craft-project-explore

craft-project-explore is a skill for Claude Code, Codex from derjochenmeyer/claude-code-craft. It costs 24 tokens per session (483 once invoked), scanned A, original, MIT.

A project-specific discovery guide for finding integrations and Claude Code features that match a codebase's languages, frameworks, services, and workflow.

In plain words
What is it for?
Identifying suitable MCP tools and integrations for a project's technology stack and recurring development tasks, with links to supporting documentation.
Why use it?
It filters out generic suggestions by first examining the project's files, backlog, and recent Git history. This makes the resulting recommendations more relevant.

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/derjochenmeyer/claude-code-craft/craft-project-explore
Any agent
npx skills add derjochenmeyer/claude-code-craft --skill craft-project-explore
Clone the repo
git clone --depth 1 https://github.com/derjochenmeyer/claude-code-craft

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.

agentmods badge for craft-project-explore

README.md
[![agentmods](https://agentmods.dev/badge/skills/derjochenmeyer/claude-code-craft/craft-project-explore.svg)](https://agentmods.dev/skills/derjochenmeyer/claude-code-craft/craft-project-explore)
Your own site
<a href="https://agentmods.dev/skills/derjochenmeyer/claude-code-craft/craft-project-explore"><img src="https://agentmods.dev/badge/skills/derjochenmeyer/claude-code-craft/craft-project-explore.svg" alt="Measured on agentmods" height="20"></a>
Per session 24 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 483 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 $0.00024 $0.00483
Opus 5 $0.00012 $0.00242
Sonnet 5 $0.00005 $0.00097
Haiku 4.5 $0.00002 $0.00048

Measured 3d ago against content hash b0524258dcf5, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

craft-project-explore 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 3d 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/craft-project-explore/SKILL.md · 68 lines

What it actually says

craft-project-explore

Discover MCPs and Claude Code integrations that are actually relevant to this project -- not a generic list, a filtered one based on detected stack and workflow patterns.

Behavior

Step 1: Detect project context

Read, in order (skip files that do not exist):

  • package.json
  • requirements.txt
  • composer.json
  • CLAUDE.md
  • .craft/PROJECT_STATE.md
  • .craft/BACKLOG.md

Run git log --oneline -10 to detect recent workflow patterns.

From these sources, extract:

  • Languages and runtimes
  • Frameworks and major dependencies
  • External services mentioned (databases, APIs, deployment targets)
  • Recurring workflow patterns from backlog and git history

Step 2: Fetch current integrations

Fetch:

  • https://modelcontextprotocol.io/docs/tools/sampling (or the MCP registry index if available)
  • https://docs.anthropic.com/en/docs/claude-code/mcp for official Claude Code MCP docs

Step 3: Cross-reference and output

Only include tools that match the detected stack. Do not list generic tools unless they address a pattern seen in the backlog or git history. Cite the source URL for each recommendation.

## Opportunities for [project name]

Based on detected stack: [comma-separated list]

| Tool / Integration | What it enables for this project | Install | Effort |
|-------------------|----------------------------------|---------|--------|
| [name]            | [specific to detected needs]     | [exact command or URL] | low / medium / high |

Sort by relevance to the detected stack -- most relevant first.

Below the table:

Sources: [URLs fetched]

Want me to install any of these? Reply with numbers.

Rules

  • Only recommend real tools with real, verifiable install commands.
  • If a tool appears in the registry but has no stable install path, note that instead of guessing.
  • Do not pad the table with generic tools to make it look longer.
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. 3d ago First seen · 68 lines · 24 tokens per session scan A b0524258dcf5

Subscribe to this mod's changes

craft-project-explore is a skill published in the GitHub repository derjochenmeyer/claude-code-craft (2 stars, last pushed 4mo ago), licensed MIT. It adds 24 tokens to every session and 483 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

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

chat-perf

Run chat perf benchmarks and memory leak checks against the local dev build or any published VS Code version. Use when investigating chat rendering regressions, validating perf-sensitive changes to chat UI, or checking for memory leaks in the chat response pipeline.

microsoft/vscode · 51 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