epic-implement

epic-implement is a skill for Claude Code from vergil-project/vergil-claude-plugin. It costs 41 tokens per session (1,798 once invoked), scanned A, original, MIT.

A coordinator for an epic, meaning a larger GitHub task made up of smaller issues. It reads the epic, its sub-issues, and its plan to determine what should happen next.

In plain words
What is it for?
Start or resume an epic, reconstruct its progress, guide issues toward their human approval points, and stop when a blocker or review gate requires attention.
Why use it?
It lets work on a multi-issue project continue across sessions without relying on temporary chat context. The authoritative state remains in GitHub and the referenced plan.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: mentions CLAUDE.md; mentions subagents.

Part of the vergil plugin — 15 skills, 2 agents, 2 hooks shipped together

Install

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.

agentmods
npx agentmods add skills/vergil-project/vergil-claude-plugin/epic-implement
Any agent
npx skills add vergil-project/vergil-claude-plugin --skill epic-implement
Clone the repo
git clone --depth 1 https://github.com/vergil-project/vergil-claude-plugin

Made for: Claude Code.

Or install vergil, the plugin that ships this one along with the rest of its 15 skills, 2 agents, 2 hooks.

Wrote 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.

agentmods badge for epic-implement

README.md
[![agentmods](https://agentmods.dev/badge/skills/vergil-project/vergil-claude-plugin/epic-implement.svg)](https://agentmods.dev/skills/vergil-project/vergil-claude-plugin/epic-implement)
Your own site
<a href="https://agentmods.dev/skills/vergil-project/vergil-claude-plugin/epic-implement"><img src="https://agentmods.dev/badge/skills/vergil-project/vergil-claude-plugin/epic-implement.svg" alt="Measured on agentmods" height="20"></a>
Per session 41 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,798 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00041 $0.01798
Opus 5 $0.00020 $0.00899
Sonnet 5 $0.00008 $0.00360
Haiku 4.5 $0.00004 $0.00180

Measured 5d ago against content hash 4469ba5040a2, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

epic-implement 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 5d 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.

skills/epic-implement/SKILL.md · 136 lines

How it starts

The opening of the file, as written. The whole thing — 136 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Epic implement

Shepherd an epic from wherever it stands to its next human gate. epic-implement is the epic-level driver above the issue-* skills. It is stateless by design: everything authoritative lives in GitHub — the epic issue, its sub-issues' open/closed status, and the aligned plan the epic references. Any session context you accumulate is a bonus, never a requirement; if this session is lost or compacted, re-invoking /vergil:epic-implement <epic-ref> re-derives position and continues.

Preflight

  1. Confirm you are the USER agent: vrg-whoami --mode must print user. If not, stop.
  2. Resolve the epic ref (<org>/.github#N, #N, or a URL). Read the epic issue.

1. Emit the rename line

Read the epic title and print a paste-ready session rename for the human — the agent cannot rename its own session:

Suggested session name → run:  /rename epic-<N>-<slug>

2. Reconstruct state from GitHub, starting at the epic issue

Do not rely on any single tool as a state engine. Reconstruct position by:

  1. Reading the epic issue and its referenced plan (epics/<N>-<slug>/plan.md in the epic's home repo) — the plan is the authoritative execution driver: the intended task sequence and the terminal bookends live there.
  2. Reading each sub-issue's open/closed status.
  3. Reconciling the two: the runnable frontier is every task the plan says is ready whose dependencies (per the plan) are closed, and which is itself open.

vrg-epic-audit may be consulted as a consistency check (linking, drift) but is never the source of position. Where the plan's ordering is informal (no Blocked-by links), infer it from the plan text plus issue state.

3. Work the runnable frontier

Drive every currently-runnable task to its gate. Use sub-agents wherever they make this efficient — independent tasks should run in parallel. Route each task by its kind label:

Task kind Run via
code (default task) issue-implement
validation issue-validate
deployment issue-deploy

Read the full file on GitHub · 136 lines

Changes

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.

  1. 5d ago First seen · 136 lines · 41 tokens per session scan A 4469ba5040a2

Subscribe to this mod's changes

epic-implement is a skill published in the GitHub repository vergil-project/vergil-claude-plugin (2 stars, last pushed 3d ago), licensed MIT. It adds 41 tokens to every session and 1,798 once invoked, about $0.0002 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 2026-08-31.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

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…

microsoft/ai-agents-for-beginners · 200 tokens

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…

vercel/next.js · 95 tokens

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…

vercel/next.js · 103 tokens

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…

microsoft/vscode · 72 tokens

imagegen

Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…

openai/codex · 113 tokens