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 agentmods add commands/michael-ovo/obsidian-knowledge-agent/refactorgit clone --depth 1 https://github.com/Michael-OvO/obsidian-knowledge-agentWrote 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/commands/michael-ovo/obsidian-knowledge-agent/refactor)<a href="https://agentmods.dev/commands/michael-ovo/obsidian-knowledge-agent/refactor"><img src="https://agentmods.dev/badge/commands/michael-ovo/obsidian-knowledge-agent/refactor.svg" alt="Measured on agentmods" 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 | $0.00024 | $0.00273 |
| Opus 5 | $0.00012 | $0.00137 |
| Sonnet 5 | $0.00005 | $0.00055 |
| Haiku 4.5 | $0.00002 | $0.00027 |
Grade A, and why
refactor 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 4d 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.
What it actually says
Carry out the restructuring in $ARGUMENTS without breaking the vault.
- Plan. State exactly what will move, rename, split, or merge, and which files link to the affected notes (search for wikilinks to them). Show me the plan before changing anything.
- Baseline. Validate links first (
scripts/validate_links.py) so we know the starting point is clean. - Execute with
git mvwhere possible (preserve history). For a split, create the new notes and move the relevant content; for a merge, combine and redirect. Preserve frontmatter. - Rewire EVERY wikilink that pointed at a moved/renamed/merged note — including aliased
and table-escaped (
\|) links — and update any indexes and concept-graph canvas. - Re-validate links (must be zero broken) and commit. Never delete a note without my explicit approval — leave a redirect stub or archive it instead.
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.
- 4d ago First seen · 18 lines · 24 tokens per session scan A f9915db6404e
refactor is a command published in the GitHub repository Michael-OvO/obsidian-knowledge-agent (207 stars, last pushed 2mo ago), licensed MIT. It adds 24 tokens to every session and 273 once invoked, about $0.0001 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 2026-08-30.
Other commands, from other repositories
pseo-refresh
Use when: kullanıcı "verileri freshle", "veri tazele", "GSC SF DFS yenile", "master excel yenile", "tüm veriyi güncelle", "pillar cluster kontrol et", "aktif taskları revize et", "adstark taskları güncelle", "refresh audit" der ya da /pseo-refresh [project-slug] [daysback] çağırırsa. Also use when: aktif proje için…
pseo-content-decay
Use when: kullanıcı "içerik decay", "content decay", "tıklama düşen sayfalar", "ctr düştü", "90 gün öncesine göre azalma", "trafik kaybeden sayfalar", "decay analizi", "contentdecay sheet yenile", "ranking decay" der ya da /pseo-content-decay çağırırsa. Also use when: aktif projenin GSC verisi master.xlsx'te mevcut…
pseo-driftcheck
Use when: kullanıcı "drift", "drift kontrol", "tutarsızlık", "schema kontrol", "cross-sheet invariant", "tutarlılık raporu" der ya da /pseo-driftcheck çağırırsa. Also use when: master.xlsx'e büyük bir ingestion (sf-import, gsc-pull, dfs-pull, sf-crawl-orchestrator) sonrası logical sheet'ler arasındaki cross-sheet…
pseo-new-blog
Use when: kullanıcı "yeni blog yaz", "blog üret", "new content", "pillar/cluster yaz", "blog draft", "makale üret" der ya da /pseo-new-blog çağırırsa. Also use when: aktif projede master.xlsx[newcontentplan] sheet'inde bekleyen NCP satırı var; pillar content production tetiklenmek isteniyor; Foundational Principles…
pseo-monthly
Use when: kullanıcı "aylık rapor", "monthly report", "ay sonu özet", "geçen ay neler oldu", "ay raporu üret" der ya da /pseo-monthly çağırırsa. Also use when: bir ayın sonunda aktif proje için outputs/reports/{YYYY-MM}-monthly.md üretilecek; master.xlsx'te trafik/sıralama/içerik verileri ay boyunca toplanmış ve…
pseo-quickwin
Use when: kullanıcı "quick win", "hızlı kazanım", "11-20 sıradaki keyword", "low-hanging fruit", "kolay yükselebilir sayfalar" der ya da /pseo-quickwin çağırırsa. Also use when: aktif projenin GSC verisi master.xlsx içinde mevcut; sıralamada eşik bandında olan sorgular için gsc-pull → quick-wins skill chain'i…