epic-retrospective

epic-retrospective is a skill for Claude Code from vergil-project/vergil-claude-plugin. It costs 113 tokens per session (1,883 once invoked), scanned A, original, MIT.

The final record in a planned body of work called an epic, which is a larger project made up of related tasks. It creates a retrospective describing what was planned and what actually happened.

In plain words
What is it for?
Finish an epic by writing its retrospective after the specification, plan, and implementation work are complete.
Why use it?
It closes the project with an honest comparison between the plan and the result, so lessons and differences are not lost.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the vergil plugin — 15 skills, 1 agent, 2 hooks shipped together

Good fit Finish an epic by writing its retrospective after the specification, plan, and implementation work are complete.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/vergil-project/vergil-claude-plugin/epic-retrospective
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.

Any agent
npx skills add vergil-project/vergil-claude-plugin --skill epic-retrospective
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, 1 agent, 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-retrospective

README.md
[![agentmods](https://agentmods.dev/badge/skills/vergil-project/vergil-claude-plugin/epic-retrospective/github.svg)](https://agentmods.dev/skills/vergil-project/vergil-claude-plugin/epic-retrospective)
Your own site
<a href="https://agentmods.dev/skills/vergil-project/vergil-claude-plugin/epic-retrospective"><img src="https://agentmods.dev/badge/skills/vergil-project/vergil-claude-plugin/epic-retrospective/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.

agentmods 80×15 button for epic-retrospective

Your own site · 80×15
<a href="https://agentmods.dev/skills/vergil-project/vergil-claude-plugin/epic-retrospective"><img src="https://agentmods.dev/badge/skills/vergil-project/vergil-claude-plugin/epic-retrospective.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 113 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,883 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 $0.00113 $0.01883
Opus 5 $0.00056 $0.00941
Sonnet 5 $0.00023 $0.00377
Haiku 4.5 $0.00011 $0.00188

Measured 10d ago against content hash 0844c7a2ee2a, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

epic-retrospective 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 10d 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-retrospective/SKILL.md · 140 lines

How it starts

The opening of the file, as written. The whole thing — 140 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Epic retrospective

Overview

epic-retrospective is the terminal, run-once finishing gate of the epic lifecycle. Where epic-create opens an epic with a spec + plan and epic-implement drives its tasks (re-run as many times as the work takes), epic-retrospective closes it by authoring a single backward-looking record — retrospective.md — that partners spec.md and plan.md at the documentation tier. A later reader follows spec → plan → retrospective: what we set out to do, how we planned it, and honestly how it went.

Its deeper purpose is the delta between what was planned and what was actually done — the check a Gantt chart never circles back to make. A small delta means the planning discipline is working; a large one means the epic taught us something. Either way it is captured, not lost.

The three-skill lifecycle and their invocation cardinality:

Skill Runs Role
epic-create once make the epic exist (spec + plan + bookends)
epic-implement N times drive the runnable frontier; pause on blockers; resume
epic-retrospective once the finishing gate every epic passes through

Canonical convention: vergil-project/.github#40; this skill's own epic: vergil-project/.github#201.

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) and read the epic issue. Identify the retrospective task — the epic's retrospective bookend, seeded by epic-create and stamped with the retrospective label (vrg-issue-create --kind retrospective, tooling ≥ 2.1.167). Identify it by that label. Fall back to the title convention (Retrospective: <epic-slug>) only for epics created before the label existed.

The definition-of-done gate

Running this skill is the assertion "the epic is done." The gate mechanically verifies that assertion — it is the sole enforcement of the retrospective's terminality (there are no static Blocked-by reflinks; they would not scale against a dynamic epic):

Read the full file on GitHub · 140 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. 10d ago First seen · 140 lines · 113 tokens per session scan A 0844c7a2ee2a

Subscribe to this mod's changes

epic-retrospective is a skill published in the GitHub repository vergil-project/vergil-claude-plugin (2 stars, last pushed 8d ago), licensed MIT. It adds 113 tokens to every session and 1,883 once invoked, about $0.0006 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