A file writer for creating child Epic definitions from structured project information. An Epic is a large piece of work that groups related tasks or user stories.

Creating or refining one Epic-definition file per Epic, using Jira information, code-scan results, scope decisions, and existing Epics.

It turns prepared project findings and requirements into consistent Epic files while reducing duplicate work. It leaves version-control commits to the user.

epic-writer — Agent for Claude Code by ihudak/ihudak-claude-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 ihudak/ihudak-claude-plugins

Claude Code

/plugin install product-workflows

Made for: Claude Code.

Or install product-workflows, the plugin that ships this one along with the rest of its 12 commands, 14 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/agents/ihudak/ihudak-claude-plugins/epic-writer/github.svg)](https://agentmods.dev/agents/ihudak/ihudak-claude-plugins/epic-writer)

Your own site

<a href="https://agentmods.dev/agents/ihudak/ihudak-claude-plugins/epic-writer"><img src="https://agentmods.dev/badge/agents/ihudak/ihudak-claude-plugins/epic-writer/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/agents/ihudak/ihudak-claude-plugins/epic-writer"><img src="https://agentmods.dev/badge/agents/ihudak/ihudak-claude-plugins/epic-writer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 110 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 2,973 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	$0.00110	$0.02973
Opus 5.5	$0.00044	$0.01189
Sonnet 5.5	$0.00022	$0.00595
Haiku 4.5	$0.00011	$0.00297

Measured 1mo ago against content hash 29f3a3cd2881, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

epic-writer 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/product-workflows/agents/epic-writer.md · 178 lines

How it starts

The opening of the file, as written. The whole thing — 178 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Core references. A citation of the form workflows-core:<name> names a shared reference in the workflows-core plugin. Load it with Skill(skill: "workflows-core:reference", args: "<name>") — never by path: ${CLAUDE_PLUGIN_ROOT} resolves to this plugin, which does not carry it.

Epic-definition writer for /epics Phase 6. The orchestrator resolved scope and inputs in Phases 2–5; this agent executes — write-only, and it never creates a branch or commits (still true — it runs no git at all; the specs-repo commit is the orchestrator's terminal commit-artifacts step touches only $SPECS_PATH).

Inputs

The orchestrator writes a handoff file (a temp file) and passes its absolute path. Read it first. It contains:

folder_read
code_scanner_outputs (when code scan ran; else empty)
scope — the Phase 2 in-scope / out-of-scope decisions
existing_epics — for non-duplication
prd_dir — the resolved PRD folder; each Epic is written to its own EPIC-<PRD-KEY>-NN-<eslug>/ inside it
vi_goal, key
requirements + requirements_source — the PRD requirement inventory (from the folder read); the coverage ground truth.
applicable_ard — the PRD-level ARD invariants (AD#N) + guidance_summary, or absent when no ARD resolved.
existing_epic_themes — themes of the already-linked Epics, for the pre-draft dedup pre-flight.
mode — generate (net-new Epics, the legacy default), refine (fill in / re-refine the refinement_targets), or both.
refinement_targets — list of {key, scope_hint, current_body_path} for the existing Epics to fill in (present only when mode is refine or both; empty otherwise). current_body_path is that Epic's existing draft, at <prd_dir>/EPIC-<key>-<eslug>/epic.md — the same keyless-filename, keyed-folder shape this agent writes (see the invariant below). Nothing imports anything, and <EPIC-KEY>.md is a filename this agent explicitly forbids, so naming it here made every refine run regenerate instead of iterating.
docs_grounding — the docs-grounder digest (docs_references + docs_challenges), or absent when docs grounding was OFF/EMPTY. Use docs_references for terminology / current-behavior consistency; treat docs_challenges as authoring cautions. Consistency reference only — not a source of new Epic claims (see Traceability below).

Read the full file on GitHub · 178 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 Changed · +5 lines 29f3a3cd2881
2mo ago Changed · +2 lines 5b838c4f99d3
2mo ago Changed · -4 lines · +3 tokens per session 0ee74e504a77
2mo ago First seen · 175 lines · 107 tokens per session scan A 2cb4b8986f29

Subscribe to this mod's changes

epic-writer is an agent published in the GitHub repository ihudak/ihudak-claude-plugins (2 stars, last pushed 1mo ago), licensed MIT. It adds 110 tokens to every session and 2,973 once invoked, about $0.0004 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.

Claude Code Project management Writing and docs ai-agents ai-code-review claude-code-plugins developer-productivity documentation-automation

epic-writer next to 6 agents from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
epic-writerihudak/ihudak-claude-plugins	Agent	2	1mo ago	MIT	A	110	Claude Code
code-reviewerJose-Ribeir/claude-code-review-gate	Agent	3	today	Apache-2.0	A	41	Claude Code
code-resolverJose-Ribeir/claude-code-review-gate	Agent	3	today	Apache-2.0	A	56	Claude Code
code-filterJose-Ribeir/claude-code-review-gate	Agent	3	today	Apache-2.0	A	54	Claude Code
code-reviewerNikiforovAll/claude-code-rules	Agent	142	9d ago	Apache-2.0	A	37	Claude Code
meeting-organizerjuliusz-cwiakalski/agentic-delivery-os	Agent	43	today	MIT	A	9	Claude Code
Music Producerfrankxai/agentic-creator-os	Agent	12	2d ago	Apache-2.0	A	16	Claude Code