What is shipwrights-craft-agent?

A project-specific agent generator for Claude Code. It scans a project or accepts a description, then creates Markdown agent files in .claude/agents/ so Claude Code can use specialists familiar with that project's conventions.

Use it to detect useful specialist agents, create one from a description, list existing crafted agents, or remove a previously created agent.

It avoids repeatedly giving every agent the same details about a codebase. The generated files preserve project layout, framework choices, terminology, and preferred patterns in one place.

shipwrights-craft-agent — Skill for Claude Code and Codex by shipwrigh

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.

Any agent

npx skills add shipwrights/core --skill shipwrights-craft-agent

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

Your own site

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

Per session 73 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 2,023 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	$0.00073	$0.02023
Opus 5	$0.00036	$0.01012
Sonnet 5	$0.00015	$0.00405
Haiku 4.5	$0.00007	$0.00202

Measured 6d ago against content hash 1eee8e568254, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

shipwrights-craft-agent 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 6d 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-craft-agent/SKILL.md · 169 lines

How it starts

The opening of the file, as written. The whole thing — 169 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/shipwrights-craft-agent — generate project-specific agents

Generic bundled agents (product-owner-strategist, node-backend-systems-architect, …) carry every team's project context in the prompt at runtime. That works, but at scale it's expensive and noisy. Project-specific agents bake the conventions in once: directory layout, framework choice, in-house terminology, idiomatic patterns. The orchestrator (and you, ad-hoc) get a sharper specialist for the cost of one well-crafted markdown file.

This skill writes those files.

Inputs

/shipwrights-craft-agent — auto-detect mode. Scan the project, propose a set of agents, ask which to generate.
/shipwrights-craft-agent <slug> "<description>" — explicit mode. Draft a single agent the user described in their own words.
/shipwrights-craft-agent --list — show all agents currently at .claude/agents/<name>.md, with which are bundled vs user-crafted.
/shipwrights-craft-agent --remove <slug> — delete a previously-crafted agent (refuses to remove bundled agents).

Workflow — auto-detect mode

1. Preflight

.shipwrights.yml exists (this skill is for already-initialised projects). If not: tell user to run /shipwrights-init first.
.claude/agents/ exists (created by /shipwrights-init). If not: tell user to run /shipwrights-upgrade first.

2. Scan the project

Run via Bash (one-liner using the lib helper) and capture the JSON:

node -e "import('@shipwrights/core/lib/project-signals.mjs').then(m => console.log(JSON.stringify(m.detectProjectSignals(process.cwd()))))"

Or read it via lib/project-signals.mjs directly. Surface the headline to the user:

Detected:
  Project:    arms-invoice-frontend-pro
  Stack:      vue3 + pinia + vue-router + vue-quill + apexcharts + pdfmake
  Build:      vite
  Tests:      vitest
  Styling:    tailwindcss
  Conv:       src/components, src/stores, src/services, src/router
  Domain:     invoice, finance, quickbooks

3. Propose agents

Read the full file on GitHub · 169 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.

6d ago First seen · 169 lines · 73 tokens per session scan A 1eee8e568254

Subscribe to this mod's changes

shipwrights-craft-agent is a skill published in the GitHub repository shipwrights/core (2 stars, last pushed 1mo ago), licensed MIT. It adds 73 tokens to every session and 2,023 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.

Building agents Claude Code Orchestration agentic-coding ai-agents claude-code-plugin epic-management

great_cto

Use when the CTO describes a feature, task, or project goal. Orchestrates the full SDLC pipeline automatically based on project type.

avelikiy/great_cto · 32 tokens

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

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.