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.
git clone --depth 1 https://github.com/fatihkan/badiWrote 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/commands/fatihkan/badi/coach)<a href="https://agentmods.dev/commands/fatihkan/badi/coach"><img src="https://agentmods.dev/badge/commands/fatihkan/badi/coach/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/commands/fatihkan/badi/coach"><img src="https://agentmods.dev/badge/commands/fatihkan/badi/coach.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00000 | $0.00851 |
| Opus 5.5 | $0.00000 | $0.00340 |
| Sonnet 5.5 | $0.00000 | $0.00170 |
| Haiku 4.5 | $0.00000 | $0.00085 |
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 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 — 143 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Coaching analysis command. Performs data-driven work-pattern analysis and offers personal improvement suggestions.
Required Tools
- Read (memory, tasks, notes, previous coaching reports)
- Write (coaching report)
- Grep (pattern scan)
- Glob (finding data sources)
- Bash (git statistics)
Optional Time Window
Ask the user: "Which period shall we analyze?"
- Weekly: Last 7 days
- Monthly: Last 30 days
- All Data: Every existing record
Procedure (4 Sections)
Section 0: Data Collection
Gather the data sources for analysis:
- Read
memory.md - Review the task board (completed, in progress, deferred)
- Scan the daily notes (for the chosen period)
- Collect git statistics (commit frequency, change volume)
- Read previous coaching observations (if any)
- Review the handoff notes
- Check the retrospective reports
Section 1: Productivity Analysis
Metrics:
- Task completion rate (completed / planned)
- Average daily commit count
- Productive day count and patterns
- Average time spent per task
- Time distribution analysis (development / meetings / management / research)
- Most productive hour and day analysis
- Bottlenecks and waiting times
Assessment:
- Top-performance areas
- Areas needing improvement
- Productivity trend (rising/falling/flat)
Section 2: Growth Analysis
Metrics:
- Newly learned technologies and tools
- Content production frequency (blog, documentation, etc.)
- Tasks with rising complexity (difficulty progression)
- Change in problem-solving speed
- Channel diversity (development, design, business development, etc.)
- Technical depth indicator
Assessment:
- Skill development areas
- Did they step out of the comfort zone?
- Were new challenges sought?
Section 3: Sustainability Analysis
Signals:
- Burnout symptoms:
- Weekend work frequency
- Excessively long sessions (4+ hours uninterrupted)
- Late-night development activity
- Rising error rate
- Blocker density (how often blocked?)
- Recurring problems (how many times did the same thing break?)
- Break patterns (enough breaks taken?)
- Work/life balance indicators
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 · 143 lines · 0 tokens per session scan A 9c5f6e20a9ee
coach is a command published in the GitHub repository fatihkan/badi (7 stars, last pushed 14d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 851 tokens. 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.
Other commands, from other repositories
catchup
Restore context after /clear by summarizing recent work and project state.
sessions
Browse Claude Code sessions history.
dashboard
Launch ccboard TUI dashboard.
ccboard-install
Install or update ccboard.
hatch3r-handoff
Prepare, resume, list, complete, and prune cross-session handoff documents.
check-cache-bugs
Audit Claude Code setup for cache bugs (CC#40524) — sentinel, --resume/--continue, attribution header + ArkNill B3/B4/B5.