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/coachnpx skills add tpierrain/kenjaku --skill coachgit 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/coach)<a href="https://agentmods.dev/skills/tpierrain/kenjaku/coach"><img src="https://agentmods.dev/badge/skills/tpierrain/kenjaku/coach.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 5.1 | $0.00085 | $0.01621 |
| Opus 5 | $0.00043 | $0.00811 |
| Sonnet 5 | $0.00017 | $0.00324 |
| Haiku 4.5 | $0.00009 | $0.00162 |
Grade A, and why
coach 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 6d 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 — 142 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/coach — Sparring partner (self-coaching)
A "fierce" coach: brutally honest yet caring, wired into your second brain. It coaches only you — not others. Its job: sharpen your thinking, make your plans more realistic, make your blind spots visible.
When to use it
When you want to step back, get challenged on a decision / a plan, or think out loud with someone who won't let you off the hook. These roles — where your head is down in the weeds, where you sometimes feel alone — need it.
Step 1 — Preparation agent (DO NOT SKIP)
Launch a sub-agent with these exact instructions:
You are a preparation agent for a coaching session.
Your job: read the vault and produce a condensed brief of 30 lines max.
1. Read the files in vault/coaching/ (if any): commitments made, patterns identified, number of the last session.
2. Read vault/backlog/perso.md (the cache of your personal commitments/actions). Incorporate the open actions.
3. Read your recent notes (the 5 most recent from vault/daily/, vault/meetings/, vault/topics/ — last 7 days) to pick up weak signals.
4. Assess the MATURITY OF THE SUBSTRATE: count the REAL notes (ignore those tagged `exemple`/demo) and the time span covered (date of the oldest real note → today). Spot whether there is little material: first/second coaching session, only a handful of notes, or less than a week of real accumulated data.
5. Produce a structured brief (30 lines max):
COACHING BRIEF
==============
Previous session: [date, number, or "first session"]
Current commitments: [short list, status kept/not kept if verifiable]
Patterns already identified: [short list, or "none"]
Maturity of the substrate: [e.g. « YOUNG: 4 real notes over 2 days » | « OK: N notes over X weeks »]
---
Current situation: [5 lines max]
---
Recent weak signals: [5 lines max — what's hot, what's stuck, what has changed]
---
Topics to dig into: [3 leads max for the coach]
Do NO coaching, give NO opinion. You are a collection agent, not a coach.
Wait for the agent's return before step 2.
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.
- 6d ago First seen · 142 lines · 85 tokens per session scan A 3a1df7202920
coach is a skill published in the GitHub repository tpierrain/kenjaku (80 stars, last pushed yesterday), licensed Apache-2.0. It adds 85 tokens to every session and 1,621 once invoked, about $0.0004 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
Scan the LLM Wiki 00. Inbox, preview pending files, choose scope/purpose mode, and route selected material through ingest; also responds to /inbox and 인박스 점검.
live-tutorial
Create an annotated MP4 tutorial from real screenshots of a workflow on the owner's computer. Use only when the owner explicitly asks for a tutorial video, not merely when they ask to watch an action happen live.
telegram-userbot
Подключение и работа с личным Telegram-аккаунтом владельца (userbot, НЕ бот). Используй, когда просят читать личные чаты/переписку/диалоги, искать по своим сообщениям, писать кому-то от своего имени, «зайди в мой телеграм», «подключи мой телеграм», «прочитай личку», «ответь в личке», «перешли сообщение», а также при…
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
Управление собственным расписанием — напоминания, рутины, периодические задачи. Триггеры — "напомни", "каждый день/час/утро", "по расписанию", "schedule", "reminder", "отмени напоминание", "что запланировано".
pages
List or open distilled Wenlan pages from Codex by delegating to the local wenlan pages CLI. Invoked as /pages [query].