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.
/plugin marketplace add ihudak/ihudak-claude-plugins/plugin install product-workflowsWrote 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.
[](https://agentmods.dev/commands/ihudak/ihudak-claude-plugins/epics)<a href="https://agentmods.dev/commands/ihudak/ihudak-claude-plugins/epics"><img src="https://agentmods.dev/badge/commands/ihudak/ihudak-claude-plugins/epics/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.
<a href="https://agentmods.dev/commands/ihudak/ihudak-claude-plugins/epics"><img src="https://agentmods.dev/badge/commands/ihudak/ihudak-claude-plugins/epics.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00193 | $0.22068 |
| Opus 5.5 | $0.00077 | $0.08827 |
| Sonnet 5.5 | $0.00039 | $0.04414 |
| Haiku 4.5 | $0.00019 | $0.02207 |
Grade A, and why
epics 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.
How it starts
The opening of the file, as written. The whole thing — 985 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Draft child Epics for the resolved Product Requirements Document: $ARGUMENTS
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.
/epics is the keyed Epic-writing workflow. Given a Product Requirements Document key, it reads the PRD plus its existing Epics from the resolved PRD folder, optionally scans code repos to identify reusable capabilities and gaps, drafts child Epic definitions as markdown files under the resolved output directory, and gates the result on an Opus review.
Key distinction from /document (keyed mode): the PRD being Epic-ized is not yet implemented — there is no implementation record and no commit to diff. Code scanning (when enabled) is a plain filesystem search to understand what exists and what needs to be built.
/epics accepts exactly two shapes and refuses everything else (Phase 0 steps 1a and 1b): a PRD- folder, which it partitions into new Epics, or an EPIC- folder holding its epic.md that has a PRD above it, which it re-refines. A stand-alone EPIC- folder, an EPIC- folder holding no epic.md and a BRD- container are all refused. Epics come from a PRD only, and /epics is the only command in this plugin that creates an EPIC- folder — /create-ard and /specify refuse an absent one rather than minting it.
/epics never branches and never commits the Epic drafts (still true — the run's git writes are confined to $SPECS_PATH, per workflows-core:specs-repo-git; the run does make read-only git calls elsewhere — Phase 4's git remote get-url origin per candidate clone and Phase 8's git diff --stat from project_root — but none of them writes), and writes only inside the resolved PRD folder — one EPIC-<PRD-KEY>-NN-<eslug>/ per Epic, plus _coverage.md beside prd.md. Git hygiene of the write target is the user's responsibility — they may or may not have it under version control. The run commits only inside $SPECS_PATH, and only its bounded session-artifact paths (workflows-core:specs-repo-git §2.1) — via the specs-preflight flush at run start (§3.4) and the terminal commit-artifacts step (§4); never the drafts, never the write target. It still creates no branch (still true — specs-preflight switches $SPECS_PATH only between branches that already exist, and only plugin-created ones (workflows-core:specs-repo-git §2.2); it creates none).
Phase 0 — Load
- Flags.
--no-docs— boolean; turns documentation grounding off for this run (Phase 2).--docs <path>— points documentation grounding at that root for this run instead of${DOCS_PATH:-/workspace/docs}; strip the flag and its value together before any remaining-argument classification, or the path is read as part of the address. Declared for every consumer byworkflows-core:docs-groundingProcedure step 1 (Flags first), which resolves it; this command only has to recognise it and pass the invocation through. Strip both, and--docs's value, from$ARGUMENTSbefore step 1 classifies what remains. - Resolve the address. Parse the single positional address from
$ARGUMENTS— a<KEY>, or an@<path>naming a folder or a file inside one — and resolve it withresolve-address(Skill(skill: "workflows-core:reference", args: "addressing resolve-address"), §3), with no<KIND>argument: a slice folder isPRD--prefixed while thebrd-link.mdinside it assertskind: brd, so narrowing the resolution by kind would refuse on one route the very folder it resolves on the other (workflows-core:addressing§3,resolve-keystep 1). The kind gate is step 1b's, and it is taken on what the resolved folder holds.status: found→ carry itspath,kindandkeyforward;ambiguous→ stop, naming every match and@<path>as the way through.absentis a graceful stop, not a folder to create —/epicspartitions a PRD folder that exists and creates no PRD folder of its own:
Every command that stop names creates the folder it claims to, and none of them is a command this one would then refuse:EPICS_NOT_FOUND: no folder found for <ADDRESS> under $SPECS_PATH/specifications/ (every level addressing.md §3 bounds, plus §5's legacy fallback) — check the address. /epics partitions an existing PRD folder and creates none. A PRD folder is created by /product-workflows:idea <KEY> or /product-workflows:create-prd <KEY> on the idea route, and by /product-workflows:brd-split on its parent BRD on the BRD route; an EPIC- folder is created by this command and by no other, so an Epic address that resolves to nothing was never drafted here./ideaand/create-prdeach writePRD-<KEY>-<slug>/on their first write, and/brd-splitcarves thePRD-slice — all threePRD-folders that pass step 1a.
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 · +21 lines · +37 tokens per session b40fdc0aa55a
- 1mo ago Changed · +8 lines 84ae1d7e6690
- 1mo ago Changed · +8 lines 0c25ff28174f
- 2mo ago Changed · +2 lines 80d4cb1c6a19
- 2mo ago Changed · -2 lines · +26 tokens per session 3459ce640d1a
- 2mo ago Changed · +185 lines · +83 tokens per session 0bace008e3a4
- 2mo ago First seen · 763 lines · 47 tokens per session scan A d45114bbb5d4
epics is a command published in the GitHub repository ihudak/ihudak-claude-plugins (2 stars, last pushed 1mo ago), licensed MIT. It adds 193 tokens to every session and 22,068 once invoked, about $0.0008 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.
epics compared with commands from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| epicsihudak/ihudak-claude-plugins | Command | 2 | 1mo ago | MIT | A | 193 | Claude Code |
| battlecardphuryn/pm-skills | Command | 28k | 2d ago | MIT | A | 19 | Claude Code |
| memorizelucasrosati/claude-code-memory-setup | Command | 1.1k | 21d ago | MIT | A | 0 | Claude Code |
| watchMarcel-Bich/marcel-bich-claude-marketplace | Command | 12 | 2d ago | MIT | A | 11 | Claude Code |
| opsfrankxai/agentic-creator-os | Command | 12 | 2d ago | Apache-2.0 | A | 35 | Claude Code |
| value-prop-statementsstefanoskarakasis/Product-Marketing-Skills | Command | 11 | 2d ago | MIT | A | 16 | Claude Code |
| commitjoaquimscosta/arkhe-claude-plugins | Command | 22 | 26d ago | MIT | A | 11 | Claude Code |