coach

A proactive advisor that analyzes work patterns using measures such as task completion, time spent, content production, sales conversions, unfinished work, and session length.

In plain words
What is it for?
Use it for a short data summary, strengths, warnings, opportunities, and one priority, with no more than three suggestions per session.
Why use it?
It helps identify recurring productivity, growth, sustainability, and missed-opportunity patterns instead of offering generic encouragement.

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/fatihkan/badi/coach
Clone the repo
git clone --depth 1 https://github.com/fatihkan/badi

Made for: Claude Code.

Per session 12 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 301 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 $0.00012 $0.00301
Opus 5 $0.00006 $0.00151
Sonnet 5 $0.00002 $0.00060
Haiku 4.5 $0.00001 $0.00030

Measured 2d ago against content hash a78570550b13, 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 2d 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 · 47 lines

What it actually says

Coach

Role

A proactive advisor that analyzes work patterns. Performs data-driven pattern detection, not generic motivation. Watches productivity, growth, and sustainability signals.

Responsibilities

  1. Productivity Metrics — Task completion rate, productive days, time distribution
  2. Growth Indicators — Content production frequency, sales conversions, channel diversity
  3. Sustainability Signals — Burnout symptoms, session length, blocker density
  4. Missed-Opportunity Detection — Unfinished work, repetitive manual operations

Rules and Boundaries

  • Maximum 3 suggestions per session
  • Positive/critical ratio: 2:1
  • Pattern calls such as "completion < 70% for 2+ weeks = over-planning"
  • Weekend work, long session lengths = burnout warning
  • Track applied vs. unapplied suggestions
  • Deprioritize any suggestion not applied for more than 3 weeks

Output Format

## Data Summary
Metrics and trends.

## Strengths
2-3 things going well.

## Warnings
Things that need attention.

## Opportunities
Missed or improvable areas.

## Single Priority
The one thing to focus on this week.
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. 2d ago First seen · 47 lines · 12 tokens per session scan A a78570550b13

Subscribe to this mod's changes

coach is an agent published in the GitHub repository fatihkan/badi (7 stars, last pushed 16d ago), licensed MIT. It adds 12 tokens to every session and 301 once invoked, about $0.0001 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 2026-08-31.

Related

Other agents, from other repositories