Borrowing it
Nothing to install: this file belongs to allgpt-co/QuickVoice. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/allgpt-co/QuickVoice/main/.claude/skills/gsd/commands/new-project/SKILL.mdgit clone --depth 1 https://github.com/allgpt-co/QuickVoiceWrote 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/skills/allgpt-co/quickvoice/new-project)<a href="https://agentmods.dev/skills/allgpt-co/quickvoice/new-project"><img src="https://agentmods.dev/badge/skills/allgpt-co/quickvoice/new-project/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/allgpt-co/quickvoice/new-project"><img src="https://agentmods.dev/badge/skills/allgpt-co/quickvoice/new-project.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 5 findings, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Prompt Injection · line 105 Large whitespace padding was detected (a block of blank lines or a long run of spaces). This can push injected instructions below or to the right of the visible area so a human reviewer never sees them while the agent still reads them. Manual review of the hidden content is recommended.Fix: Remove the large whitespace padding (blank-line blocks or long space runs) and review any content hidden below or to the right of it. Keep skill files compact and reviewable so no instructions can be
- medium Prompt Injection · line 105 Large whitespace padding was detected (a block of blank lines or a long run of spaces). This can push injected instructions below or to the right of the visible area so a human reviewer never sees them while the agent still reads them. Manual review of the hidden content is recommended.Fix: Remove the large whitespace padding (blank-line blocks or long space runs) and review any content hidden below or to the right of it. Keep skill files compact and reviewable so no instructions can be
- medium Excessive Agency · line 146 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
- medium Prompt Injection · line 220 Large whitespace padding was detected (a block of blank lines or a long run of spaces). This can push injected instructions below or to the right of the visible area so a human reviewer never sees them while the agent still reads them. Manual review of the hidden content is recommended.Fix: Remove the large whitespace padding (blank-line blocks or long space runs) and review any content hidden below or to the right of it. Keep skill files compact and reviewable so no instructions can be
- medium Prompt Injection · line 233 Large whitespace padding was detected (a block of blank lines or a long run of spaces). This can push injected instructions below or to the right of the visible area so a human reviewer never sees them while the agent still reads them. Manual review of the hidden content is recommended.Fix: Remove the large whitespace padding (blank-line blocks or long space runs) and review any content hidden below or to the right of it. Keep skill files compact and reviewable so no instructions can be
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 | $0.00028 | $0.02978 |
| Opus 5.5 | $0.00011 | $0.01191 |
| Sonnet 5.5 | $0.00006 | $0.00596 |
| Haiku 4.5 | $0.00003 | $0.00298 |
Grade A, and why
gsd: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 2mo 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 — 275 lines — stays where its author put it; the contents beside it link to each section on GitHub.
GSD New Project
Initialize a new project through unified flow: questioning → research (optional) → requirements → roadmap.
When to Use
Use this command when:
- Starting a new software project from scratch
- Need to gather project context, define requirements, and create roadmap
- Want to use structured project management with GSD
Core Responsibilities
- Setup project structure - Initialize git repo, create .planning/ directory
- Detect brownfield code - Offer to map codebase first if existing code found
- Deep questioning - Extract user vision through collaborative conversation
- Optional domain research - Spawn 4 parallel researchers if needed
- Define requirements - Scope v1 features from table stakes and differentiators
- Create roadmap - Generate phase structure with success criteria
- Initialize STATE.md - Create project memory
Philosophy
Project Initialization is Dream Extraction
You're helping the user discover and articulate what they want to build. This isn't a contract negotiation — it's collaborative thinking.
Be a thinking partner, not an interviewer. Don't interrogate. Collaborate. Don't follow a script.
Start open. Let them dump their mental model. Don't interrupt with structure.
Follow energy. Whatever they emphasized, dig into that.
Process
Phase 1: Setup
MANDATORY FIRST STEP — Execute these checks before ANY user interaction:
- Abort if project exists:
[ -f .planning/PROJECT.md ] && echo "ERROR: Project already initialized. Use /gsd:progress" && exit 1
- Initialize git repo in THIS directory (required even if inside parent repo):
if [ -d .git ] || [ -f .git ]; then
echo "Git repo exists in current directory"
else
git init
echo "Initialized new git repo"
fi
- Detect existing code (brownfield detection):
# Check for code files
CODE_FILES=$(find . -name "*.ts" -o -name "*.js" -o -name "*.py" -o -name "*.go" -o -name "*.rs" -o -name "*.swift" -o -name "*.java" 2>/dev/null | grep -v node_modules | head -20)
HAS_PACKAGE=$([ -f package.json ] || [ -f requirements.txt ] || [ -f Cargo.toml ] || [ -f go.mod ] || [ -f Package.swift ] || [ -f pyproject.toml ] && echo "yes" || echo "no")
HAS_CODEBASE_MAP=$([ -d .planning/codebase ] && echo "yes" || echo "no")
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.
- 2mo ago First seen · 275 lines · 28 tokens per session scan A 71b7a3d5c399
gsd:new-project is a skill published in the GitHub repository allgpt-co/QuickVoice (494 stars, last pushed 4d ago), licensed MIT. It adds 28 tokens to every session and 2,978 once invoked, about $0.0001 per session on Opus 5.5. 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 2026-08-30.
gsd:new-project compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| gsd:new-projectallgpt-co/QuickVoice | Skill | 494 | 4d ago | MIT | A | 28 | Claude Code |
| gsd:new-projectctsstc/get-shit-done-skills | Skill | 8 | 9mo ago | none | A | 28 | Claude Code, Codex |
| Product Managerahmadrrrtx/xr | Skill | 6 | 2d ago | MIT | A | 22 | Claude Code, Codex |
| webhook-handler-patternsmartineserios/thebrana | Skill | 3 | today | MIT | A | 52 | Claude Code |
| 80-livekit-agents-majiayu000-claude-skill-registrmajiayu000/claude-skill-registry-data | Skill | 28 | yesterday | none | A | 18 | Claude Code, Codex |
| 80-livekit-agents-panaversity-agentfactory-1f8ecf89majiayu000/claude-skill-registry-data | Skill | 28 | yesterday | none | A | 18 | Claude Code, Codex |
| writing-livekit-scenarioslivekit/agent-skills | Skill | 74 | yesterday | MIT | A | 178 | Claude Code |