Borrowing it
Nothing to install: this file belongs to sangvucitek/MCP_SAP. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/sangvucitek/MCP_SAP/main/CLAUDE.mdgit clone --depth 1 https://github.com/sangvucitek/MCP_SAPWrote 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/instructions/sangvucitek/mcp_sap/claude-md)<a href="https://agentmods.dev/instructions/sangvucitek/mcp_sap/claude-md"><img src="https://agentmods.dev/badge/instructions/sangvucitek/mcp_sap/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.
<a href="https://agentmods.dev/instructions/sangvucitek/mcp_sap/claude-md"><img src="https://agentmods.dev/badge/instructions/sangvucitek/mcp_sap/claude-md.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 | $0.01988 | $0.01988 |
| Opus 5.5 | $0.00795 | $0.00795 |
| Sonnet 5.5 | $0.00398 | $0.00398 |
| Haiku 4.5 | $0.00199 | $0.00199 |
Grade A, and why
MCP_SAP 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 2mo 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 — 168 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 = dev context. README.md = user onboarding. reports/ = research/history. contexts/ = session handoff.
Current Priorities
1. Graph Engine (pkg/graph/) — In Progress
Sequence: unify existing dep logic → SQL/ADT adapters → impact/path queries.
- Done: core types, parser dep extraction, boundary analyzer (11 tests)
- Pending: SQL adapters (CROSS/WBCROSSGT/D010INC), ADT adapters, unify
cli_deps.go+cli_extra.go+ctxcomp/analyzer.go - Design: 002, 003
2. GUI Debugger (Issue #2) — Strategic
Plan: MCP debug sessions → DAP → Web UI. ADT REST API mapped from CL_TPDA_ADT_RES_APP. Design: 001
3. Open Issues
- #88 Lock handle bug (EditSource/WriteSource) — real user report
- #55 RunReport in APC — architectural limit
- #46, #45 Sync script — low effort
Build & Test
go build -o vsp ./cmd/vsp # Build
go test ./... # Unit tests
go test -tags=integration -v ./pkg/adt/ # Integration (needs SAP)
make build-all # 9 platforms
Key flags: --mode focused|expert|hyperfocused, --read-only, --allowed-packages "Z*", --disabled-groups 5THD
Codebase
cmd/vsp/ CLI entry + 28 commands
internal/mcp/
handlers_*.go Domain handlers (read, edit, debug, graph, ...)
tools_register.go Registration + mode logic
tools_focused.go Focused mode whitelist
handlers_universal.go Hyperfocused single-tool (SAP)
pkg/
adt/ ADT client (HTTP, CSRF, sessions, all SAP ops)
graph/ Dependency graph engine (in progress)
ctxcomp/ Context compression (dep resolution for read)
abaplint/ ABAP lexer + parser (91 statements, 8 lint rules)
dsl/ Fluent API, YAML workflows, batch ops
cache/ In-memory + SQLite
scripting/ Lua engine
llvm2abap/ LLVM→ABAP (research)
wasmcomp/ WASM→ABAP (research)
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.
- 2mo ago First seen · 168 lines · 1,988 tokens per session scan A afbf60ef68cd
MCP_SAP CLAUDE.md is an instructions file published in the GitHub repository sangvucitek/MCP_SAP (0 stars, last pushed 6mo ago), licensed MIT. It adds 1,988 tokens to every session, about $0.0080 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.
MCP_SAP CLAUDE.md compared with instructions from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| MCP_SAP CLAUDE.mdsangvucitek/MCP_SAP | Instructions file | 0 | 6mo ago | MIT | A | 1,988 | Claude Code |
| 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 |
| deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness | Instructions file | 274k | 2d ago | MIT | A | 4,313 | Codex, OpenCode |