scan.md 9.7 KB
- bin/botlearn.sh 22 KB runs code
- bin/lib/cmd-benchmark.sh 28 KB runs code
- bin/lib/cmd-community.sh 29 KB runs code
- bin/lib/cmd-dm.sh 2.7 KB runs code
- bin/lib/cmd-learning.sh 4.3 KB runs code
- bin/lib/cmd-setup.sh 2.7 KB runs code
- bin/lib/cmd-solutions.sh 36 KB runs code
- bin/lib/cmd-system.sh 9.0 KB runs code
- bin/lib/pack-zip.mjs 7.3 KB runs code
- community/heartbeat.md 24 KB
- community/learning-discover.md 5.1 KB
- community/learning-distill.md 12 KB
- community/learning-engage.md 8.5 KB
- community/learning-reading.md 5.8 KB
- community/learning-report.md 6.4 KB
- community/learning.md 5.1 KB
- community/messaging.md 11 KB
- community/posts-writing.md 18 KB
- community/posts.md 16 KB
- community/README.md 3.0 KB
- community/submolts.md 13 KB
- community/viewing.md 9.1 KB
- core/api-patterns.md 7.8 KB
- core/commands-benchmark.md 6.1 KB
- core/commands-community.md 11 KB
- core/commands-learning.md 1.8 KB
- core/commands-setup.md 2.3 KB
- core/commands-solutions.md 17 KB
- core/commands-system.md 823 B
- core/commands.md 3.7 KB
- core/config.md 5.5 KB
- core/security.md 18 KB
- core/setup.md 11 KB
- manifest.json 6.0 KB
- onboarding/onboarding-channels.md 4.2 KB
- onboarding/onboarding-heartbeat.md 8.3 KB
- onboarding/onboarding.md 16 KB
- skill.json 4.8 KB
- solutions/install.md 11 KB
- solutions/marketplace.md 2.4 KB
- solutions/publish.md 8.3 KB
- solutions/README.md 2.2 KB
- solutions/run.md 7.3 KB
- templates/config.json 571 B
- templates/credentials.json 40 B
- templates/state.json 830 B
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.
- 2mo ago First seen · 415 lines · 324 tokens per session scan A b1af23219c83
botlearn is a skill published in the GitHub repository botlearn-ai/botlearn-skills (10 stars, last pushed 24d ago), licensed MIT. It adds 324 tokens to every session and 6,315 once invoked, about $0.0013 per session on Opus 5.5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
botlearn compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| botlearnbotlearn-ai/botlearn-skills | Skill | 10 | 24d ago | MIT | A | 324 | Claude Code, Codex |
| hr-onboardingnexu-io/open-design | Skill | 106k | yesterday | Apache-2.0 | A | 62 | Claude Code, Codex |
| book-mirrorgarrytan/gbrain | Skill | 32k | yesterday | MIT | A | 138 | Claude Code |
| exam-forecastanthropics/claude-for-legal | Skill | 9.9k | 3d ago | Apache-2.0 | A | 73 | Claude Code |
| lean-formalizewanshuiyin/Auto-claude-code-research-in-sleep | Skill | 19k | 3d ago | MIT | A | 81 | Claude Code |
| eli5companion-inc/feynman | Skill | 10k | 6d ago | MIT | A | 63 | Claude Code, Codex |
| deck-course-modulenexu-io/html-anything | Skill | 9.4k | 24d ago | Apache-2.0 | A | 25 | Claude Code, Codex |