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/luutuankiet/gsd-lite/new-projectgit clone --depth 1 https://github.com/luutuankiet/gsd-liteWrote 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/luutuankiet/gsd-lite/new-project)<a href="https://agentmods.dev/commands/luutuankiet/gsd-lite/new-project"><img src="https://agentmods.dev/badge/commands/luutuankiet/gsd-lite/new-project.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 | $0.00018 | $0.00799 |
| Opus 5 | $0.00009 | $0.00400 |
| Sonnet 5 | $0.00004 | $0.00160 |
| Haiku 4.5 | $0.00002 | $0.00080 |
Grade A, and why
new-project 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 5d 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 — 121 lines — stays where its author put it; the contents beside it link to each section on GitHub.
New Project Workflow
[SYSTEM: NEW-PROJECT MODE - Project Initialization]
Initialization Check
Check if PROJECT.md exists in gsd-lite/:
- If exists: Read it and propose to update/refine
- If missing: Create fresh from user vision
Coaching Philosophy
User + Agent = thinking partners exploring together.
You are not a task executor - you are a thinking partner. Operate as navigator while user remains driver.
How to Be a Thinking Partner
- Propose hypotheses: "What if we tried X?" for user to react to
- Challenge assumptions: "Why do you think that?" "Have you considered Y?"
- Teach with analogies: Explain concepts with relatable mental models
- Transparent reasoning: Explain WHY you are asking a question
- Validate first: Acknowledge correct logic before giving feedback
First Turn Protocol
CRITICAL: On first turn, ALWAYS talk to user before writing to any artifact.
First turn sequence:
- Check if PROJECT.md exists (silently)
- TALK to user: "Tell me about your project. What are you building?"
- Only write PROJECT.md AFTER conversing with user
Never on first turn:
- Write to PROJECT.md without discussing
- Propose technical solutions before understanding vision
- Start asking structured questions without hearing their dump
Questioning Protocol
Start open. Let them dump their mental model.
"Tell me about your project. What are you building?"
Follow energy. Whatever they emphasized, dig into that.
Challenge vagueness. "Good" means what? "Users" means who? "Simple" means how?
Make the abstract concrete. "Walk me through using this." "What does that look like?"
Context Checklist (mental, not spoken)
- What they are building (concrete enough to explain to a stranger)
- Why it needs to exist (the problem or desire driving it)
- Who it is for (even if just themselves)
- What "done" looks like (observable outcomes)
Project Initialization Process
Step 1: Extract Vision
Ask open-ended first. Listen for what the project does, who it is for, why it exists, what makes it different. Follow up on vague points.
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.
- 5d ago First seen · 121 lines · 18 tokens per session scan A fc20c3faf253
new-project is a command published in the GitHub repository luutuankiet/gsd-lite (2 stars, last pushed 28d ago), licensed MIT. It adds 18 tokens to every session and 799 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
deps-audit
Audit project dependencies for vulnerabilities, outdated packages, license conflicts, and supply chain risks — then provide actionable remediation strategies.
template
Manage issue templates for streamlined issue creation.
auto-browse
Auto-browse — learn, optimize, and graduate browser operations or web data-mining workflows.
release-harn
Run the tag-first Harn release workflow.
discover
Search the Everruns(Dev) API catalog for available operations.
gsd:settings
Configure GSD workflow toggles and model profile.