What is vibing-steampunk CLAUDE.md?

Repository guidance for vsp, a Go-based MCP server and command-line tool for SAP development tools, focused on its graph engine and debugger plans.

Use it when investigating or modifying the graph engine, debugger, command-line tools, or project documentation.

It gives an AI coding assistant the project's current priorities, architecture notes, and open work so changes fit the repository's direction.

How oisee/vibing-steampunk configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to oisee/vibing-steampunk. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/oisee/vibing-steampunk/main/CLAUDE.md

Clone the repo

git clone --depth 1 https://github.com/oisee/vibing-steampunk

Made for: Claude Code.

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/instructions/oisee/vibing-steampunk/claude-md/github.svg)](https://agentmods.dev/instructions/oisee/vibing-steampunk/claude-md)

Your own site

<a href="https://agentmods.dev/instructions/oisee/vibing-steampunk/claude-md"><img src="https://agentmods.dev/badge/instructions/oisee/vibing-steampunk/claude-md/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/instructions/oisee/vibing-steampunk/claude-md"><img src="https://agentmods.dev/badge/instructions/oisee/vibing-steampunk/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 3,517 This file is loaded in full into every session.

When invoked 3,517 The same file — it is already loaded in full.

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	$0.03517	$0.03517
Opus 5.5	$0.01407	$0.01407
Sonnet 5.5	$0.00703	$0.00703
Haiku 4.5	$0.00352	$0.00352

Measured 1mo ago against content hash ac873a9c46a1, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

vibing-steampunk CLAUDE.md 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.

CLAUDE.md · 191 lines

How it starts

The opening of the file, as written. The whole thing — 191 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md

vsp — Go-native MCP server and CLI for SAP ABAP Development Tools (ADT).

Doc intent: CLAUDE.md = what an agent needs in every session. README.md = user onboarding. docs/dev-notes.md = background and history by area. reports/ = research. contexts/ = session handoff. agenda/ = what is open and what was decided (AGENDA.md is the living board).

Shared knowledge base: ../sap-kb/ maps vsp against its SAP-protocol siblings (open-rfc-go, open-diag-go-pro, sap-sso-trace). vsp owns pkg/sapcompress (decode), pkg/datacluster, the ADT transport and the ZADT_VSP bridge.

Current work and priorities are on the project's Trail Map, in agenda/AGENDA.md, and in the GitHub issues. They are not in this file, because a status line here goes stale.

Build & Test

go build -o vsp ./cmd/vsp               # Build
go test ./...                            # Unit tests
go test -tags=integration -v ./pkg/adt/  # Integration (needs SAP or the OSD emulator)
make build-all-all                       # Release build, all 6 platforms (build-all builds only 3)

Key flags: --mode focused|expert|hyperfocused, --read-only, --allowed-packages "Z*", --block-free-sql, --disabled-groups 5THD

CI on every PR:

Blocking: build, vet, tests (-race, shuffled), the correctness lint on new code (.github/ci/lint.sh gate), and the leak scan.
Advisory: full lint, complexity and token drift (make metrics), fuzz, and an integration run against the OSD SAP emulator (.github/workflows/osd-integration.yml, versions pinned with committed sha256).
Hooks: opt-in, enabled with git config core.hooksPath .githooks. The pre-push hook runs the lint gate and the leak scan.

Agents and budget modes

How to run codex and Claude subagents (commands, sandboxes, prompt shapes, the review loop) is in the shared playbook oisee/agent-playbook (private; gh repo clone oisee/agent-playbook), especially critics-and-executors and review-loop. Alice sets the mode in chat; without a word from her it is normal.

Read the full file on GitHub · 191 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 · -94 lines · -1,172 tokens per session ac873a9c46a1
1mo ago Changed · +8 lines · +272 tokens per session 2cd0cc3568a1
1mo ago Changed · +2 lines · +129 tokens per session f70694ad3970
2mo ago Changed · +1 lines · +96 tokens per session e0a3019a392d
2mo ago Changed · +5 lines · +172 tokens per session e3c50f27d842
2mo ago Changed · +38 lines · +934 tokens per session 25b178dc637e
2mo ago First seen · 231 lines · 3,086 tokens per session scan A 4b1a72636d6b

Subscribe to this mod's changes

vibing-steampunk CLAUDE.md is an instructions file published in the GitHub repository oisee/vibing-steampunk (522 stars, last pushed 15d ago), licensed MIT. It adds 3,517 tokens to every session, about $0.0141 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 2026-08-30.

abap adt mcp vibe-coding

vibing-steampunk CLAUDE.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
vibing-steampunk CLAUDE.mdoisee/vibing-steampunk	Instructions file	522	15d ago	MIT	A	3,517	Claude Code
vibe-coding-prompt-template backend.instructions.mdKhazP/vibe-coding-prompt-template	Instructions file	3.2k	1mo ago	MIT	A	139	GitHub Copilot
vscode buildNext.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	9,719	GitHub Copilot
next.js AGENTS.mdvercel/next.js	Instructions file	143k	today	MIT	A	7,461	Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchain	Instructions file	149k	yesterday	MIT	A	4,680	Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	5,516	GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	3,093	GitHub Copilot

vibing-steampunk: Instructions file for Claude Code