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-inquirygit 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-inquiry)<a href="https://agentmods.dev/skills/arjunpatel7/shikhu/shikhu-inquiry"><img src="https://agentmods.dev/badge/skills/arjunpatel7/shikhu/shikhu-inquiry/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-inquiry"><img src="https://agentmods.dev/badge/skills/arjunpatel7/shikhu/shikhu-inquiry.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 | $0.00232 | $0.01619 |
| Opus 5.5 | $0.00093 | $0.00648 |
| Sonnet 5.5 | $0.00046 | $0.00324 |
| Haiku 4.5 | $0.00023 | $0.00162 |
Grade A, and why
shikhu-inquiry 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 2d 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.
How it starts
The opening of the file, as written. The whole thing — 142 lines — stays where its author put it; the contents beside it link to each section on GitHub.
shikhu-inquiry — answer from the codebase, then bank the question
Why this exists
Shikhu tracks how well the user understands their own code. Historically that meant generating quizzes and asking them to sit through them, which people don't do. But people do ask their agent to explain their code, constantly. This skill turns that existing habit into the same signal: the question they already asked becomes the seed of a quiz question, and the files you cite become the record of what it was about.
Two things follow from that, and they are the whole point:
- Show your work. Don't just answer — say which files answer it and why those files. The user should end the turn knowing where the answer lives, not just what it is.
- Ask once, cheaply. One short confirm closes the loop. Silence earns nothing.
0. Invoked explicitly?
If the user ran /shikhu-inquiry directly, skip any judgment about whether this is a
conceptual question — they've already made that call. Use their message as the question, or
ask them for one if they gave none, then continue from step 1.
1. Get the packet
shikhu inquiry-packet "<the user's question>"
If shikhu is not on PATH or is an older install without this command, invoke the module
directly instead: python -m shikhu inquiry-packet "<question>", using the interpreter for
this project.
Three possible outcomes:
| output | what it means | what you do |
|---|---|---|
START HERE + files |
files were found | continue to step 2 |
not answerable from this codebase |
the question is about a library, a tool, or general knowledge | answer normally, record nothing, skip the confirm |
No cached file summaries |
the repo hasn't been summarized | say one line: "shikhu has no summaries for this repo yet — shikhu summarize would let me point at files." then answer normally |
Never invent a packet. If the command fails for any reason, just answer the question normally and say nothing about shikhu.
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.
- 2d ago First seen · 142 lines · 232 tokens per session scan A 5624d03ac0ff
shikhu-inquiry is a skill published in the GitHub repository arjunpatel7/shikhu (12 stars, last pushed yesterday), licensed MIT. It adds 232 tokens to every session and 1,619 once invoked, about $0.0009 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…
hps-bauhaus
A visual-design fundamentals course for new brand designers — grid, type, color, and the exercises that build the eye. Built as a decision-grade professional training deck for junior designers, new hires.
html-ppt-zhangzara-daisy-days
A customer-success workshop onboarding users to a project-management app — the first-value path and the habits that retain. Built as a decision-grade professional training deck for new customers, CS team.
html-ppt-zhangzara-retro-windows
An IT security-awareness training on spotting phishing — the tells, the drill, and what to do in the first 60 seconds. Built as a decision-grade professional training deck for all employees.
hr-onboarding
A new-hire onboarding plan as a single page — first week schedule, buddy + manager intro, learning track, equipment checklist, and "you're set when…" outcomes. Use when the brief mentions "onboarding", "new hire", "first week plan", or "入职".
playwright
Use when the task requires capturing or automating a real browser from the terminal.