Agent Skill
Code Understand skill
code-understandAr9av/obsidian-wiki.skills/code-understand/SKILL.md
Map the load-bearing files, symbols, callers, and dependencies of an unfamiliar codebase before making changes. Use for architecture orientation, impact analysis, what-would-break questions, or finding callers. Uses CodeGraph when available and a dependency-free builtin fallback.
always on
55 tokname + description
once used
1,023 tokSKILL.md body
bundled files
0
repo stars
3.6kGitHub
Install the Code Understand skill
Skills CLI (Claude Code, Codex, Cursor and others)
npx skills add https://github.com/Ar9av/obsidian-wiki --skill code-understand
Claude Code, by hand (all projects)
git clone --depth 1 https://github.com/Ar9av/obsidian-wiki.git /tmp/obsidian-wiki mkdir -p ~/.claude/skills cp -R /tmp/obsidian-wiki/.skills/code-understand ~/.claude/skills/code-understand
For one project only, copy the folder into .claude/skills/ in that project instead. The agent picks it up when a task matches its description.
What it costs your context
Agent Skills load in three steps. Tokens counted with the o200k tokenizer; your model's count will differ a little.
| When | What loads | Cost |
|---|---|---|
| Every session | Name and description | 55 tok |
| When the agent uses it | The SKILL.md instructions | 1,023 tok |
| Only if opened | No bundled files | — |
Until it is used, code-understand costs about 25× less than the median MCP server we measured (1,363 tokens on every turn). Installing all 40 skills from Ar9av/obsidian-wiki would load 1,925 tokens of descriptions. Skills vs MCP study
Checks
Our checks found nothing to flag: it follows the Agent Skills specification's naming and size guidelines and doesn't pipe downloads into a shell.
Checked 2026-10-22 · method
What's inside
The headings of its SKILL.md. Read the full file on GitHub.
- Code Understand — On-Demand Architecture Focus Map
- When to reach for this
- Running it
- Reading the output
- If CodeGraph isn't installed
More skills from Ar9av/obsidian-wiki
- claude-history-ingestAr9av/obsidian-wiki
Ingest Claude Code conversation/session history into Obsidian as distilled knowledge. Use for importing or mining past Claude sessions, .claude data, project/session history, or audit logs.
3.6k43 tok idle · 5,382 in use - codex-history-ingestAr9av/obsidian-wiki
Ingest Codex CLI conversation/session history into Obsidian as distilled knowledge. Use for importing or mining ~/.codex sessions, rollout files, indexes, or transcript logs; use wiki-agent for targeted topic-only recall.
3.6k50 tok idle · 2,021 in use - copilot-history-ingestAr9av/obsidian-wiki
Ingest GitHub Copilot CLI/session history into Obsidian as distilled knowledge. Use for importing or mining Copilot history; not for general Copilot help, simple session search, or backup.
3.6k46 tok idle · 4,119 in use - cross-linkerAr9av/obsidian-wiki
Find and add missing cross-references between wiki pages. Use when pages are disconnected or after large ingestion. This modifies pages to add links; use wiki-lint for report-oriented structural auditing.
3.6k42 tok idle · 3,699 in use - daily-updateAr9av/obsidian-wiki
Run or configure the daily wiki maintenance cycle: check source freshness, refresh the index and hot.md, and manage its scheduled 9 AM launchd/systemd/cron reminder. Use for daily or morning wiki refresh or scheduler setup and verification.
3.6k51 tok idle · 2,588 in use - graph-colorizeAr9av/obsidian-wiki
Configure Obsidian graph colors by tag, folder, category, or visibility by updating .obsidian/graph.json. Use for graph colorization; preserve other graph settings and back up before changes.
3.6k44 tok idle · 2,272 in use - hermes-history-ingestAr9av/obsidian-wiki
Ingest Hermes agent history into Obsidian as distilled knowledge. Use for importing or mining ~/.hermes sessions, memories, or logs; use wiki-agent for targeted topic-only cross-agent recall.
3.6k45 tok idle · 2,048 in use - impl-validatorAr9av/obsidian-wiki
Independently check whether an implementation matches its stated goal and return PASS/WARN/FAIL with actionable issues. Use for second-opinion validation of an implementation or generated output.
3.6k37 tok idle · 1,026 in use