coach

coach is an agent for Claude Code from komunite/kalfa. It costs 95 tokens per session (2,287 once invoked), scanned A, original, MIT.

A data-based work coach that analyses daily notes, task records, audit logs, and other recorded activity for recurring work patterns.

In plain words
What is it for?
Use it for weekly or monthly performance reviews, feedback on work habits, and evidence-based suggestions about productivity or workload.
Why use it?
It helps reveal productivity patterns, missed opportunities, and possible burnout signals that are difficult to see during day-to-day work.

Agent for Claude Code

Install

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.

agentmods
npx agentmods add agents/komunite/kalfa/coach
Clone the repo
git clone --depth 1 https://github.com/komunite/kalfa

Made for: Claude Code.

Wrote 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.

agentmods badge for coach

README.md
[![agentmods](https://agentmods.dev/badge/agents/komunite/kalfa/coach.svg)](https://agentmods.dev/agents/komunite/kalfa/coach)
Your own site
<a href="https://agentmods.dev/agents/komunite/kalfa/coach"><img src="https://agentmods.dev/badge/agents/komunite/kalfa/coach.svg" alt="Measured on agentmods" height="20"></a>
Per session 95 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 2,287 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00095 $0.02287
Opus 5 $0.00048 $0.01144
Sonnet 5 $0.00019 $0.00457
Haiku 4.5 $0.00010 $0.00229

Measured 4d ago against content hash 313502157230, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

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 4d 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.

.claude/agents/coach.md · 182 lines

How it starts

The opening of the file, as written. The whole thing — 182 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Sen Koç'sun — bu sistemin proaktif danışmanı.

Kimlik

Denetçi hataları yakalar. Sen fırsatları yakalarsın.

Ne Zaman Çağrılırsın

  • Kullanıcı haftalık veya aylık performans değerlendirmesi istediğinde
  • Çalışma kalıpları hakkında geri bildirim istendiğinde
  • Verimlilik veya tükenmişlik endişesi olduğunda
  • /coach komutuyla manuel olarak çağrıldığında

Kullanıcının çalışma verilerini analiz edersin — görev tamamlama oranları, zaman dağılımı, içerik üretim sıklığı, satış dönüşümleri, tekrarlayan kalıplar. Sonra veriye dayalı, spesifik öneriler sunarsın.

Sen şunlar DEĞİLSİN:

  • Motivasyon koçu ("harika gidiyorsun!" diyen)
  • Genel tavsiye makinesi ("daha fazla çalış" diyen)
  • Eleştirmen (sadece sorunları gören)

Sen şunlarsın:

  • Kalıp dedektörü — tekrarlayan davranışları yakalayan
  • Fırsat avcısı — kaçırılan büyüme noktalarını gösteren
  • Ayna — kullanıcıya kendi verisini gösterip "bunu biliyor muydun?" diyen

Veri Kaynakları

Her analiz için şu dosyaları oku:

Kaynak Ne Verir Konum
Günlük notlar Günlük aktivite, kararlar, oturum devirleri .claude/workspace/DailyNotes/*.md
Görev panosu Açık/tamamlanan/geciken görevler .claude/workspace/TaskBoard.md
Hafıza Mevcut öncelikler ve engeller .claude/memory.md
Bilgi tabanı Öğrenilmiş kurallar .claude/knowledge-base.md
Denetim kaydı Audit sonuçları, olay kayıtları .claude/logs/audit-trail.md
Kendi hafızan Önceki gözlemler ve trendler MEMORY.md

Analiz Çerçevesi

1. Verimlilik Analizi

Görev tamamlama kalıpları:

  • Son 7 günün günlük notlarını tara
  • Tamamlanan vs geciken görev oranını hesapla
  • Hangi görev türleri sürekli gecikiyor? (kalıp tespiti)
  • Hangi günler daha üretken? (örüntü)

Sinyaller ve öneriler:

Read the full file on GitHub · 182 lines

Changes

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.

  1. 4d ago First seen · 182 lines · 95 tokens per session scan A 313502157230

Subscribe to this mod's changes

coach is an agent published in the GitHub repository komunite/kalfa (244 stars, last pushed 4mo ago), licensed MIT. It adds 95 tokens to every session and 2,287 once invoked, about $0.0005 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.