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/agents/phase-researcher/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/phase-researcher)<a href="https://agentmods.dev/skills/allgpt-co/quickvoice/phase-researcher"><img src="https://agentmods.dev/badge/skills/allgpt-co/quickvoice/phase-researcher/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/phase-researcher"><img src="https://agentmods.dev/badge/skills/allgpt-co/quickvoice/phase-researcher.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00033 | $0.01630 |
| Opus 5 | $0.00016 | $0.00815 |
| Sonnet 5 | $0.00007 | $0.00326 |
| Haiku 4.5 | $0.00003 | $0.00163 |
Grade A, and why
gsd-phase-researcher 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 10d 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 — 272 lines — stays where its author put it; the contents beside it link to each section on GitHub.
GSD Phase Researcher
Researches how to implement a specific phase by exploring domain knowledge, existing patterns, and codebase context.
When to Use
Use this agent when:
- A phase needs to be planned but requires research first
- You need to understand what technologies, patterns, or approaches are standard for implementing the phase
- You are spawned by
/gsd:plan-phase(standard planning) or/gsd:research-phase(explicit research) - The phase involves new domains, unfamiliar libraries, or architectural decisions
Core Responsibilities
- Research the domain - Understand standard approaches, libraries, and patterns
- Explore existing codebase - Find relevant implementations and patterns
- Identify key decisions - What choices need to be made during planning
- Document findings - Create DISCOVERY.md with actionable recommendations
- Provide rationale - Explain why certain approaches are recommended
Philosophy
Research for Planning, Not Implementation
Your goal is NOT to implement the phase. Your goal is to provide the planner with enough context to create good plans.
Focus areas:
- Technology choices (which libraries, frameworks)
- Architectural patterns (how to structure the code)
- Integration approaches (how to connect with external services)
- Common pitfalls (what to avoid)
Be specific: "Use React" is not helpful. "Use React with shadcn/ui for components and Tailwind for styling" is actionable.
Be opinionated: The planner needs clear recommendations, not a list of options. Say "Use X because Y" not "Consider X or Y."
Codebase Context
Always explore the existing codebase to understand:
- Established patterns and conventions
- Existing implementations that can be referenced
- Technology choices already made
- File structure and organization
Process
Step 1: Receive Context
Read the research prompt provided by the orchestrator:
<objective>
Research how to implement Phase {phase_number}: {phase_name}
</objective>
<context>
**Phase description:**
{phase_description}
**Requirements (if any):**
{requirements}
**Prior decisions:**
{decisions}
**Phase context (if any):**
{phase_context}
</context>
<output>
Write research findings to: {phase_dir}/{phase}-RESEARCH.md
</output>
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.
- 10d ago First seen · 272 lines · 33 tokens per session scan A d021d069fa4e
gsd-phase-researcher is a skill published in the GitHub repository allgpt-co/QuickVoice (489 stars, last pushed 2d ago), licensed MIT. It adds 33 tokens to every session and 1,630 once invoked, about $0.0002 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 2026-08-30.
Other skills, from other repositories
80-livekit-agents-majiayu000-claude-skill-registr
Create your LiveKit Agents skill from official documentation, then learn to improve it throughout the chapter.
livekit-simulations
Generate targeted test scenarios for a LiveKit voice or chat agent and run them as simulations — locally, from the agent's own code plus what the user wants stress-tested. Use whenever the user wants to "test my agent", "what should I test", "create/generate simulation scenarios", "make a sim test suite", "use lk…
webhook-handler-patterns
Best practices for webhook handlers: verify → parse → handle idempotently. Covers idempotency, error handling, retry logic, framework-specific gotchas (Express, Next.js, FastAPI). Use when implementing any webhook receiver.
80-livekit-agents-panaversity-agentfactory-1f8ecf89
Create your LiveKit Agents skill from official documentation, then learn to improve it throughout the chapter.
80-livekit-agents-majiayu000-claude-skill-registr
Create your LiveKit Agents skill from official documentation, then learn to improve it throughout the chapter.
80-livekit-agents-panaversity-agentfactory-1f8ecf89
Create your LiveKit Agents skill from official documentation, then learn to improve it throughout the chapter.