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 arjunpatel7/shikhu --skill shikhu-studygit clone --depth 1 https://github.com/arjunpatel7/shikhuWrote 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/arjunpatel7/shikhu/shikhu-study)<a href="https://agentmods.dev/skills/arjunpatel7/shikhu/shikhu-study"><img src="https://agentmods.dev/badge/skills/arjunpatel7/shikhu/shikhu-study/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/arjunpatel7/shikhu/shikhu-study"><img src="https://agentmods.dev/badge/skills/arjunpatel7/shikhu/shikhu-study.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 | $0.00040 | $0.01592 |
| Opus 5.5 | $0.00016 | $0.00637 |
| Sonnet 5.5 | $0.00008 | $0.00318 |
| Haiku 4.5 | $0.00004 | $0.00159 |
Grade A, and why
shikhu-study 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 today.
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 — 120 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/shikhu-study — guided file review before a quiz
About shikhu
Shikhu is a knowledge-coverage CLI that tracks how well a user understands their own codebase. It generates MCQ questions from each tracked file via an LLM (OpenRouter), quizzes the user in the terminal, and counts "golden" questions (answered correctly and user-validated as testing real understanding) — 3 goldens per file (1 for files under 75 non-blank lines) means the file is "covered." shikhu is the CLI entry point.
There are two ways in. /shikhu-study <file> is the deliberate one: the user picks a file
and you walk it. The other is shikhu-inquiry, which triggers when they ask a conceptual
question mid-task — same destination, no ceremony. Both write to the same tables, so a
question asked either way can seed a quiz. If the user is asking about their code in passing
rather than sitting down to study a file, prefer shikhu-inquiry.
The flow is code → study → quiz. /shikhu-study is the learn step: you build the user's mental model of one file before they quiz on it, and every conceptual question they ask gets logged so shikhu generate-from-study <file> can later seed quiz Qs that test those same concepts.
Your role
You are the user's study partner. Your job in this skill is the study step: build the user's mental model of a specific file before they take a quiz on it, so the quiz tests knowledge instead of being their first read.
1. Resolve the target file
The argument is $ARGUMENTS. Treat it as the path to study.
- If no argument is provided, tell the user
Usage: /shikhu-study <file-path>and stop. (Auto-recommendation is a follow-up ship, not in scope here.) - Verify the file exists with
Readbefore proceeding. If it doesn't, stop and tell the user. - Check that the file is tracked by git:
If the command exits non-zero (file untracked), tell the user one line — "Heads up:git ls-files --error-unmatch "$ARGUMENTS"$ARGUMENTSisn't tracked by git, soshikhu refreshandshikhu coveragewon't see it until yougit addit. /shikhu-study still works." — then continue. Don't stop.
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.
- today Changed 9e2e2210d31d
- 22d ago First seen · 120 lines · 40 tokens per session scan A 6de1f522d62b
shikhu-study is a skill published in the GitHub repository arjunpatel7/shikhu (14 stars, last pushed today), licensed MIT. It adds 40 tokens to every session and 1,592 once invoked, about $0.0002 per session on Opus 5.5. 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 2026-10-04.
Other skills, from other repositories
immersive-reading
Turn long-form source material into bespoke interactive learning spaces. Use when the user wants to convert a blog post, essay, transcript, note, paper, or other long content into a polished static reader with chapters, sections, quotes, search, highlights, notes, optional bilingual support, light/dark mode, and…
playwright
Use when the task requires capturing or automating a real browser from the terminal.
show-me
Help the user understand the current topic visually with concise diagrams, code-shape sketches, and focused HTML artifacts.
document-service
This skill should be used when the user asks to "analyze this codebase", "document this service", "generate technical docs", "I inherited this code", "help me understand this system", "create docs for this project", "what does this system look like", "onboard me to this codebase", "this codebase has no docs"…
hyperpod-version-checker
Check and compare software component versions on SageMaker HyperPod cluster nodes - NVIDIA drivers, CUDA toolkit, cuDNN, NCCL, EFA, AWS OFI NCCL, GDRCopy, MPI, Neuron SDK (Trainium/Inferentia), Python, and PyTorch. Use when checking component versions, verifying CUDA/driver compatibility, detecting version mismatches…
directory-management
Manages project directory setup and artifact organization. Use when starting a new project, resuming an existing one, or when a PLAN.md needs to be associated with a project directory. Creates the project folder structure (specs/, scripts/, notebooks/, manifests/, agentmemory/) and resolves project naming.