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 quanghoangf/vibedoc --skill roadmapgit clone --depth 1 https://github.com/quanghoangf/vibedocWrote 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/quanghoangf/vibedoc/roadmap)<a href="https://agentmods.dev/skills/quanghoangf/vibedoc/roadmap"><img src="https://agentmods.dev/badge/skills/quanghoangf/vibedoc/roadmap/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/quanghoangf/vibedoc/roadmap"><img src="https://agentmods.dev/badge/skills/quanghoangf/vibedoc/roadmap.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00133 | $0.02814 |
| Opus 5.5 | $0.00053 | $0.01126 |
| Sonnet 5.5 | $0.00027 | $0.00563 |
| Haiku 4.5 | $0.00013 | $0.00281 |
Grade A, and why
roadmap 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 8d 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 — 163 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Roadmap planner
Turn a project's docs plus a short interview into an epic-level roadmap: a few horizons on the spine, and epics under each one. Stop at epics. Breaking an epic into tasks is a separate step that happens later.
R001 Now (horizon)
R004 Auth & accounts (epic)
R005 Billing (epic)
R002 Next (horizon)
R006 Team workspaces (epic)
R003 Later (horizon)
R007 Public API (epic)
Stay at the business level
Every question and every epic is about what the product does and for whom. Leave out stack, architecture, databases, frameworks, infra and code structure. Those choices are made when an epic is broken into tasks. If you ask about them now, the interview gets longer and the user has to decide things too early. When a doc is mostly technical, take out the user-facing capability it describes and leave the rest.
What an epic is
An epic is a user-visible capability, or a business outcome, that a small team ships in a few weeks to a couple of months. Some tests:
- Too small (a task): "Add Google login button", "Fix pagination".
- Too big (a theme): "Growth", "Better UX", "Scale".
- Right: "Social sign-in", "Self-serve billing", "Team workspaces", "Onboarding checklist".
Aim for 5–15 epics in total. Use short noun phrases as titles (2–5 words).
Process
1. Check what exists
Read the current roadmap. Call vibedoc_get_roadmap if the VibeDoc MCP tools are available. If they are not, list plans/roadmap/R*.md.
The VibeDoc server writes to the project it was started for, and that may not be the one you are in. Call vibedoc_get_status and compare the project name in its heading with the current directory. If they do not match, do not use the MCP tools for this run. Use the file fallback in step 5 and tell the user why.
If items already exist, ask once (single-select) whether to add epics to the existing roadmap (reuse the existing horizons and skip epics that are already there) or stop. Never delete or rewrite existing items. The user owns them.
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.
- 8d ago Changed · +2 lines 375af0739beb
- 14d ago First seen · 161 lines · 133 tokens per session scan A f941c93ca27b
roadmap is a skill published in the GitHub repository quanghoangf/vibedoc (7 stars, last pushed 4d ago), licensed MIT. It adds 133 tokens to every session and 2,814 once invoked, about $0.0005 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 2026-10-06.
Other skills, from other repositories
story-readiness
Checks whether a story is ready to implement: clear acceptance criteria, no open questions, valid ADR and dependencies. Use when the user asks if a story, or the sprint's stories, are ready to start or build.
recipe-create-meet-space
Create a Google Meet meeting space and share the join link.
workthreads
SpecStory Workthreads - a weekly work-thread rollup across a team's repos from SpecStory coding histories (any agent - Claude Code, Codex, Cursor, Gemini, and more). It groups the window's sessions into threads of work per project and labels each new / open / recently closed, so a lead sees what shipped, what is still…
atmos-config
Atmos root configuration: atmos.yaml discovery, precedence, deep merging, basepath, imports, minimal bootstrap, and routing to narrower Atmos skills.
handle-linkedin-connection-request-signal
Use this skill when someone sends a team member an inbound LinkedIn connection request. An inbound request is a deliberate, ACTIVE first-party intent signal — meaningfully stronger than a passive profile view — and it deserves different scoring rules. The skill resolves and enriches the requester, gates them through…
remove
Remove a deployed framework or addon from the current workspace.