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/mrnaqa/sourceweave-web-search/agents-mdgit clone --depth 1 https://github.com/MRNAQA/sourceweave-web-searchWrote 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/mrnaqa/sourceweave-web-search/agents-md)<a href="https://agentmods.dev/instructions/mrnaqa/sourceweave-web-search/agents-md"><img src="https://agentmods.dev/badge/instructions/mrnaqa/sourceweave-web-search/agents-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 | $0.00995 | $0.00995 |
| Opus 5 | $0.00498 | $0.00498 |
| Sonnet 5 | $0.00199 | $0.00199 |
| Haiku 4.5 | $0.00100 | $0.00100 |
Grade A, and why
sourceweave-web-search 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 3d 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 — 41 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Agent Notes
Canonical Files
- If docs conflict, trust
pyproject.toml,src/sourceweave_web_search/*.py, and.github/workflows/*.ymlover prose.CONTRIBUTING.mdand some repo-local skill text lag current code. src/sourceweave_web_search/tool.pyis the source of truth.cli.pyandmcp_server.pyare thin wrappers around it.artifacts/sourceweave_web_search.pyis generated fromsrc/sourceweave_web_search/tool.py. Rebuild withuv run sourceweave-build-openwebui; verify drift withuv run sourceweave-build-openwebui --check.- The public MCP contract is exactly
search_web(query, domains?, urls?),read_pages(page_ids, focus?), andread_urls(urls, focus?). Some older repo prose still mentions only two tools; trustsrc/sourceweave_web_search/mcp_server.pyandtests/test_packaging.py.
Runtime Defaults
- Dev install:
uv sync --locked --group dev. - Package and test defaults target host-side services:
http://127.0.0.1:19080/search?format=json&q=<query>,http://127.0.0.1:19235, andredis://127.0.0.1:16379/2. - The compose
mcpservice uses container-network endpoints instead:http://searxng:8080/search?format=json&q=<query>,http://crawl4ai:11235, andredis://redis:6379/2. Do not call those the defaults unless you are inside the compose container. SEARXNG_BASE_URLis normalized to a template withformat=jsonandq=<query>; preserve that behavior when touching config handling.- Usual local dependency stack:
cp .env.example .env && docker compose up -d redis crawl4ai searxng. docker compose up -d mcpbuilds and runs the publishable image and exposeshttp://127.0.0.1:18000/mcp. Runninguv run sourceweave-search-mcp --transport streamable-httpuses port8000.
Verification
- If you touch runtime, packaging, or release surfaces, mirror the
release-gateorder:uv run python scripts/sync_release_metadata.py --checkuv run sourceweave-build-openwebui --checkuv run ruff check src testsuv run pyright src testsuv run pytest tests/test_config.py tests/test_packaging.py tests/test_tool.py -m "not integration"
- For a quick local typecheck, use
uvx pyright src tests; keepuv run pyright src testsas the deterministic gate. tests/test_phase4.pyis a separate manual Crawl4AI HTTP check; it is excluded frompyrightand the default deterministic CI gate.
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.
- 3d ago First seen · 41 lines · 995 tokens per session scan A 93db1f2daadf
sourceweave-web-search AGENTS.md is an instructions file published in the GitHub repository MRNAQA/sourceweave-web-search (2 stars, last pushed 4mo ago), licensed MIT. It adds 995 tokens to every session, about $0.0050 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 2026-08-31.
Other instructions, from other repositories
wet-mcp AGENTS.md
Instructions for n24q02m/wet-mcp, covering agents.md - wet-mcp, cau truc, lenh thuong dung, mise shortcuts and cau hinh quan trong.
searxng-mcp AGENTS.md
Instructions for TadMSTR/searxng-mcp, covering agents.md — searxng-mcp, what it does, structure, dependencies and build and run.
wet-mcp CLAUDE.md
Instructions for n24q02m/wet-mcp, covering wet-mcp, cau truc, lenh thuong dung, mise shortcuts and cau hinh quan trong.
llm-context.py CLAUDE.md
Instructions for cyberchitta/llm-context.py, covering claude.md, working notes (gitignored) and draining the field notes.
openrouter-mcp-multimodal AGENTS.md
AGENTS.md instructions for stabgan/openrouter-mcp-multimodal, covering agent instructions, before you ship, releasing (read this before publishing), short version and version files (must all match package.json).
seekstone CLAUDE.md
Instructions for shaqmughal/seekstone, covering claude.md, what this repo is, commands, the harness itself (run after npm install) and architecture.