Borrowing it
Nothing to install: this file belongs to tpierrain/kenjaku. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/tpierrain/kenjaku/main/.claude/skills/local-mirror/SKILL.mdgit clone --depth 1 https://github.com/tpierrain/kenjakuWrote 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/tpierrain/kenjaku/local-mirror)<a href="https://agentmods.dev/skills/tpierrain/kenjaku/local-mirror"><img src="https://agentmods.dev/badge/skills/tpierrain/kenjaku/local-mirror/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/tpierrain/kenjaku/local-mirror"><img src="https://agentmods.dev/badge/skills/tpierrain/kenjaku/local-mirror.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 2 findings, up to high
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- high Privilege Escalation · line 137 Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.Fix: Remove references to credential paths. Use environment variables or secrets managers. For docs, use placeholder paths (e.g., /path/to/config). Never load .env or token files in production code paths.
- high Privilege Escalation · line 141 Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.Fix: Remove references to credential paths. Use environment variables or secrets managers. For docs, use placeholder paths (e.g., /path/to/config). Never load .env or token files in production code paths.
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 | $0.00349 | $0.06641 |
| Opus 5 | $0.00175 | $0.03320 |
| Sonnet 5 | $0.00070 | $0.01328 |
| Haiku 4.5 | $0.00035 | $0.00664 |
Grade A, and why
local-mirror 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 9d 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.
Copies of this mod
1 near-identical copy found in the catalogue:
- costly-signaling — 86% identical, 355 lines differ
How it starts
The opening of the file, as written. The whole thing — 337 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/local-mirror — Mirror a live internal source into your vault (opt-in, safe)
Brain-side skill. A local mirror (a copie miroir / réplica locale) is a zone of an internal tool (Notion for the MVP) that you declare once; the brain then mirrors its pages into
vault/mirrors/<name>/as plain Markdown (orvault/<universe>/mirrors/<name>/when the mirror belongs to a universe, see below). From there the existing RAG indexes and cites them like any other note — the central RAG you don't have yet, but local and right now, plugged onto your live sources.⚠️ This skill holds no logic. All the real, testable work lives in the
local-mirrorMCP server (its own package, Outside-in TDD). This skill only recognizes intent, gathers the declaration, guides the token into.env, calls the right MCP tool, and reports.
First — a local mirror, or the native Notion connector? (don't mix them up)
A brain can touch Notion two completely different ways. Put yourself in the user's shoes and route to the right one before doing anything:
- They just want to read, write, create, edit, fetch or search something in Notion — live, ad hoc?
→ that's the native Notion connector (the brain's general, real-time Notion access:
notion-fetch,notion-search,notion-create-pages, …). NOT this skill. Let that connector handle it; do not onboard a local mirror for it. - They want a sub-zone of Notion replicated locally so the local RAG can search & cite it — offline, framed, refreshed on demand, without re-querying Notion every time? → that's a local mirror. This skill. (Mirror = one-way read-only copy into the vault; this skill never writes back to Notion.)
🧭 One-line litmus: live read/write in the ocean → native Notion connector; a local mirror of a slice of the ocean for the RAG → local mirror (this skill).
Disambiguate first — the balanced 2-option question (don't guess)
The exact fault line is a phrasing like "je veux que mon cerveau puisse chercher dans ce Notion". It can mean either tool. When the intent is genuinely ambiguous, don't assume — ask one honest, balanced question (not a sales funnel that pushes the mirror):
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.
- 9d ago First seen · 337 lines · 349 tokens per session scan A ed81e90caeed
local-mirror is a skill published in the GitHub repository tpierrain/kenjaku (80 stars, last pushed today), licensed Apache-2.0. It adds 349 tokens to every session and 6,641 once invoked, about $0.0017 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
migrate
Scan the project and migrate existing documentation into OKF format. Use when the user wants to populate the knowledge base from existing docs, README, schemas, API specs, runbooks, or any structured project knowledge. Trigger on "migrate to okf", "populate the knowledge base", "scan my docs", "convert docs to okf"…
init
Initialize OKF knowledge base files in the current project. Use when the user wants to start documenting their project for claude-mega-brain, or when the user says "init mega brain", "setup the knowledge base", "cria o okf", "inicializa o mega brain", "quero usar o mega brain", "criar a estrutura do knowledge base"…
wiki-export
Export a vault's wiki either as a single portable file (llms.txt or llms-full.txt per the llmstxt.org standard) or as an OKF knowledge bundle (Google's Open Knowledge Format v0.1 — a shareable directory of markdown files any AI agent can consume). Use when the user says "export my wiki", "make an llms.txt", "share my…
harvest-knowledge
Re-scan the repo's human-authored documentation (docs trees, ADRs, decision logs, design specs, roadmaps, kanban) and fold newly-durable facts into the shared memory/ layer — additively, on demand. Use when docs have grown or changed since enable, or to backfill a repo enabled before the curious harvest existed.…
wiki
Build and maintain a persistent, interlinked wiki from source documents. Knowledge is compiled once and kept current. Based on Andrej Karpathy's LLM Wiki pattern. Commands: /wiki (dashboard), /wiki-ingest, /wiki-query, /wiki-lint, /wiki-save, /wiki-graph, /wiki-review.
refresh-context
A context snapshot updater for Core Context.md, a summary file built from nine main system files and selected essays. It refreshes that summary when the underlying material changes or the snapshot is more than 30 days old.