sensei: Skill for Claude Code

.claude/skills/challenge-description/SKILL.md

challenge-description is a skill for Claude Code from dojo-coder/sensei. It costs 56 tokens per session (663 once invoked), scanned A, original, MIT.

A writing and review procedure for DojoCode challenge descriptions. DojoCode challenges are programming exercises, and this procedure makes them read like clear school textbook tasks.

In plain words
What is it for?
It helps create, rewrite, translate, or review challenge descriptions, including their task wording, rules, examples, and language level.
Why use it?
Challenge statements can be ambiguous or inconsistent in level, requirements, examples, and translation. A fixed process makes the exercise easier to understand and review.

Skill for Claude Code

Written for Claude Code: installed under .claude/.

This is dojo-coder/sensei's own configuration. It tells Claude Code how to work on sensei itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything sensei configures →

Reuse

Borrowing it

Nothing to install: this file belongs to dojo-coder/sensei. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/dojo-coder/sensei/main/.claude/skills/challenge-description/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/dojo-coder/sensei

Made for: Claude Code.

Wrote 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.

agentmods badge for challenge-description

README.md
[![agentmods](https://agentmods.dev/badge/skills/dojo-coder/sensei/challenge-description/github.svg)](https://agentmods.dev/skills/dojo-coder/sensei/challenge-description)
Your own site
<a href="https://agentmods.dev/skills/dojo-coder/sensei/challenge-description"><img src="https://agentmods.dev/badge/skills/dojo-coder/sensei/challenge-description/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.

agentmods 80×15 button for challenge-description

Your own site · 80×15
<a href="https://agentmods.dev/skills/dojo-coder/sensei/challenge-description"><img src="https://agentmods.dev/badge/skills/dojo-coder/sensei/challenge-description.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 56 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 663 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00056 $0.00663
Opus 5.5 $0.00022 $0.00265
Sonnet 5.5 $0.00011 $0.00133
Haiku 4.5 $0.00006 $0.00066

Measured 3d ago against content hash 91ff7a2f1051, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

challenge-description 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 3d 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.

.claude/skills/challenge-description/SKILL.md · 44 lines

How it starts

The opening of the file, as written. The whole thing — 44 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Challenge description

The full rules are in style/challenge-description-style.md. Read that file before writing a single sentence; this skill is only the procedure.

Writing a new description

  1. Settle the level (beginner / intermediate / expert) and the kind (program with or without input, function, UI component, API). The level table in section 2 of the guide fixes the length, the number of requirements and how many examples.
  2. Look up the vocabulary. If style/textbooks/*.txt exist (otherwise run python style/textbooks/fetch.py), grep them for the concept the challenge is about and read how two or three exercises on that topic are worded: grep -n -i "divizor" style/textbooks/*.txt. Use the wording and the structure, never the exercise itself.
  3. Write the statement: optional context of 1-2 sentences, then the task in one sentence with a textbook opening ("Write a program that reads … and prints …", "Write the function f(x), which receives … and returns …", "Build a Name component that shows …"). Types and limits go next to each name.
  4. Write ### Rules & clarifications: one fact per bullet, special cases included, the language named, platform notes last. Add ### Input and output before it only when the task sentence cannot carry the data.
  5. Write ### Examples: the ordinary case first and explained, special cases after; a function example reads "f(7) returns True", without an arrow. Run every example against the reference solution.
  6. Run the checklist in section 6 of the guide and remove every phrase from the "Words to avoid" table.
  7. Copy the same text into README.md and the description field of details.json.

Romanian

The platform translates the English description automatically, so the challenge files hold English only. Write Romanian when the user asks for it (a review, a proposed translation, text for a teacher):

  • write it as a Romanian Informatics teacher would, following section 4 of the guide: second person singular ("Scrie", "Determină", "Afișează"), diacritics, every term from the glossary;
  • never translate anything in backticks or code blocks, nor the strings the tests compare;
  • keep the structure of the English text; headings ### Restricții și precizări, ### Exemple.

Read the full file on GitHub · 44 lines

Changes

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.

  1. 3d ago First seen · 44 lines · 56 tokens per session scan A 91ff7a2f1051

Subscribe to this mod's changes

challenge-description is a skill published in the GitHub repository dojo-coder/sensei (2 stars, last pushed 4d ago), licensed MIT. It adds 56 tokens to every session and 663 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 2026-11-12.

Related

challenge-description compared with skills from other repositories

challenge-description next to 6 skills from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
challenge-descriptiondojo-coder/senseiSkill24d agoMITA56Claude Code
hr-onboardingnexu-io/open-designSkill108ktodayApache-2.0A62Claude Code, Codex
book-mirrorgarrytan/gbrainSkill33ktodayMITA138Claude Code
exam-forecastanthropics/claude-for-legalSkill10kyesterdayApache-2.0A73Claude Code
lean-formalizewanshuiyin/Auto-claude-code-research-in-sleepSkill19kyesterdayMITA81Claude Code
eli5companion-inc/feynmanSkill10ktodayMITA63Claude Code, Codex
deck-course-modulenexu-io/html-anythingSkill10.0ktodayApache-2.0A25Claude Code, Codex