A planning command for creating a large, multi-phase feature plan with tests-first steps. TDD, or test-driven development, structures work around defining tests alongside the implementation plan.

Use it for substantial features that need codebase exploration, risk review, phased execution, and optionally a TDD structure.

It turns a broad feature into phases, tasks, and saved state while first exploring the codebase and its existing testing patterns.

epic — Skill for Claude Code by Zate/cc-plugins

Install

Getting it into your agent

This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.

Claude Code

/plugin marketplace add Zate/cc-plugins

Claude Code

/plugin install devloop

Made for: Claude Code.

Or install devloop, the plugin that ships this one along with the rest of its 19 skills, 6 agents.

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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/zate/cc-plugins/epic/github.svg)](https://agentmods.dev/skills/zate/cc-plugins/epic)

Your own site

<a href="https://agentmods.dev/skills/zate/cc-plugins/epic"><img src="https://agentmods.dev/badge/skills/zate/cc-plugins/epic/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/zate/cc-plugins/epic"><img src="https://agentmods.dev/badge/skills/zate/cc-plugins/epic.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 16 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 1,675 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.

Model	Per session	Once invoked
Fable 5.1	$0.00016	$0.01675
Opus 5.5	$0.00006	$0.00670
Sonnet 5.5	$0.00003	$0.00335
Haiku 4.5	$0.00002	$0.00168

Measured 1mo ago against content hash c3d5bfb40766, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

epic 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 1mo 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.

plugins/devloop/skills/epic/SKILL.md · 153 lines

How it starts

The opening of the file, as written. The whole thing — 153 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Devloop Epic

Create a multi-phase epic plan. Produces epic.md (full plan) and epic.json (state machine). Do the work directly.

Step 1: Parse Input

Extract topic from $ARGUMENTS. If missing, show usage and STOP. --no-tdd skips the tests-first structure.

Step 2: Check Existing Epic

If .devloop/epic.json exists:

"complete": archive to .devloop/archive/. Continue.
"in_progress": Report progress. AskUserQuestion: "Archive and replace" or "Cancel".

Step 3: Explore & Ask in Parallel

3a. Background Exploration

Spawn an Explore agent with run_in_background: true to scan the codebase for context on the topic. Let it report back: tech stack, testing framework, affected areas, existing patterns, risks.

The agent should use LSP.workspaceSymbol to find topic-related symbols and LSP.documentSymbol to map affected file structure. If LSP errors or is unavailable, fall back to Grep + Glob for pattern-based discovery.

Token efficiency: Instruct the Explore agent to cap its report at ~500 words. It should report findings as concise bullet points (file paths + one-line description), not raw file contents. Filter out files unrelated to the epic topic before reporting. This keeps the exploration context lean so the planning phase receives signal, not noise.

3b. While Explorer Runs -- End State

AskUserQuestion: "What does 'done' look like for this epic? What should the user/system be able to do when it's complete?"

Review Pattern (applies to Steps 4, 5, 8)

AskUserQuestion truncates long content -- users cannot scroll inside it. Never embed full content in the question.

mdv Detection (once, before first review)

Call mcp__mdv__list_contexts. If it succeeds, mdv is available -- remember this for all subsequent reviews. If the tool errors or is not found, mdv is unavailable -- skip all mdv calls for the rest of the session.

Presenting content for review

Write the full content to .devloop/draft/<name>.md (create .devloop/draft/ if needed)
Output a concise summary as regular conversation text (this is scrollable)
mdv available: call mcp__mdv__navigate_to to open the draft file. Use scroll_to_element or add_annotation to highlight areas needing attention if useful.
mdv unavailable: tell the user: "Full content at .devloop/draft/<name>.md -- open it in your editor to review."
AskUserQuestion: only the short prompt (e.g., "Add, remove, or modify any?"), never the content itself

Read the full file on GitHub · 153 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.

1mo ago First seen · 153 lines · 16 tokens per session scan A c3d5bfb40766

Subscribe to this mod's changes

epic is a skill published in the GitHub repository Zate/cc-plugins (10 stars, last pushed 2mo ago), licensed MIT. It adds 16 tokens to every session and 1,675 once invoked, about $0.0001 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 2026-08-31.

Planning TDD Testing

engram-testing-coverage

TDD and coverage standards for Engram. Trigger: When implementing behavior changes in any package.

Gentleman-Programming/engram · 25 tokens

conductor-implement

Execute tasks from a track's implementation plan following TDD workflow.

rmyndharis/antigravity-skills · 17 tokens

principle-test-behavior-not-implementation

Apply when you write, change, or keep a test. Assert what the code's users can observe, so that the test fails when that behavior breaks and keeps passing when only the internals change.

michael-denyer/pstack-claude · 50 tokens

iterative-development

TDD iteration loops using Claude Code Stop hooks - runs tests after each response, feeds failures back automatically.

alinaqi/maggy · 24 tokens

python

Python development with ruff, mypy, pytest - TDD and type safety.

alinaqi/maggy · 18 tokens

tdd

This skill should be used when the user wants to implement features or fix bugs using test-driven development. Enforces the RED-GREEN-REFACTOR cycle with vertical slicing, context isolation between test writing and implementation, human checkpoints, and auto-test feedback loops. Uses multi-agent orchestration with the…

glebis/claude-skills · 92 tokens