Borrowing it
Nothing to install: this file belongs to zoharbabin/due-diligence-agents. 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/zoharbabin/due-diligence-agents/main/CLAUDE.mdgit clone --depth 1 https://github.com/zoharbabin/due-diligence-agentsWrote 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/zoharbabin/due-diligence-agents/claude-md)<a href="https://agentmods.dev/instructions/zoharbabin/due-diligence-agents/claude-md"><img src="https://agentmods.dev/badge/instructions/zoharbabin/due-diligence-agents/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/zoharbabin/due-diligence-agents/claude-md"><img src="https://agentmods.dev/badge/instructions/zoharbabin/due-diligence-agents/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 | $0.03693 | $0.03693 |
| Opus 5 | $0.01847 | $0.01847 |
| Sonnet 5 | $0.00739 | $0.00739 |
| Haiku 4.5 | $0.00369 | $0.00369 |
Grade A, and why
due-diligence-agents 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 11d 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 — 179 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Due Diligence Agent SDK
Forensic M&A due diligence pipeline — analyzes contract data rooms with specialist AI agents, enforces quality gates, produces cross-domain HTML + Excel reports.
Commands
pip install -e ".[dev,pdf]" # Dev install
pytest tests/unit/ -x -q && mypy src/ --strict && ruff check src/ tests/ # Quality gate (run after EVERY change)
dd-agents run path/to/deal-config.json # Run pipeline
dd-agents run path/to/deal-config.json --dry-run # Preview steps
dd-agents validate path/to/deal-config.json # Validate config
Architecture Map
All source lives under src/dd_agents/. Each package has one job:
| Package | Purpose | Entry point |
|---|---|---|
orchestrator/ |
38-step async pipeline with checkpoint/resume | engine.py → PipelineEngine.run() |
agents/ |
Specialist agent runners + extensible registry | base.py → BaseAgentRunner (abstract) |
agents/prompts/ |
Built-in prompt prose as editable markdown (specialists, synthesis, search, auto-config) | loader.py → load_builtin_specialist() |
models/ |
Pydantic v2 schemas for all data | __init__.py re-exports ~100 classes |
reporting/ |
HTML + Excel report generation | html_base.py → SectionRenderer (abstract) |
hooks/ |
Pre/post tool-use guards (allow/block) | pre_tool.py → guard functions |
persistence/ |
Three-tier data lifecycle | tiers.py → TierManager |
knowledge/ |
Deal knowledge base (compounds across runs) | base.py → DealKnowledgeBase |
customization/ |
User-editable agent personas/profiles (dd-config/) |
loader.py → resolve_chain(), profiles/*.md |
extraction/ |
PDF/Office text extraction pipeline | pipeline.py → fallback chain |
entity_resolution/ |
Cross-document name deduplication | matcher.py → EntityResolver |
inventory/ |
Data room scanning and classification | discovery.py, subjects.py |
validation/ |
QA audit + DoD checks (fail-closed) | dod.py, numerical_audit.py |
search/ |
Contract search with citation verification | runner.py → SearchRunner |
tools/ |
MCP server + custom tool implementations | mcp_server.py |
chat/ |
Interactive chat mode | engine.py |
cli.py |
Click CLI command groups | dd-agents entry point |
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.
- 11d ago First seen · 179 lines · 3,693 tokens per session scan A ea7262463a9a
due-diligence-agents CLAUDE.md is an instructions file published in the GitHub repository zoharbabin/due-diligence-agents (102 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 3,693 tokens to every session, about $0.0185 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 2026-08-30.
Other instructions, from other repositories
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.