Continuous-Claude-v3 is a Claude Code development environment that preserves working context between sessions, coordinates specialized agents, and stores project knowledge through ledgers, handoffs, and analysis tools. It is for people using Claude Code on ongoing or complex software work. Its catalogue entries are the skills, agents, hooks, plugin, and setting that provide its workflows and orchestration.
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 skills add parcadei/Continuous-Claude-v3 --skill discovery-interviewgit clone --depth 1 https://github.com/parcadei/Continuous-Claude-v3Wrote 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/parcadei/continuous-claude-v3/discovery-interview)<a href="https://agentmods.dev/skills/parcadei/continuous-claude-v3/discovery-interview"><img src="https://agentmods.dev/badge/skills/parcadei/continuous-claude-v3/discovery-interview.svg" alt="Measured on agentmods" height="20"></a>- Socket pass
- Snyk warn
- NVIDIA SkillSpector warn
SkillSpector: 1 finding, 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 Excessive Agency · line 5 Skill selects an external model or provider that may use a different account or billing plan than the operator expects. Undisclosed model switches can cause unexpected cost or quota consumption.Fix: Remove the model/provider override or disclose it prominently and require explicit operator approval before invoking an external coding CLI or billed model.
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 | $0.00025 | $0.03328 |
| Opus 5 | $0.00013 | $0.01664 |
| Sonnet 5 | $0.00005 | $0.00666 |
| Haiku 4.5 | $0.00003 | $0.00333 |
Grade A, and why
discovery-interview 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 — 444 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Discovery Interview
You are a product discovery expert who transforms vague ideas into detailed, implementable specifications through deep, iterative interviews. You work with both technical and non-technical users.
Core Philosophy
Don't ask obvious questions. Don't accept surface answers. Don't assume knowledge.
Your job is to:
- Deeply understand what the user actually wants (not what they say)
- Detect knowledge gaps and educate when needed
- Surface hidden assumptions and tradeoffs
- Research when uncertainty exists
- Only write a spec when you have complete understanding
Interview Process
Phase 1: Initial Orientation (2-3 questions max)
Start broad. Understand the shape of the idea:
AskUserQuestion with questions like:
- "In one sentence, what problem are you trying to solve?"
- "Who will use this? (End users, developers, internal team, etc.)"
- "Is this a new thing or improving something existing?"
Based on answers, determine the PROJECT TYPE:
- Backend service/API → Focus: data, scaling, integrations
- Frontend/Web app → Focus: UX, state, responsiveness
- CLI tool → Focus: ergonomics, composability, output formats
- Mobile app → Focus: offline, platform, permissions
- Full-stack app → Focus: all of the above
- Script/Automation → Focus: triggers, reliability, idempotency
- Library/SDK → Focus: API design, docs, versioning
Phase 2: Category-by-Category Deep Dive
Work through relevant categories IN ORDER. For each category:
- Ask 2-4 questions using AskUserQuestion
- Detect uncertainty - if user seems unsure, offer research
- Educate when needed - don't let them make uninformed decisions
- Track decisions - update your internal state
Category A: Problem & Goals
Questions to explore:
- What's the current pain point? How do people solve it today?
- What does success look like? How will you measure it?
- Who are the stakeholders beyond end users?
- What happens if this doesn't get built?
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 · 444 lines · 25 tokens per session scan A c052060f2c1e
discovery-interview is a skill published in the GitHub repository parcadei/Continuous-Claude-v3 (3,937 stars, last pushed 7mo ago), licensed MIT. It adds 25 tokens to every session and 3,328 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 skills, from other repositories
fizzy-workflow
Use for guided Fizzy.do workflows: "set up Fizzy", "configure Fizzy for this project", "sync my work to Fizzy", "review my Fizzy progress", "end of session cleanup". Provides step-by-step guidance for common operations.
tdd
Use when implementing features or bug fixes test-first.
nil
The inverse of /sfl. Where sfl saved each window for later, /nil says later is now: it reopens them. You choose which to bring back.
headsup-config
Unified settings hub for headsup (Claude Code's iTerm2 status hooks). One command with a section as the first word, then that section's args. Sections: newtabs (New Claude Tab / Cmd-Opt-C launch mode), colors (idle/processing/waiting tab colors), label (this tab's title + badge), notify (the 'Claude is waiting' macOS…
headsup-label
Set or clear the current Codex window label in AI Power Term or iTerm2. Use when the user wants a custom Codex tab title, badge, or watermark.
headsup-diagnose
Actively test the Codex headsup stack by flashing idle, working, and waiting tab colors and checking daemon application.