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 skills add tpierrain/kenjaku --skill open-notegit 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/open-note)<a href="https://agentmods.dev/skills/tpierrain/kenjaku/open-note"><img src="https://agentmods.dev/badge/skills/tpierrain/kenjaku/open-note/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/open-note"><img src="https://agentmods.dev/badge/skills/tpierrain/kenjaku/open-note.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00086 | $0.01292 |
| Opus 5.5 | $0.00034 | $0.00517 |
| Sonnet 5.5 | $0.00017 | $0.00258 |
| Haiku 4.5 | $0.00009 | $0.00129 |
Grade A, and why
open-note 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 1mo 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 — 87 lines — stays where its author put it; the contents beside it link to each section on GitHub.
open-note — "open X for me"
Default behavior of the natural command "open for me". Goal: the user always has something to read in front of them — either the existing note, or a fresh synthesis created on the fly and persisted into the vault.
Principle
One promise only: "open X for me" never falls into the void.
- If a vault doc is about X → open it as-is (do not modify it).
- If nothing covers X → synthesize from the vault, write a note that follows the conventions, and open it.
The judgment (which doc, whether to create one, where to file it) stays in the skill; the opening itself is deterministic and is NOT this skill's rule to invent — it belongs to the constitution's §"Opening / viewing / editing a note" (ADR 0027), which this skill obeys as-is.
Procedure
1. Understand the target
Extract the topic from the request. Three cases:
- Known file (exact path, precise date, obvious note name:
daily/2026-06-12, "the prep for ", "the backlog for ") → go straight to step 3 (direct open, no RAG). - Semantic topic ("what we know about front-end governance", "the topic") → step 2 (search).
- Ambiguous → treat as semantic, and resolve the ambiguity by surfacing the candidates.
2. Search the vault
mcp__vault-rag__search_vaultfirst (semantic, ~300ms, free).grep/findas a complement for exact matches (name, identifier, date).- Judge the relevance of the best match: does this doc really cover X, or just mention it in passing?
3. If a relevant doc exists → open it as-is
Open it exactly the way the constitution prescribes: a note of the vault goes to Obsidian
through obsidian://open?path=<url-encoded-abs-path> handed to the OS opener (open / start "" /
xdg-open), anything else goes to the OS opener on the file itself. Do not restate or re-derive that
rule here — read it there, so the two can never disagree.
- Do not modify it (respect append-only for dailies, living notes for people/topics — never overwrite a living doc on a mere "open X for me").
- State which file is being opened and its freshness (
updateddate). - If several docs are equally relevant: open the best one, cite the other candidates in one line (do not block on a choice).
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.
- 1mo ago First seen · 87 lines · 86 tokens per session scan A 588172052752
open-note is a skill published in the GitHub repository tpierrain/kenjaku (92 stars, last pushed 25d ago), licensed Apache-2.0. It adds 86 tokens to every session and 1,292 once invoked, about $0.0003 per session on Opus 5.5. 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
setup-vault-types
Use when configuring which document types a vault tracks: after installing ai-brain-starter, when a new kind of note appears (journals, books, meetings, clients, podcasts, travel, WhatsApp/Slack/iMessage exports), when extraction skips files because no extractor matches their type, or to add, list, or remove a custom…
ingest-health
Use when the user says /ingest-health, asks to import, sync, ingest, or load Apple Health / Apple Watch / HealthKit data, has a fresh export.zip from the iPhone Health app, a Simple Health Export CSV folder, or a Health Auto Export TCP live feed, or when health-mcp queries return empty because no data was ever…
grok-sync
A tool for importing conversations from an official Grok data export into an Obsidian vault. Grok is xAI's chat service, and Obsidian is a note-taking application; the import creates notes and a local database.
granola-sync
Pull fresh meetings from Granola (summaries, transcripts, participants) into an Obsidian vault over the official API. Incremental and idempotent by note id and updatedat, so re-runs make no duplicates. Triggers: "/granola-sync", "pull granola", "refresh meetings".
feishu
A guide for operating Feishu, a workplace collaboration platform used for messages, documents, tasks, calendars, and groups.
template-execute
Execute a Templater template, optionally writing the rendered output to a new file. Arguments are exposed to the template via tp.mcpTools.prompt("key") (directly under tp, NOT under tp.user — easy footgun). EN triggers: "render the X template", "run the daily template", "execute Templates/X.md with arg1=v1", "use…