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 epic-breakdowngit 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/epic-breakdown)<a href="https://agentmods.dev/skills/quanghoangf/vibedoc/epic-breakdown"><img src="https://agentmods.dev/badge/skills/quanghoangf/vibedoc/epic-breakdown/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/epic-breakdown"><img src="https://agentmods.dev/badge/skills/quanghoangf/vibedoc/epic-breakdown.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 | $0.00169 | $0.02983 |
| Opus 5.5 | $0.00068 | $0.01193 |
| Sonnet 5.5 | $0.00034 | $0.00597 |
| Haiku 4.5 | $0.00017 | $0.00298 |
Grade A, and why
epic-breakdown scanned grade A with 1 finding 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
<exact commands from this project: build, lint, tests, a curl or a page to open> How it starts
The opening of the file, as written. The whole thing — 171 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Epic breakdown
Turn one epic into a short, ordered list of tasks. A coding agent should be able to pick up any one of them cold and finish it. This skill is a follow-up to roadmap-planner: epics are roadmap items that have a **Parent:** (horizon), and their body often already contains In scope / Out of scope / Done when.
The tasks are the product of this skill. Someone who reads a task file should know what to build, where it goes, how it follows the codebase's patterns, and how to prove it works, without asking anyone. A vague task gets a vague implementation.
1. Pick the epic
Argument given: resolve it.
- An id:
R004,r4. - A path:
plans/roadmap/R004-billing.md. - A title fragment: match it against the titles.
Read the file. If what you read is a horizon (it has no **Parent:**), say so and treat it as "no argument", listing only that horizon's epics.
No argument: list the epics and let the user choose.
-
Get every item with
vibedoc_get_roadmap(MCP), or readplans/roadmap/R*.md. Epics are the items that have a parent. -
Print a compact table: id, title, horizon, status, and linked task count with their done count. For example:
ID Epic Horizon Status Tasks R005 Self-serve billing Now in-progress 2/5 done R006 Team workspaces Now planned — R009 Public API Next planned — -
Ask one single-select
AskUserQuestionwith the 3–4 most likely candidates, in this order: in-progress epics first, then planned epics with no tasks in the earliest horizon. Leave outdoneepics. The user can pick "Other" to type any id.
If the chosen epic already has linked tasks, show them and ask whether to add the missing tasks or stop. Never rewrite existing task files, because an agent may already be working from them.
A spec instead of an epic: the user pastes a feature spec (or describes a feature) rather than naming an epic. Use the spec as the epic body in the steps below, and first ask one single-select question about where the tasks go:
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 First seen · 171 lines · 169 tokens per session scan A 2a038e61953d
epic-breakdown is a skill published in the GitHub repository quanghoangf/vibedoc (5 stars, last pushed today), licensed MIT. It adds 169 tokens to every session and 2,983 once invoked, about $0.0007 per session on Opus 5.5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-29.
Other skills, from other repositories
story-readiness
Is a story implementation-ready? Checks clear acceptance criteria, open questions, ADR refs. READY/NEEDS WORK/BLOCKED/NOT ASSESSED.
recipe-create-meet-space
Create a Google Meet meeting space and share the join link.
atmos-config
Atmos root configuration: atmos.yaml discovery, precedence, deep merging, basepath, imports, minimal bootstrap, and routing to narrower Atmos skills.
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…
projects
List all managed projects with status, branch, open PRs, and open issue counts — portfolio-level view.
remove
Remove a deployed framework or addon from the current workspace.