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 commands/whchoi98/project-init/add-runbookgit clone --depth 1 https://github.com/whchoi98/project-initWrote 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/whchoi98/project-init/add-runbook)<a href="https://agentmods.dev/commands/whchoi98/project-init/add-runbook"><img src="https://agentmods.dev/badge/commands/whchoi98/project-init/add-runbook.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 | $0.00013 | $0.01332 |
| Opus 5 | $0.00006 | $0.00666 |
| Sonnet 5 | $0.00003 | $0.00266 |
| Haiku 4.5 | $0.00001 | $0.00133 |
Grade A, and why
add-runbook 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.
How it starts
The opening of the file, as written. The whole thing — 180 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Add Runbook
Create a new operational runbook with structured steps and update project-level docs.
Step 1: Determine Runbook Name
Target: $ARGUMENTS
- If no name provided, ask the user for the runbook name
- Convert to kebab-case for the filename (e.g. "Deploy Production" ->
deploy-production.md) - Check if
docs/runbooks/directory exists; create it if missing - Check if the runbook already exists; if so, offer to update it instead
ls docs/runbooks/ 2>/dev/null
Step 2: Gather Runbook Details
Ask the user:
- Purpose: What operational task does this runbook cover? (one sentence)
- When to use: Under what circumstances should someone follow this runbook?
- Prerequisites: What tools, permissions, or access are needed?
- Procedure: What are the high-level steps? (Claude will expand these)
- Rollback: Is there a recovery procedure if something goes wrong?
If the user provides minimal input, infer from the runbook name and project context:
- Read
CLAUDE.mdfor tech stack and deployment info - Read
docs/architecture.mdfor system components - Infer appropriate steps based on the runbook topic
Step 3: Read Templates and Style Guide
Read the shared writing style guide and runbook template:
Read file: skills/project-scaffolder/references/writing-style-guide.md
Read file: skills/project-scaffolder/references/docs-templates.md
Follow all bilingual structure, formatting, and style rules from the writing style guide. Use the Runbook Template section as the base structure.
Step 4: Create Bilingual Runbook
Create docs/runbooks/<runbook-name>.md with bilingual (English/Korean) structure:
# Runbook: <Title>
<a href="#english"><img src="https://img.shields.io/badge/lang-English-blue.svg" alt="English"></a>
<a href="#korean"><img src="https://img.shields.io/badge/lang-한국어-red.svg" alt="Korean"></a>
---
<a id="english"></a>
# English
## Overview
<purpose from user input or inferred from context>
## When to Use
<circumstances that trigger this runbook>
## Prerequisites
- <required permissions>
- <required tools>
- <required access>
## Procedure
### 1. <First Phase>
<detailed steps with copy-paste ready commands>
### 2. <Second Phase>
<detailed steps with copy-paste ready commands>
### 3. <Third Phase>
<detailed steps with copy-paste ready commands>
## Verification
- [ ] <check 1>
- [ ] <check 2>
## Rollback
1. <rollback step 1>
2. <rollback step 2>
## Notes
- Last verified: <today's date>
- Author: <user or inferred>
---
<a id="korean"></a>
# 한국어
## 개요
<사용자 입력 또는 컨텍스트에서 유추한 목적>
## 사용 시점
<이 런북을 따라야 하는 상황>
## 사전 요구 사항
- <필요한 권한>
- <필요한 도구>
- <필요한 접근 권한>
## 절차
### 1. <첫 번째 단계>
<복사-붙여넣기 가능한 명령어와 상세 단계>
### 2. <두 번째 단계>
<복사-붙여넣기 가능한 명령어와 상세 단계>
### 3. <세 번째 단계>
<복사-붙여넣기 가능한 명령어와 상세 단계>
## 검증
- [ ] <확인 1>
- [ ] <확인 2>
## 롤백
1. <롤백 단계 1>
2. <롤백 단계 2>
## 참고
- 최종 검증일: <오늘 날짜>
- 작성자: <사용자 또는 유추>
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.
- 4d ago First seen · 180 lines · 13 tokens per session scan A 830541f38dd6
add-runbook is a command published in the GitHub repository whchoi98/project-init (2 stars, last pushed 1mo ago), licensed MIT. It adds 13 tokens to every session and 1,332 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.
Other commands, from other repositories
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.
converge
Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.
implement
Execute the implementation plan by processing and executing all tasks defined in tasks.md.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.