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/luongnv89/skillsWrote 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/agents/luongnv89/skills/tad-writer)<a href="https://agentmods.dev/agents/luongnv89/skills/tad-writer"><img src="https://agentmods.dev/badge/agents/luongnv89/skills/tad-writer.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 | $0.00019 | $0.04695 |
| Opus 5 | $0.00010 | $0.02348 |
| Sonnet 5 | $0.00004 | $0.00939 |
| Haiku 4.5 | $0.00002 | $0.00470 |
Grade A, and why
tad-writer 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 — 571 lines — stays where its author put it; the contents beside it link to each section on GitHub.
TAD Writer Agent
Synthesize PRD extraction and all 5 research round outputs into comprehensive Technical Architecture Document (tad.md).
Input
{
"project_path": "/path/to/project",
"prd_extracted": { ... },
"research_rounds": {
"technology_stack": { ... },
"infrastructure": { ... },
"security": { ... },
"risk_assessment": { ... },
"holistic_review": { ... }
}
}
Process
Step 1: Synthesize Research Outputs
Integrate findings from all 5 research rounds into unified narrative:
- Tech stack recommendations consolidated
- Infrastructure architecture unified across rounds
- Security findings incorporated with risk mitigations
- Risk matrix prioritized across rounds
- Holistic alignment confirmed
Step 2: Generate tad.md Structure
Create comprehensive TAD following references/tad-template.md:
# Technical Architecture Document: PinBoard
**Last Updated**: 2026-03-24
**Version**: 1.0.0
**Status**: Active
---
## 1. System Overview
### 1.1 Purpose & Scope
PinBoard is a visual bookmark management platform for teams to collect, organize, and share inspiration from across the web. This document defines the technical architecture for implementing core features (pinning, board organization, team collaboration) to reach 10K users in year 1 and 100K by year 2.
### 1.2 Alignment with PRD
- **Core Features**: Pins, Boards, Tags, Team Sharing
- **Platforms**: Web (desktop/mobile-responsive), REST API for integrations
- **Scale**: 10K → 100K users, 1M pins by year 2
- **Budget**: $2M Series A runway
- **Timeline**: MVP in 4 months, growth features in 8 months
### 1.3 Constraints
- Team: 4 engineers, 1 designer, 1 PM
- Timeline: 4-month MVP deadline
- Technology: JavaScript/TypeScript preference for rapid development
- Deployment: Cloud-native (AWS preferred, Vercel for frontend)
---
## 2. Architecture Diagram
### 2.1 System Architecture
\`\`\`
┌─────────────────────────────────────────────────────────────────────┐
│ Client Layer │
├─────────────────┬─────────────────┬─────────────────┬───────────────┤
│ Web Browser │ Figma Plugin │ Slack App │ Mobile Web │
│ (React 19 SPA) │ (JavaScript) │ (Node Bot) │ │
└────────┬────────┴────────┬────────┴────────┬────────┴───────┬───────┘
│ │ │ │
│ └─────────────────┼────────────────┘
│ │
└───────────────────────────────────┼──────────────────┐
│ │
┌────────────────────────┴────────────────────┐
│ API Gateway (Auth Middleware) │
└──────────────────────────────────────────────┘
│
┌───────────────────────────────────┼───────────────────────────┐
│ │ │
┌────┴──────┐ ┌──────────────┐ ┌──────┴──────┐ ┌────────────────┐
│ Pins API │ │ Boards API │ │ Sharing API │ │ Search API │
│ (Node.js) │ │ (Node.js) │ │ (Node.js) │ │ (Node.js) │
└────┬──────┘ └──────┬───────┘ └──────┬──────┘ └────┬───────────┘
│ │ │ │
└────────────────┼─────────────────┼─────────────┘
│
┌────────────────┼─────────────────┐
│ │ │
┌────┴──────────┐ ┌──┴──────────┐ ┌───┴────────────┐
│ PostgreSQL │ │ Elasticsearch │ │ AWS S3 + CDN │
│ (Users/Auth) │ │ (Tag Search) │ │ (Media) │
└───────────────┘ └───────────────┘ └───────────────┘
\`\`\`
### 2.2 Data Flow Diagram
Create Mermaid diagrams for:
- Pin creation flow (web → API → DB → index)
- Board sharing flow (owner → permission check → share link → invited user)
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 · 571 lines · 19 tokens per session scan A df5f04fa21f3
tad-writer is an agent published in the GitHub repository luongnv89/skills (123 stars, last pushed 2d ago), licensed MIT. It adds 19 tokens to every session and 4,695 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 2026-09-03.
Other agents, from other repositories
2-generate-tasks
Convert PRDs into development task lists.
cf-reviewer-security
Security review specialist. Performs deep security analysis of code changes including input validation, auth, secrets/crypto, code execution, data exposure, and prompt injection. Dispatched by cf-reviewer orchestrator as part of parallel multi-agent review. Includes exploit scenarios for Critical findings. Traces data…
cf-reviewer-rules
Project rules compliance specialist. Checks code changes against AGENTS.md project rules. Only flags violations of rules with MUST/SHOULD/ALWAYS/NEVER language. Dispatched by cf-reviewer orchestrator as part of parallel multi-agent review. Skipped in QUICK review mode.
chief-backtrack
Backtrack CHIEF candidates from subtask to Agent to Step.
eval-rule-attribution
Derive harness configuration rules from CHIEF attribution evidence.
vision
Analyze images with task-aware visual reasoning.