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/playbook)<a href="https://agentmods.dev/commands/fatihkan/badi/playbook"><img src="https://agentmods.dev/badge/commands/fatihkan/badi/playbook.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 | $0.00000 | $0.00734 |
| Opus 5 | $0.00000 | $0.00367 |
| Sonnet 5 | $0.00000 | $0.00147 |
| Haiku 4.5 | $0.00000 | $0.00073 |
Grade A, and why
playbook 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 today.
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 — 89 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Workflow-to-command command. Converts repetitive manual workflows into reusable Badi commands.
Required Tools
- Read (existing commands) -- Write (new command) -- Glob (existing command list) -- Grep (pattern/reference)
Procedure (7 Steps)
1. Name It
- Use the argument if given -- otherwise derive it from the description
- Rules: kebab-case (
bug-triage,sprint-plan) -- short and memorable (1-3 words) -- action-reflecting (verb/verb-object) -- no collision with existing names
Collision check: scan .claude/commands/ -- same/similar exists? -- suggest alternatives.
2. Capture the Workflow
For every step: what is done (action) -- where (file/directory/system) -- why (purpose/context) -- inputs -- outputs -- success criterion -- failure case
Chronological order + numbering.
3. Detect the Patterns
- Parallelism: independent steps -- parallel subtasks
- User input: human decisions -- approval waits -- data-collection points
- Conditional branching: "If X then Y, else Z" -- optional steps -- error routing
- Tool needs: Claude tools (Read, Write, Bash, Grep, ...) -- external tools (git, npm, docker, ...)
- Existing skill matches: do parts overlap with an existing command -- can it be invoked as a substep
4. Define the Arguments
Identify the inputs that change per run:
- Which values vary -- defaults -- required/optional split -- the
argument-hintdescription
Argument: [project-name] Default: current directory Description: "Name of the project the playbook targets"
5. The Command File
Create .claude/commands/[name].md in the standard format:
[One-line description]
# Required Tools
- [Tool 1] ([for what])
- [Tool 2] ([for what])
# Procedure ([step count] Steps)
### Step 1: [Name]
[instruction]
### Step 2: [Name]
[instruction]
# Output Format
[template]
Rules: write in English, clear and direct -- every step understandable on its own -- tool usage explicit -- failure cases covered -- a crisp output format.
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.
- today First seen · 89 lines · 0 tokens per session scan A 4b40470ab388
playbook is a command published in the GitHub repository fatihkan/badi (7 stars, last pushed yesterday), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 734 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 2026-09-06.
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.
audit-agents-skills
Audit quality of agents, skills, and commands in a Claude Code project.
check-cache-bugs
Audit Claude Code setup for cache bugs (CC#40524) — sentinel, --resume/--continue, attribution header + ArkNill B3/B4/B5.