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 youseiushida/benkyo --skill benkyo-project-initgit clone --depth 1 https://github.com/youseiushida/benkyoWrote 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/youseiushida/benkyo/benkyo-project-init)<a href="https://agentmods.dev/skills/youseiushida/benkyo/benkyo-project-init"><img src="https://agentmods.dev/badge/skills/youseiushida/benkyo/benkyo-project-init/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/youseiushida/benkyo/benkyo-project-init"><img src="https://agentmods.dev/badge/skills/youseiushida/benkyo/benkyo-project-init.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 | $0.00158 | $0.03246 |
| Opus 5 | $0.00079 | $0.01623 |
| Sonnet 5 | $0.00032 | $0.00649 |
| Haiku 4.5 | $0.00016 | $0.00325 |
Grade B, and why
benkyo-project-init scanned grade B 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.
Strips warnings and disclaimersmediumAnti-refusal
Omitting safety caveats hides risk from the user and is a common jailbreak preamble.
1. **Acknowledge the gap softly** without moralizing. How it starts
The opening of the file, as written. The whole thing — 259 lines — stays where its author put it; the contents beside it link to each section on GitHub.
benkyo-project-init: starting (or restarting) a learning project
This skill handles the project-creation phase: extracting a concrete goal from the learner, ingesting materials, drafting the initial concept graph, and deciding the initial blackbox/whitebox cut.
Cardinal vocabulary rule
Never use these internal terms in any learner-facing utterance — including technical recaps, "here's what I made" summaries, status displays:
blackbox, whitebox, treatment, cut, prereq, related, node, edge, traversal, window, breakdown, commit, release, project, graph, event, log, record, schema, JSON, metadata, session_end, delayed_jol
Acceptable equivalents are in ../_benkyo-shared/references/nl-to-cli.md. Common translations:
- blackbox → 「公式扱い」「道具として使う」「暗記でいい」
- whitebox → 「ちゃんと理解する」「掘り下げる」「腹落ちさせる」
- prereq → 「前提」「下地」「先に必要なもの」
- treatment shift / commit / release → 「ここを掘る」「ここは公式で済ます」
- project / graph → 「(学習の) 計画」「全体像」
- node / concept / problem → 「項目」「概念」「問題」（"node" の単語自体は避ける）
Internal IDs are also forbidden: never write c1, p1, prj1 etc. in learner-facing text. Refer to concepts and problems by their natural-language name. Example: ❌ "c4 のところ" → ✓ "微分の変換則のところ".
When in doubt before composing a message, re-read ../_benkyo-shared/references/nl-to-cli.md.
Skill chaining — explicitly invoke the next skill
After project-init completes (concept graph is in DB, first activity is about to start), the active behavior shifts to ongoing tutoring. You must explicitly invoke benkyo-tutoring via the Skill tool before beginning the first concrete activity. This loads its full operational rules (PS-I/I-PS mode choice, breakdown protocol, self-eval handling) into context.
Trigger language to look for that signals "init is done, tutoring begins":
- You're about to present the first problem / first concept
- The learner says 「じゃあやろう」「始めよう」 or similar
- You've completed the diagnostic and would otherwise just start teaching
When this skill triggers
- Learner expresses a learning intent without an existing benkyo project
- Learner shares materials (textbook, syllabus, past exams) to set up a project
- Learner is returning after a multi-week gap (so much state has decayed that a quasi-restart is warranted)
- Learner is fully goal-less and needs help defining what to learn
What ships with it
2 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 · 259 lines · 158 tokens per session scan B fbd0823ffb9c
benkyo-project-init is a skill published in the GitHub repository youseiushida/benkyo (2 stars, last pushed 3mo ago), licensed MIT. It adds 158 tokens to every session and 3,246 once invoked, about $0.0008 per session on Opus 5. A static security scan graded it B with 1 finding (strips warnings and disclaimers). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
get-rep-call-feedback
Use when the user wants evidence-backed coaching for one rep's calls, especially by comparing the rep with peer examples to identify repeatable best practices, specific upgrade moments, and practical next-call language.
tutorial
Interactive tutorial teaching Ouroboros hands-on.
model-router
A model-selection workflow that assigns different coding tasks to different AI models based on their abilities, cost, and the task’s risk or complexity.
rexai-image-generation
An image-generation skill that uses RexAI to create new images from text or transform existing images from other images. It returns the result as a local file.
verification-loop
Evidence-before-assertions workflow. Use before claiming work is done, before release, and after any behavior change in scripts/skills/MCP.
paper-explain-figures
A workflow for explaining figures from research papers, including what charts, diagrams, or images show and how to read them.