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/jerryliu369/agent-web-search/agents-mdgit clone --depth 1 https://github.com/JerryLiu369/agent-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/jerryliu369/agent-web-search/agents-md)<a href="https://agentmods.dev/instructions/jerryliu369/agent-web-search/agents-md"><img src="https://agentmods.dev/badge/instructions/jerryliu369/agent-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 5.1 | $0.00207 | $0.00207 |
| Opus 5 | $0.00103 | $0.00103 |
| Sonnet 5 | $0.00041 | $0.00041 |
| Haiku 4.5 | $0.00021 | $0.00021 |
Grade A, and why
agent-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 6d 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.
What it actually says
Agent instructions
Read ARCHITECTURE.md before changing transports, configuration,
authentication, deployment, providers, tool schemas, or public entry points.
Non-negotiable invariants:
- Keep one
SearchEngineand one shared MCP server definition. - Keep
agent-web-search-mcpas the single MCP command; stdio is its default and HTTP is a transport mode. - Keep MCP HTTP stateless, JSON-response based, and authenticated by default.
- Keep runtime configuration environment-only; do not add an application configuration file.
- Keep stdio and HTTP tool schemas, result shapes, and error semantics equal.
- Keep provider credentials server-side and out of MCP tool arguments.
- Keep deployment-specific code limited to thin launch adapters.
- Do not add REST, OAuth, multi-tenancy, or persistent sessions without an explicit architecture decision from the project owner.
Update ARCHITECTURE.md in the same change whenever an approved decision
changes one of these invariants.
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.
- 6d ago First seen · 22 lines · 207 tokens per session scan A 2999aaac285f
agent-web-search AGENTS.md is an instructions file published in the GitHub repository JerryLiu369/agent-web-search (6 stars, last pushed 2d ago), licensed MIT. It adds 207 tokens to every session, about $0.0010 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
mcp-deep-search CLAUDE.md
Claude Code instructions for just-every/mcp-deep-search, covering claude.md, project overview, core modules & files, commands and development.
SearChat CLAUDE.md
Claude Code instructions for yokingma/SearChat, covering claude.md, project overview, architecture, monorepo structure and key technologies.
airweave CLAUDE.md
Instructions for airweave-ai/airweave, covering claude.md, what is airweave?, architecture, common commands and local development (docker).
social_dive CLAUDE.md
Claude Code instructions for krishddd/social_dive, covering social dive — developer conventions, language & environment, architecture rules, version sync and testing.
ai-dial-core CLAUDE.md
Claude Code instructions for epam/ai-dial-core, covering claude.md, build & run, set credentials via environment variables, build (skip tests) and run all tests.
ai AGENTS.md
AGENTS.md instructions for vercel/ai, covering agents.md, project overview, repository structure, key directories and core package dependencies.