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 PranitMohnot/repo-learner-suite --skill repo-learnergit 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/skills/pranitmohnot/repo-learner-suite/repo-learner)<a href="https://agentmods.dev/skills/pranitmohnot/repo-learner-suite/repo-learner"><img src="https://agentmods.dev/badge/skills/pranitmohnot/repo-learner-suite/repo-learner/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/pranitmohnot/repo-learner-suite/repo-learner"><img src="https://agentmods.dev/badge/skills/pranitmohnot/repo-learner-suite/repo-learner.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 | $0.00092 | $0.04007 |
| Opus 5 | $0.00046 | $0.02004 |
| Sonnet 5 | $0.00018 | $0.00801 |
| Haiku 4.5 | $0.00009 | $0.00401 |
Grade C, and why
repo-learner scanned grade C 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 10d 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.
Recursive force deletehighDestructive command
rm -rf with a variable or a broad path is one typo away from removing the wrong tree.
into a real run, `rm -rf learn && mv learn_test learn` and re-run the How it starts
The opening of the file, as written. The whole thing — 382 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Repo Learner — Orchestrator
Routes /learn commands to the right sub-skill.
Command Routing
| Command | Sub-skill |
|---|---|
/learn analyze <path> |
repo-analyzer |
/learn exercises [section] |
exercise-gen |
/learn tutor [section] |
code-tutor |
/learn quiz [section] |
code-quiz |
/learn status |
(self — parse README.md checkboxes) |
/learn test |
full pipeline in test mode → learn_test/ (see below) |
No subcommand — always lead with one action
Check state and recommend ONE thing:
- No
learn/directory: "Let's start. I'll analyze the codebase and build your learning path." → run analyze pipeline. No menus. learn/curriculum.mdexists, no checkboxes ticked: "Your curriculum is ready — openlearn/curriculum.md(orlearn/curriculum.htmlfor interactive). Start with Section 0 (overview), or saytutor,quiz,exercises."- Some checkboxes ticked: "You're on Section X.Y. Pick up where you left off?"
→ recommend the next unchecked step. One escape line at the end:
"Or:
tutor,quiz,exercises,status."
Never dump a decision tree. One recommended action, one escape line.
Front-Loaded Questions (start of any fresh pipeline)
Before reading any code, ask the user 3–4 questions in a single AskUserQuestion call. The user's answers directly shape tutoring depth, exercise scaffolding, and environment setup — they cannot be auto-detected.
Step 0: auto-detect language + platform (silent)
Sniff the repo before asking anything:
| Signal | Language |
|---|---|
*.py, pyproject.toml, setup.py, requirements.txt, uv.lock, poetry.lock |
python |
Currently only Python is supported by the notebook scaffolder. Other
languages will be added as language profiles (see
exercise-gen/scripts/scaffold_notebook.py:LANGUAGE_PROFILES). If a
repo's primary language is not python, surface that to the user and ask
how to proceed.
Persist as repo.language in .config.json. Downstream skills
(exercise-gen, code-quiz) read it.
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.
- 10d ago First seen · 382 lines · 92 tokens per session scan C 65421c4166b0
repo-learner is a skill published in the GitHub repository PranitMohnot/repo-learner-suite (4 stars, last pushed 3mo ago), licensed MIT. It adds 92 tokens to every session and 4,007 once invoked, about $0.0005 per session on Opus 5. A static security scan graded it C with 1 finding (recursive force delete). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
learning-codebases
Use when the user wants to learn, understand, study, map, onboard to, or walk through an unfamiliar codebase or software project, especially when explanations should suit a beginner with basic Python knowledge.
lov-hanzi-lens
A research and infographic workflow for explaining one Chinese character, including its pronunciation, written form, history, meanings, and use in classical texts.
lov-subtitle-freedom
Create learner-friendly English subtitles with level-aware glosses and optional spoiler-safe subtitle sidecars.
lov-thesis-polish
An academic editing tool for improving an MBA thesis or dissertation in Markdown, a plain-text format for structured documents. It addresses language, argument structure, logic, research contributions, and formatting.
learning-assistant
An interactive study assistant that turns a learning goal into a structured plan and guides the learner through it. It uses a local knowledge graph, a connected record of topics and learning state, as its long-term memory.
reading-notes
Process a book or article into structured progressive summary notes saved to the resources folder. Use when the user has finished reading something and wants to capture structured notes — 'I just finished reading X', 'take notes on this book'. Do NOT use for: fetching and summarizing a URL now (use summarize)…