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.
git clone --depth 1 https://github.com/PranitMohnot/repo-learner-suiteWrote 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/commands/pranitmohnot/repo-learner-suite/learn)<a href="https://agentmods.dev/commands/pranitmohnot/repo-learner-suite/learn"><img src="https://agentmods.dev/badge/commands/pranitmohnot/repo-learner-suite/learn/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/commands/pranitmohnot/repo-learner-suite/learn"><img src="https://agentmods.dev/badge/commands/pranitmohnot/repo-learner-suite/learn.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 | $0.00000 | $0.00290 |
| Opus 5.5 | $0.00000 | $0.00116 |
| Sonnet 5.5 | $0.00000 | $0.00058 |
| Haiku 4.5 | $0.00000 | $0.00029 |
Grade A, and why
learn 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 1mo 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.
What it actually says
/learn
Entry point for the repo-learner skill suite.
Routing
Parse the first word of $ARGUMENTS as the subcommand. If empty, check state and recommend ONE action (see orchestrator SKILL.md for the logic — never dump a menu).
| Subcommand | Sub-skill |
|---|---|
analyze [path] [--focus topic] |
repo-analyzer |
exercises [section] |
exercise-gen |
tutor [section-id] |
code-tutor |
quiz [section-id|--full] |
code-quiz |
status |
Parse learn/README.md checkboxes, summarize progress |
Fresh run (no learn/ directory)
- Auto-detect: primary language, framework, lockfile/package manager.
- MANDATORY: Ask 3-4 questions in one call (see orchestrator SKILL.md "Front-Loaded Questions"). Do NOT skip this and assume defaults — the user has preferences (especially env manager) that you cannot infer.
- Save answers to
learn/internals/.config.json. - Hand off to repo-analyzer, then exercise-gen. No stops between.
Status
Parse checkbox state from learn/README.md table rows. Count checked vs unchecked
per phase. Suggest the next unchecked section.
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.
- 1mo ago First seen · 31 lines · 0 tokens per session scan A ecec017cc6b5
learn is a command published in the GitHub repository PranitMohnot/repo-learner-suite (5 stars, last pushed 5mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 290 tokens. 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 commands, from other repositories
explain
Explain code or concepts clearly with practical examples and analogies.
review-record
Score the answers on a published review page into the Covate ledger.
review
Make a review quiz page from what is due and what you just learned.
learn
Append an insight to the daily llm-wiki. Inspired by everything-claude-code + karpathy llm-wiki.
dev-setup
Set up OLM development repositories and onboard to the team.
echo
Hello world plugin implementation.