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 pe-menezes/vibeflow --skill discovergit clone --depth 1 https://github.com/pe-menezes/vibeflowWrote 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/pe-menezes/vibeflow/discover)<a href="https://agentmods.dev/skills/pe-menezes/vibeflow/discover"><img src="https://agentmods.dev/badge/skills/pe-menezes/vibeflow/discover.svg" alt="Measured on agentmods" 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 | $0.00066 | $0.01276 |
| Opus 5 | $0.00033 | $0.00638 |
| Sonnet 5 | $0.00013 | $0.00255 |
| Haiku 4.5 | $0.00007 | $0.00128 |
Grade A, and why
discover 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 yesterday.
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.
Copies of this mod
2 near-identical copies found in the catalogue:
- discover — 98% identical, 0 lines differ
- vibeflow-discover — 86% identical, 37 lines differ
How it starts
The opening of the file, as written. The whole thing — 137 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Description and examples
What it does: Runs a short discovery dialogue (1–5 rounds): you describe an idea, the agent asks clarifying questions, challenges scope, and produces a PRD in .vibeflow/prds/<slug>.md. Use when the idea is still vague; if it's already clear, you can go straight to gen-spec.
Examples:
discover quero um fluxo de login por email e senha— Starts dialogue; at the end you get a PRD and can run gen-spec on it.discover feature de exportar relatório em PDF— Same; the agent will ask about scope, audience, and success criteria.
Language
Detect the language of the user's current request or conversation. Write ALL output in that same language. Technical terms in English are acceptable regardless of the detected language.
Web Search Policy
Use WebSearch and WebFetch only when local context (.vibeflow/, codebase,
git history) is insufficient — an unfamiliar framework or API. Local first.
Role
You are an experienced CPO/CTO running a discovery session: challenge vague assumptions, force decisions, cut scope, propose an alternative when the approach looks wrong, say no when something doesn't make sense. Criticize the idea, never the person.
Ground the session in .vibeflow/index.md, conventions.md, and the relevant
patterns. Without .vibeflow/, say so:
"I recommend running analyze first so I can better understand the
project. I will continue with what I can read directly from the code."
Clarity evaluation (fast-track)
After the user's first response, judge three things: is the problem concrete — a real, specific pain rather than a generic one; is the audience defined; is the scope closable into a v0 you can picture.
All three → quick round: summarize what you understood in 3–4 lines (problem, audience, probable scope), challenge 1–2 specific points — can the scope be smaller, is the anti-scope clear — and generate the PRD once the user confirms. That turns a 3–5 round discovery into 1–2.
Otherwise → the full flow below.
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.
- yesterday Changed · -1 lines 4b890fda59f6
- 7d ago First seen · 138 lines · 66 tokens per session scan A 2215dd96d860
discover is a skill published in the GitHub repository pe-menezes/vibeflow (29 stars, last pushed 2d ago), licensed MIT. It adds 66 tokens to every session and 1,276 once invoked, about $0.0003 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
copilot-setup-audit
Audit repository Copilot customization setup. Use this skill to analyze existing configuration, identify missing files, check for best practices, and suggest improvements for agents, prompts, instructions, and skills.
copilot-compatibility-checker
Check VS Code and GitHub Copilot feature compatibility. Use this skill when diagnosing why a feature isn't working, checking required settings, or verifying version requirements for experimental features.
copilot-skill-builder
Create and maintain Agent Skills for VS Code and GitHub Copilot. Use this skill when setting up new skills, skill directories, or SKILL.md files. Helps scaffold project skills in .github/skills/ or personal skills in /.copilot/skills/.
personetta-set-active
Switches the active Personetta persona via set-active. The target tool is auto-detected from the host agent (Claude Code here), so no --format is needed. Use when the user asks to change recipe, switch persona, or set active role.
personetta-current
Reports the active Personetta recipe id using the installed CLI. The host agent (Claude Code here) is auto-detected. Use when the user asks for their current persona, active recipe, or which Personetta role is on.
personetta-list
Lists Personetta recipes (and optionally roles) using the installed Personetta CLI. Use when the user asks what recipes or personas exist before switching.