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/deedy5/ddgs/agents-mdgit clone --depth 1 https://github.com/deedy5/ddgsWhat 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 | $0.01821 | $0.01821 |
| Opus 5 | $0.00911 | $0.00911 |
| Sonnet 5 | $0.00364 | $0.00364 |
| Haiku 4.5 | $0.00182 | $0.00182 |
Grade A, and why
ddgs AGENTS.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 2d 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 — 161 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md — Guide for Coding Agents
Project Overview
ddgs (Dux Distributed Global Search) is a Python metasearch library that aggregates results from diverse web search services. It provides a DDGS class with methods like text(), images(), news(), videos(), books(), and extract().
- Python: >=3.10 (tested up to 3.14)
- Dependencies:
click,primp,lxml - Package layout:
ddgs/(source),tests/(tests), optional extras:api(FastAPI),mcp(stdio)
Build / Lint / Test Commands
# Setup (creates .venv, installs dev deps)
python3 -m venv .venv
.venv/bin/pip install -e .[dev]
# Lint (ruff check + mypy type-check)
.venv/bin/ruff check --fix
.venv/bin/mypy --install-types --non-interactive .
# Format
.venv/bin/ruff format
# Run all tests
.venv/bin/pytest
# Run a single test file
.venv/bin/pytest tests/ddgs_test.py
# Run a single test function
.venv/bin/pytest tests/ddgs_test.py::test_text_search
# Make targets (use .venv/bin/python internally)
make lint
make format
make test
Important: Tests make real HTTP requests and include a 2-second pause between tests (autouse fixture). Tests are slow by nature.
Engine Architecture
Each search engine is a subclass of BaseSearchEngine[T] in ddgs/engines/. Key concepts:
ENGINESdict inddgs/engines/__init__.pymaps category → {name → engine class}.DDGS._search()spawns threads viaThreadPoolExecutor, callingengine.search()in parallel.- Results are deduplicated and ranked by
ResultsAggregatorandSimpleFilterRanker. BaseSearchEnginehandles HTTP requests, HTML parsing (lxml), and XPath-based result extraction.- Engine instances are cached per
DDGSinstance in_engines_cache.
Pre-commit Hooks
Pre-commit is managed via prek (not pre-commit). Install with prek install. Hooks run on commit:
- Standard checks (large files, AST, trailing whitespace, etc.)
ruff check --fixruff formatmypy --install-types --non-interactive .
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.
- 2d ago First seen · 161 lines · 1,821 tokens per session scan A 162a79aaa6d4
ddgs AGENTS.md is an instructions file published in the GitHub repository deedy5/ddgs (2,925 stars, last pushed 6d ago), licensed MIT. It adds 1,821 tokens to every session, about $0.0091 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
cs CLAUDE.md
Instructions for boyter/cs, covering claude.md, project overview, build & test commands, architecture and query pipeline (pkg/search/).
ketch AGENTS.md
Instructions for 1broseidon/ketch, covering ketch — architecture, module layout, design principles, mcp server and quality standards.
Xapiand AGENTS.md
Instructions for Kronuz/Xapiand, covering agents.md — working in the xapiand codebase, first, the big split: own code vs. vendored, where things live, build & toggles and verifying changes end-to-end (the docs are a test suite).
meilisearch-mcp CLAUDE.md
Instructions for meilisearch/meilisearch-mcp, covering claude.md, 🚨 important: development workflow guidelines, 🔄 fresh start protocol, 🎯 focused development rules and 📋 task assessment phase.
ketch CLAUDE.md
Instructions for 1broseidon/ketch, covering ketch, architecture, build & test, output format and output flags (all commands).
moraine AGENTS.md
Instructions for eric-tramel/moraine, covering repository guidelines, project structure & module organization, build, test, and development commands, coding style & naming conventions and testing guidelines.