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 skills/tpierrain/kenjaku/syncnpx skills add tpierrain/kenjaku --skill syncgit clone --depth 1 https://github.com/tpierrain/kenjakuWhat 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 | $0.00056 | $0.01055 |
| Opus 5 | $0.00028 | $0.00528 |
| Sonnet 5 | $0.00011 | $0.00211 |
| Haiku 4.5 | $0.00006 | $0.00105 |
Grade A, and why
sync scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 97 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/sync — Cross-machine repo synchronization
User command. Useful when working on several machines (personal / work laptop) and you want to pull in changes pushed from the other without leaving the session.
When to use it
- When you've worked on another machine and want to pull the changes in here.
- Mid-session, without having to quit and relaunch Claude Code.
- Complements the
SessionStarthook (which pulls at startup) for mid-session cases.
ℹ️ Requires a configured git remote (
origin). For purely local use, this skill is useless.
Procedure
Step 1 — Local state
git status --porcelain
Clean → go to step 3. Dirty → step 2.
Step 2 — Commit local changes
git add .
git commit -m "auto: vault/claude sync"
Creates a safe restore point before the rebase.
Step 3 — Fetch and rebase
node scripts/set-active-universe.mjs current # remember it: step 5 compares
git fetch origin
git rebase origin/$(git branch --show-current)
Success → summary + step 5. Conflict → step 4.
Read the active universe before rebasing. The pull can carry a context switch made on the owner's other machine (it is committed state — ADR 0034), and step 5 can only say so by comparing. At session start the same thing is handled deterministically by a hook; mid-session, this skill is the only channel.
Step 4 — Conflict handling
- List the conflicting files:
git diff --name-only --diff-filter=U - Show the diff of each with context.
- Ask the user:
Conflict on N file(s). Options:
- merge: I resolve and we continue the rebase
- abort:
git rebase --abort— back to the previous state (the local commit is safe)
- If merge: resolve intelligently (vault content = often append-only → keep both versions),
git addthe resolved files,git rebase --continue. - If abort:
git rebase --abort, report that the local commit is intact, stop.
The one file with a standing rule — .vault-rag/active-universe
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.
- 2d ago First seen · 97 lines · 56 tokens per session scan A acd33ffaaecc
sync is a skill published in the GitHub repository tpierrain/kenjaku (80 stars, last pushed 8d ago), licensed Apache-2.0. It adds 56 tokens to every session and 1,055 once invoked, about $0.0003 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 skills, from other repositories
lint
Run the LLM Wiki health check: orphans, broken links, contradictions, stale pages, index sync, MOC coverage, frontmatter fields, Exploration Gate, v5 verification fields, Bias Check, cross-vault links, and Core Context freshness; also responds to /lint and 위키 점검.
refresh-context
Re-snapshot Core Context.md from the 9 mothership system files and key essays when the mothership changes or the snapshot is older than 30 days; also responds to /refresh-context and 코어 컨텍스트 갱신.
status
Show the LLM Wiki state at a glance: counts, recent activity, index drift, inbox backlog, collectionPurpose/mainVault/explored/verificationStatus coverage, and Core Context snapshot age; also responds to /status and 상태 점검.
capture-tabs
Capture Chrome tab groups, browser research bundles, or ChatGPT/Gemini/Grok/Claude/Perplexity sessions into LLM Wiki Inbox markdown; also responds to 탭 캡처, 리서치 캡처, Deep Research 캡처, and /capture-tabs.
ingest
Ingest a URL, file, raw text, or Inbox item into the LLM Wiki with the purpose gate, mothership link search, raw-source preservation, Wiki compilation, index/log update, and review; also responds to /ingest and 인제스트.
reindex
Manually re-run qmd indexing and embeddings for wiki, rawsources, and queries after Obsidian edits, bulk moves, or embedding-model changes; also responds to /reindex and 재색인.