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 vergil-project/vergil-claude-plugin --skill epic-creategit clone --depth 1 https://github.com/vergil-project/vergil-claude-pluginWrote 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/vergil-project/vergil-claude-plugin/epic-create)<a href="https://agentmods.dev/skills/vergil-project/vergil-claude-plugin/epic-create"><img src="https://agentmods.dev/badge/skills/vergil-project/vergil-claude-plugin/epic-create.svg" alt="Measured on agentmods" 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 | $0.00000 | $0.03892 |
| Opus 5 | $0.00000 | $0.01946 |
| Sonnet 5 | $0.00000 | $0.00778 |
| Haiku 4.5 | $0.00000 | $0.00389 |
Grade A, and why
epic-create 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 — 260 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Epic create
Overview
epic-create is the outer, orchestrating workflow for non-trivial work. It
runs the brainstorm → design → plan pipeline, creates the finite epic in its
resolved home (the org .github by default; a private repo self-homes its
epics — see Preflight), seeds the epic's bookend tasks, and publishes the
spec and plan as the epic's docs. This is where significant work starts — not a
step reached at the end.
Canonical convention: vergil-project/.github#40; worked example (this skill's
own redesign): vergil-project/.github#85.
Default entry point
Start here, not in brainstorming. A solution worth thinking through is
worth recording as work, so there is little value in brainstorming a design and
then walking away from it untracked. epic-create opens into brainstorming and
lets the process play out.
- Most work at this scale is a significant feature or change → an epic.
- If the design collapses to a trivial, single-PR change → it is a task,
not an epic. File it in the member repo under an existing finite epic or the
repo's ad-hoc epic (
vrg-issue-create --epic adhoc) and stop. Do not mint an epic.
When unsure, it is a task. Epics are for initiatives, not individual changes.
The epic architecture — bookend tasks
An epic is never closed until you have decided what comes next AND confirmed the docs reflect what changed. Almost no real problem is 100% closed by one epic; you deliver a tangible subset and acknowledge the follow-on. So every epic carries these bookend tasks:
- First task — documentation. The spec + plan for the epic; this task's PR
publishes them into
.github(see the workflow below). - Closing bookends — ordered, both mandatory:
- Documentation-review task — verify the epic's changes are
comprehensively reflected in the human-facing docs, especially the
versioned site docs (
docs/site/…), which are the primary interface for understanding the system and tend to drift behind the code. Treat this as a sweep, not a single edit: an epic's documentation usually spans multiple repositories — per-repo docs in each member repo, the higher-level summary docs in thedocsrepo, and occasionally correction/plan notes in.github. So it does not assume one docs PR closes it. Where a repo's docs need work, the review spawns a per-repo doc task (born linked under the epic), each closed by a same-repo PR — the only linkage that respects the placement law (see Notes). File the review task itself in the repo where the bulk of its own sweep lands (usually the member repo holding the site docs, e.g.vergil-tooling/docs/site); it spawns siblings for the other repos rather than forcing one cross-repo PR to close it. It runs before the retrospective. - Retrospective task (terminal) — the mandatory, single,
backward-looking record that partners the spec and plan at the documentation
tier; a later reader follows spec → plan → retrospective. Authored with
epic-retrospective, the run-once finishing skill whose preflight gate refuses to run until every other child of the epic is closed. Its docs PR is the epic's closing bookend, and its merge closes the epic. Seed it at creation (titleRetrospective: <epic-slug>), homed in the epic's home repo.
- Documentation-review task — verify the epic's changes are
comprehensively reflected in the human-facing docs, especially the
versioned site docs (
- Follow-on brainstorm — semi-optional (forward axis). Reviewing what shipped and brainstorming the follow-on epic(s) is a forward-looking concern that no longer defines the end of an epic. Seed it as a bookend only when a known enabling chain exists at creation ("we're building this specifically to unlock X/Y/Z"); otherwise accrue it as specific follow-on tasks during implementation, or skip it when there is nothing to chain. Its outcomes are recorded in the retrospective's §5.
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 First seen · 260 lines · 0 tokens per session scan A 21cff1edf2ae
epic-create is a skill published in the GitHub repository vergil-project/vergil-claude-plugin (2 stars, last pushed 5d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 3,892 tokens. 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 2026-08-31.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…
chronicle
Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…