What is shipwrights-epic?

A workflow for taking a planned large change, called an epic, from clarification to a pull request. It follows the stages in the project's .shipwrights.yml file and coordinates specialist coding agents.

Use it to refine an epic, split it into work, assign parts to agents on scratch branches, combine their changes, run checks, and open a pull request.

It removes the need to manage each stage, branch, specialist, check, and status update by hand. It also gives unfinished epics a defined place to resume.

shipwrights-epic — Skill for Claude Code and Codex by shipwrights: A workflow for taking a planned large change, called…

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/shipwrights/core/shipwrights-epic

Any agent

npx skills add shipwrights/core --skill shipwrights-epic

Clone the repo

git clone --depth 1 https://github.com/shipwrights/core

Made for: Claude Code, Codex.

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/shipwrights/core/shipwrights-epic.svg)](https://agentmods.dev/skills/shipwrights/core/shipwrights-epic)

Your own site

<a href="https://agentmods.dev/skills/shipwrights/core/shipwrights-epic"><img src="https://agentmods.dev/badge/skills/shipwrights/core/shipwrights-epic.svg" alt="Measured on agentmods" height="20"></a>

Per session 71 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 1,646 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.

Model	Per session	Once invoked
Fable 5.1	$0.00071	$0.01646
Opus 5	$0.00036	$0.00823
Sonnet 5	$0.00014	$0.00329
Haiku 4.5	$0.00007	$0.00165

Measured 5d ago against content hash 4cf2c21ab7d9, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

shipwrights-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 5d 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/shipwrights-epic/SKILL.md · 108 lines

How it starts

The opening of the file, as written. The whole thing — 108 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/shipwrights-epic — drive an epic through the pipeline

You are the orchestrator. Your job is to walk an epic through the stages declared in .shipwrights.yml, spawning specialist agents at the right moments and integrating their work.

You never write code on the integration feature branch directly during the build stage — specialists do that on their scratch branches. You do write code when:

Slicing (writing the slice section into the epic file).
Integrating (rebasing scratch branches; resolving truly trivial conflicts; running guards).
Shipping (opening the PR; updating the epic status; updating the in-flight register).

Inputs

The user invokes this skill with one of:

An epic id (E-04-01, audit-h7, ops-12). If <state_dir>/<id>-*.md already exists, jump in at whatever stage that file's frontmatter status is at. If not, materialise it from the configured backlog source.
A description ("the password reset flash bug"). Match against existing epic files first, then against the backlog source's items by title.
No argument. Pick the next ready epic. Order: existing files at status: refined-or-later with all parents shipped → pickNext from the backlog source.

Pipeline

The pipeline is declared in .shipwrights.yml under the pipeline: key. You execute that pipeline literally — do not assume the default 7-stage shape; the consumer may have customized it.

For each stage in order:

Check skip conditions. Evaluate optional_when against the epic's frontmatter + tier. Skip if true.
Resolve owner(s). Each stage names one or more roles (or the literal orchestrator). Roles map to agents via roles[].agent in config.
Load the stage skill. By default the skill lives at skills/stages/<stage>.md in the plugin. The stage's skill: field can override.
Execute. Read the stage skill, follow its instructions for this stage. The stage skill is responsible for what happens; you (this entry skill) are responsible for which stage runs.
Update epic status. After successful stage completion, bump the epic's frontmatter status: to match the stage's output state.
Update the in-flight register. Stage transition is a register-update event.
Stop on escalation. If the stage returned an escalation rather than completion, stop and report to the user. Don't auto-advance through escalations.

Read the full file on GitHub · 108 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.

5d ago First seen · 108 lines · 71 tokens per session scan A 4cf2c21ab7d9

Subscribe to this mod's changes

shipwrights-epic is a skill published in the GitHub repository shipwrights/core (2 stars, last pushed 1mo ago), licensed MIT. It adds 71 tokens to every session and 1,646 once invoked, about $0.0004 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.

Git and workflow Orchestration Project management agentic-coding ai-agents claude-code claude-code-plugin epic-management

vertical-real-estate

Residential-proptech domain knowledge so architect / pm aren't naive when speccing real-estate products (listings, lead-crm, transaction-coordination, property-mgmt). Codifies MLS/IDX reality, listing status lifecycle + syndication canonical-source, long-cycle lead nurture, transaction-coordination as the high-pain…

avelikiy/great_cto · 99 tokens

product-economics

Does this product make money at a price someone will pay? Forces contribution margin, a price with a stated basis, and a bottom-up market size — each number labelled measured / assumed / unknown, so a guess can never be read as a calculation.

avelikiy/great_cto · 55 tokens

check-pr

Read-only inspection of a single GitHub PR lifecycle — checks CI, review threads, description sync, and mergeability, and returns PASS or FAIL with per-gate findings. Never invokes the merge button. Use when verifying a PR is ready to merge, polling lifecycle progress, checking mergeability, or babysitting a GitHub PR…

doodledood/manifest-dev · 74 tokens

anti-patterns

Catalogue of known SDLC anti-patterns that greatcto agents must actively reject when reviewing architecture, plans, code, or post-mortems. Used by architect (pre-impl), pm (planning), senior-dev (impl), l3-support (post-incident).

avelikiy/great_cto · 59 tokens

cost-model

Standardized cost-estimation framework for greatcto plans. Forces explicit LLM cost, infra cost, human-supervision time, and the (defensible) human-equivalent comparison. Output format is parsable by the board's /api/cost path — must follow exactly.