epic

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.

In plain words
What is it for?
Use it for substantial features that need codebase exploration, risk review, phased execution, and optionally a TDD structure.
Why use it?
It turns a broad feature into phases, tasks, and saved state while first exploring the codebase and its existing testing patterns.

Skill for Claude CodeCodex

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/zate/cc-plugins/epic
Any agent
npx skills add Zate/cc-plugins --skill epic
Clone the repo
git clone --depth 1 https://github.com/Zate/cc-plugins

Made for: Claude Code, Codex.

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. 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 $0.00016 $0.01675
Opus 5 $0.00008 $0.00838
Sonnet 5 $0.00003 $0.00335
Haiku 4.5 $0.00002 $0.00168

Measured 2d ago against content hash c3d5bfb40766, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, 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 2d 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

  1. Write the full content to .devloop/draft/<name>.md (create .devloop/draft/ if needed)
  2. Output a concise summary as regular conversation text (this is scrollable)
  3. 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.
  4. mdv unavailable: tell the user: "Full content at .devloop/draft/<name>.md -- open it in your editor to review."
  5. 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.

  1. 2d 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 1mo ago), licensed MIT. It adds 16 tokens to every session and 1,675 once invoked, about $0.0001 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

brainstorming

You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.

obra/superpowers · 37 tokens

chat-pet-sprite-creation

Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.

microsoft/vscode · 53 tokens

cpu-profile-analysis

Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…

microsoft/vscode · 71 tokens

agent-host-chat-contributions

Build and review cross-cutting agent-host chat behavior through lifecycle contributions. Use when adding turn lifecycle side effects, prompt or context injection, restored-history transformation, protocol-action observation, or when reviewing changes that add code to AgentSideEffects or AgentService.

microsoft/vscode · 56 tokens

auto-perf-optimize

Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.

microsoft/vscode · 62 tokens