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 instructions/agentculture/learn-cli/claude-mdgit clone --depth 1 https://github.com/agentculture/learn-cliWhat 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 | $0.03780 | $0.03780 |
| Opus 5 | $0.01890 | $0.01890 |
| Sonnet 5 | $0.00756 | $0.00756 |
| Haiku 4.5 | $0.00378 | $0.00378 |
Grade A, and why
learn-cli CLAUDE.md 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 yesterday.
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 — 259 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md
This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.
What learn-cli is
learn-cli is the learning front for the AgentCulture mesh: one product with
three faces — a CLI (command learn), an MCP server, and a web site
(target: https://agentculture.org/learn/, one sub-page per module) — over a
single idea: humans and agents learn a subject, step by step.
It is not a tutor itself. It is the portal that fronts per-subject tutor
CLIs — each tutor stays its own sibling repo with its own progression logic,
and learn drives them as external runtimes behind one door, one profile, one
site. The relationship is "learn-cli is to its subject CLIs what
league-of-agents-platform is to the arena runtime — it hosts and unifies, it
does not reimplement." The first subjects:
french-cli(commandfrench) andspanish-cli(spanish) — language tutors. Their verbs define the tutor UX learn-cli inherits; read them before designing anything. Both runbackend: colleague.culture-guide— the non-language subject (learning to build and lead agent teams), the proof the subject interface generalizes beyond languages.
The authoritative brief is issue #1 ("Build brief: learn"). Read it before doing product work.
Current state: scaffold, not product
Almost none of the product above is built yet. This repo was cloned from
culture-agent-template
and today contains only the template's agent-first CLI skeleton (identity +
introspection verbs) plus the mesh baseline (CI, skills, deploy). The subject
registry, the MCP server, the web site, cross-subject learner profiles, and any
actual tutoring do not exist. When you read the code and its self-describing
strings still say "a clonable template for AgentCulture mesh agents," that is
leftover template identity, not a description of the finished product — replacing
it with learn-cli's real identity is part of the build.
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.
- yesterday First seen · 259 lines · 3,780 tokens per session scan A ee606b117413
learn-cli CLAUDE.md is an instructions file published in the GitHub repository agentculture/learn-cli (1 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 3,780 tokens to every session, about $0.0189 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 instructions, from other repositories
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).
next.js AGENTS.md
Instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.