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.
npx agentmods add instructions/dassianinc/dassian-adt/claude-mdgit clone --depth 1 https://github.com/DassianInc/dassian-adtWrote 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/dassianinc/dassian-adt/claude-md)<a href="https://agentmods.dev/instructions/dassianinc/dassian-adt/claude-md"><img src="https://agentmods.dev/badge/instructions/dassianinc/dassian-adt/claude-md.svg" alt="Measured on agentmods" 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 | $0.02489 | $0.02489 |
| Opus 5 | $0.01244 | $0.01244 |
| Sonnet 5 | $0.00498 | $0.00498 |
| Haiku 4.5 | $0.00249 | $0.00249 |
Grade A, and why
dassian-adt CLAUDE.md scanned grade A with 1 finding 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
curl -H "Authorization: Bearer $TOKEN" \ How it starts
The opening of the file, as written. The whole thing — 163 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md
This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.
Commands
npm run build # Compile TypeScript → dist/
npm test # Unit tests only (~180 tests, no SAP needed, <3s)
npm run test:coverage # Unit tests with coverage report
npm run test:live # Integration tests (needs SAP env vars)
npm run test:e2e # End-to-end write lifecycle (create → write → activate → delete)
npm run dev # Launch MCP Inspector for interactive tool testing
Run a single test file:
npx jest src/__tests__/unit/urlBuilder.test.ts
npx jest src/__tests__/unit/errors.test.ts
After any source change: npm run build — the MCP server runs from dist/, not src/.
Architecture
Request Flow
index.ts (AbapAdtServer)
→ handler.validateAndHandle(toolName, args) ← centralized required-field check
→ handler.handle(toolName, args) ← switch to concrete method
→ this.withSession(() => adtclient.xxx()) ← auto-reconnect wrapper
index.ts registers all handlers, wires elicitation/notify/sampling callbacks, and dispatches every tools/call to the correct handler's validateAndHandle. No tool routing logic lives outside index.ts.
Handler Hierarchy
All 8 handlers extend BaseHandler (src/handlers/BaseHandler.ts), which provides:
withSession(fn)— wraps every ADT call; detects session expiry (401, ambiguous 400) and re-logins transparentlyvalidateAndHandle(toolName, args)— checks JSON schemarequiredfields before any handler code runselicitForm / elicitChoice / confirmWithUser— MCP elicitation forms injected fromindex.tsnotify(msg, level)— progress messages visible in Claude Code's UIaskClaude(system, user)— sampling to ask Claude a question without interrupting the userfail(msg)— throws McpError; never returns
Lock → Write → Unlock Pattern
Critical invariant: lock, write, and unlock for any object MUST happen inside a single withSession(async () => { ... }) block — never in separate withSession calls.
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 · 163 lines · 2,489 tokens per session scan A a85a271fccd2
dassian-adt CLAUDE.md is an instructions file published in the GitHub repository DassianInc/dassian-adt (9 stars, last pushed today), licensed MIT. It adds 2,489 tokens to every session, about $0.0124 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other instructions, from other repositories
sap-adt-mcp CLAUDE.md
Claude Code instructions for engoetz/sap-adt-mcp, covering claude.md, what this is, commands, architecture and invariants that are easy to break.
sap-adt-mcp AGENTS.md
AGENTS.md instructions for engoetz/sap-adt-mcp, covering sap adt python — agent instructions, available mcp tools, abap development workflow, first-time setup (once per environment) and before editing any abap object.
vibing-steampunk CLAUDE.md
Claude Code instructions for oisee/vibing-steampunk, covering claude.md, current priorities, 1. graph engine (pkg/graph/) — feature-complete, 2. debugger — phase 1 shipped, #2 closed 2026-09-02 and 3. open issues.
vibing-steampunk copilot-instructions.md
Copilot instructions for oisee/vibing-steampunk, covering copilot instructions for vsp, project, build, test, lint, build and run all unit tests.
mcp-abap-adt CLAUDE.md
Claude Code instructions for fr0ster/mcp-abap-adt, covering mcp abap adt - development guide, testing, integration tests, soft mode (mass run) — save full log and test configuration.
aibap.mcp CLAUDE.md
Claude Code instructions for Hochfrequenz/aibap.mcp, covering claude.md, project overview, build & run, testing and workflow.