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/prepare-1-1/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/prepare-1-1)<a href="https://agentmods.dev/skills/tpierrain/kenjaku/prepare-1-1"><img src="https://agentmods.dev/badge/skills/tpierrain/kenjaku/prepare-1-1/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/prepare-1-1"><img src="https://agentmods.dev/badge/skills/tpierrain/kenjaku/prepare-1-1.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 | $0.00120 | $0.02128 |
| Opus 5 | $0.00060 | $0.01064 |
| Sonnet 5 | $0.00024 | $0.00426 |
| Haiku 4.5 | $0.00012 | $0.00213 |
Grade A, and why
prepare-1-1 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.
How it starts
The opening of the file, as written. The whole thing — 159 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/prepare-1-1 — Prepare a 1-1 (meta version)
Produces a briefing scannable in 2 minutes before your next 1-1. This is a meta skill:
it lays out a structure that gives you ideas; you then refine it to your own focus areas,
your KPIs and the way you run your 1-1s (edit this file, or ask /improve to help you).
Parameter
A name or alias of a person in $ARGUMENTS (e.g. /prepare-1-1 jane). Used to find
vault/people/<firstname-lastname>.md (kebab-case, no accents) and the cache vault/backlog/<name>.md.
If no profile matches, suggest the closest profiles from vault/people/ and stop.
Absolute constraint
READ-ONLY. Never send a message, email or reaction, never post anywhere. Produce only a local markdown file in the vault.
Step 0 — Direction of the 1-1 (determines the output structure)
Two cases, depending on your relationship with the person (infer it from their role in vault/people/<name>.md;
when in doubt, ask):
- A · 1-1 with YOUR manager (you are the managee) → "what I want to raise" structure.
- B · 1-1 with someone YOU manage (a report, or a peer you coach) → "follow-up + operational + KPI" structure.
Step 1 — Collection (fan-out, READ-ONLY)
In parallel (sync-sources architecture, ~500-token summaries):
- Backlog cache:
vault/backlog/<name>.md— open / recurring actions (a point raised 2+ times without closure is a priority). - Last 1-1: the note in
vault/meetings/(or via your Calendar connector) — transcript read by an isolated sub-agent (never raw transcript in the main context). Also note the next 1-1 (date of the output file; otherwise today's date). - Delta since the last 1-1: messaging, email, shared meetings — depending on your connectors.
Claim discipline
The full rules live in one place — sync-sources § Claim discipline
— and this skill obeys them rather than restating its own. Two paraphrases are two disciplines; the
control belongs where the facts are produced, and this skill consumes that fan-out.
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 · 159 lines · 120 tokens per session scan A dbdc567b547d
prepare-1-1 is a skill published in the GitHub repository tpierrain/kenjaku (80 stars, last pushed today), licensed Apache-2.0. It adds 120 tokens to every session and 2,128 once invoked, about $0.0006 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
inbox
An inbox-management skill for scanning an LLM Wiki inbox, previewing pending files, choosing how to process them, and sending selected material through an import step.
live-tutorial
Create an annotated MP4 tutorial from a workflow demonstrated in the owner's actual application. Use when asked for a tutorial video, not merely to watch an action live.
telegram-userbot
A skill for connecting to and working through the owner's personal Telegram account, rather than a Telegram bot. It can read personal chats, search messages, and send messages as the account owner after setup and consent.
dbrain-processor
Personal assistant for processing daily voice/text entries from Telegram. Classifies content, saves thoughts to Obsidian with wiki-links, generates HTML reports. Integrates Your Business context (clients, projects, CRM). Triggers on /process command or daily 21:00 cron.
cron
A scheduling and reminder helper that manages recurring or one-time jobs through a command-line tool. The jobs are reread regularly, run in a separate cron session, and send results to the user in Telegram.
pages
List or open distilled Wenlan pages from Codex by delegating to the local wenlan pages CLI. Invoked as /pages [query].