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-graph-editgit 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-graph-edit)<a href="https://agentmods.dev/skills/youseiushida/benkyo/benkyo-graph-edit"><img src="https://agentmods.dev/badge/skills/youseiushida/benkyo/benkyo-graph-edit/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-graph-edit"><img src="https://agentmods.dev/badge/skills/youseiushida/benkyo/benkyo-graph-edit.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 | $0.00147 | $0.03695 |
| Opus 5 | $0.00073 | $0.01847 |
| Sonnet 5 | $0.00029 | $0.00739 |
| Haiku 4.5 | $0.00015 | $0.00369 |
Grade A, and why
benkyo-graph-edit 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 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.
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 — 316 lines — stays where its author put it; the contents beside it link to each section on GitHub.
benkyo-graph-edit: structuring and editing the graph
This skill governs all structural changes to the global benkyo graph: adding concept and problem nodes, adding/removing edges, deciding granularity, handling duplicates. The rules apply during project init AND mid-session (when graph gaps surface).
Cardinal vocabulary rule
Even when discussing graph edits with the learner, never use internal terms (node, edge, prereq, related, graph, granularity, merge, fork, event, log, record, schema, JSON, metadata) in learner-facing utterances. Translate:
- node → 「項目」「概念」「問題」
- edge → 「つながり」「関係」「線」
- prereq edge → 「前提」「土台になる関係」
- related edge → 「関連」「セットで覚える関係」
- merge → 「同じだから 1 つにまとめる」
- fork / split → 「細かく分ける」
- graph → 「全体像」「学習の地図」
Internal operation: benkyo edge add --from c1 --to c2 --type related
Spoken to learner: 「ラプラス変換とフーリエ変換, 混同しやすいから 『セットで覚えておく』マークしとくね」
Internal IDs are also forbidden: never write c1, c2, p1, prj1 etc. in learner-facing text. Especially in graph-edit, the temptation to say "c7 を追加して c1 に related で繋いだ" is high — translate to "『フーリエ変換』を追加して『ラプラス変換』とセットで覚える関係にしといた" instead.
See ../_benkyo-shared/references/nl-to-cli.md. Re-read before composing any learner-facing message that touches structural details.
When this skill triggers
- Learner explicitly asks for a structural change ("これも追加して", "これとあれは関連してる", "これは別物")
- During a tutoring session, you (the tutor) notice a needed graph change (the learner mentions a concept that's not yet in the graph; or two concepts that should be linked but aren't)
- During project init, while drafting the initial graph
Cardinal rule: always check identity before adding
The global graph is shared across projects. Adding a duplicate of an existing concept fragments the graph and undermines the cross-project reuse benefit.
Before any benkyo concept add:
benkyo concept find --content "<exact or near-exact name>"
If matches exist, evaluate:
- Same concept? → reuse the existing id; don't add
- Different but related? → add the new one, then add a
relatededge if the relationship is real - Genuinely the same content but worded differently? →
concept merge <source> --into <canonical>(see "Merge protocol" below)
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 · 316 lines · 147 tokens per session scan A 2f47f2ccae80
benkyo-graph-edit is a skill published in the GitHub repository youseiushida/benkyo (2 stars, last pushed 3mo ago), licensed MIT. It adds 147 tokens to every session and 3,695 once invoked, about $0.0007 per session on Opus 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 2026-08-31.
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.