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-adrgit 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-adr)<a href="https://agentmods.dev/commands/whchoi98/project-init/add-adr"><img src="https://agentmods.dev/badge/commands/whchoi98/project-init/add-adr.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 | $0.00010 | $0.01297 |
| Opus 5 | $0.00005 | $0.00648 |
| Sonnet 5 | $0.00002 | $0.00259 |
| Haiku 4.5 | $0.00001 | $0.00130 |
Grade A, and why
add-adr 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 3d 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 — 185 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Add ADR
Create a new Architecture Decision Record with automatic numbering and update project-level docs.
Step 1: Determine ADR Title
Target: $ARGUMENTS
- If no title provided, ask the user for the ADR title
- Convert to kebab-case for the filename
- Check if
docs/decisions/directory exists; create it if missing
Step 2: Auto-Number
Find the next available ADR number:
find docs/decisions -name 'ADR-*.md' -not -name '.template.md' 2>/dev/null | sort | tail -1
- If no existing ADRs, start at
001 - Otherwise, take the highest number and add 1
- Format:
ADR-NNN-<title>.md(e.g.ADR-001-use-postgresql.md)
Step 3: Gather Decision Details
Ask the user:
- Context: What is the background? Why is a decision needed?
- Options considered: What alternatives were evaluated? (at least 2)
- Decision: Which option was chosen and why?
- Consequences: What are the positive and negative impacts?
- Status: Proposed, Accepted, Deprecated, or Superseded? (default: Accepted)
If the user provides minimal input:
- Read
CLAUDE.mdanddocs/architecture.mdfor project context - Read recent git log for related changes
- Infer context from the ADR title
git log --oneline -10 2>/dev/null
Step 4: Read Templates and Style Guide
Read the shared writing style guide and ADR 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 ADR Template section as the base structure.
Step 5: Create Bilingual ADR
Create docs/decisions/ADR-NNN-<title>.md with bilingual (English/Korean) structure:
# ADR-NNN: <Title in Natural Language>
<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
## Status
<Proposed | Accepted | Deprecated | Superseded>
## Context
<background explaining why a decision is needed>
## Options Considered
### Option 1: <Name>
- **Pros**: <advantages>
- **Cons**: <disadvantages>
### Option 2: <Name>
- **Pros**: <advantages>
- **Cons**: <disadvantages>
## Decision
<the decision that was made and the reasoning>
## Consequences
### Positive
- <positive impact>
### Negative
- <negative impact or trade-off>
## References
- <links to relevant docs, issues, or discussions>
---
<a id="korean"></a>
# 한국어
## 상태
<제안됨 | 승인됨 | 더 이상 사용되지 않음 | 대체됨>
## 배경
<결정이 필요한 이유를 설명하는 배경>
## 검토한 옵션
### 옵션 1: <이름>
- **장점**: <이점>
- **단점**: <단점>
### 옵션 2: <이름>
- **장점**: <이점>
- **단점**: <단점>
## 결정
<내려진 결정과 그 근거>
## 영향
### 긍정적
- <긍정적 영향>
### 부정적
- <부정적 영향 또는 트레이드오프>
## 참고 자료
- <관련 문서, 이슈, 또는 논의 링크>
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.
- 3d ago First seen · 185 lines · 10 tokens per session scan A ae98af148cb5
add-adr is a command published in the GitHub repository whchoi98/project-init (2 stars, last pushed 1mo ago), licensed MIT. It adds 10 tokens to every session and 1,297 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
git
Git operations with intelligent commit messages and workflow optimization.
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.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.
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.