benkyo-graph-edit

benkyo-graph-edit is a skill for Claude Code from youseiushida/benkyo. It costs 147 tokens per session (3,695 once invoked), scanned A, original, MIT.

A tool for organising a learner’s study map by adding, removing, splitting, combining, or connecting concepts and problems. It keeps track of which topics belong together and which provide a foundation for others.

In plain words
What is it for?
Use it to add a newly discovered concept, correct relationships between topics, separate combined subjects, or mark two ideas as related.
Why use it?
It prevents important topics from being missing, duplicated, too broad, or disconnected from the rest of the subject.

Skill for Claude Code

Written for Claude Code: installed under .claude/.

Part of the benkyo plugin — 5 skills shipped together

Good fit Use it to add a newly discovered concept, correct relationships between topics, separate combined subjects, or mark two ideas as related.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/youseiushida/benkyo/benkyo-graph-edit
Install

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.

Any agent
npx skills add youseiushida/benkyo --skill benkyo-graph-edit
Clone the repo
git clone --depth 1 https://github.com/youseiushida/benkyo

Made for: Claude Code.

Or install benkyo, the plugin that ships this one along with the rest of its 5 skills.

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 benkyo-graph-edit

README.md
[![agentmods](https://agentmods.dev/badge/skills/youseiushida/benkyo/benkyo-graph-edit/github.svg)](https://agentmods.dev/skills/youseiushida/benkyo/benkyo-graph-edit)
Your own site
<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.

agentmods 80×15 button for benkyo-graph-edit

Your own site · 80×15
<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>
Per session 147 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,695 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 $0.00147 $0.03695
Opus 5 $0.00073 $0.01847
Sonnet 5 $0.00029 $0.00739
Haiku 4.5 $0.00015 $0.00369

Measured 10d ago against content hash 2f47f2ccae80, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

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.

.claude/skills/benkyo-graph-edit/SKILL.md · 316 lines

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 related edge if the relationship is real
  • Genuinely the same content but worded differently? → concept merge <source> --into <canonical> (see "Merge protocol" below)

Read the full file on GitHub · 316 lines

Files

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.

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. 10d ago First seen · 316 lines · 147 tokens per session scan A 2f47f2ccae80

Subscribe to this mod's changes

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.