Borrowing it
Nothing to install: this file belongs to liustack/modsearch. 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/liustack/modsearch/main/AGENTS.mdgit clone --depth 1 https://github.com/liustack/modsearchWrote 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/liustack/modsearch/agents-md)<a href="https://agentmods.dev/instructions/liustack/modsearch/agents-md"><img src="https://agentmods.dev/badge/instructions/liustack/modsearch/agents-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/liustack/modsearch/agents-md"><img src="https://agentmods.dev/badge/instructions/liustack/modsearch/agents-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 | $0.01965 | $0.01965 |
| Opus 5.5 | $0.00786 | $0.00786 |
| Sonnet 5.5 | $0.00393 | $0.00393 |
| Haiku 4.5 | $0.00197 | $0.00197 |
Grade A, and why
modsearch AGENTS.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 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.
Runs shell commandslowCapability
Expected in a hook, worth knowing in a rule or an instructions file.
- **Hidden Windows children**: the core and standalone dsh plugin each own one child-process wrapper that forces `windowsHide: true`. A contract test rejects direct `child_process` access anywhere else in shipped code. How it starts
The opening of the file, as written. The whole thing — 118 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Project Overview (for AI Agent)
Goal
Provide the modsearch CLI tool that turns search queries and page URLs into structured web evidence for LLM agent workflows.
Technical Approach
- Pluggable engines — the engine interface (
buildInvocation+parseOutputfor subprocess engines, orexecutefor in-process ones) keeps each engine contained to one file, so adding or swapping one touches nothing else. Antigravity CLI (agy) is the preferred search engine when it is available. - Two modes, one CLI:
-qsearches the web,-ufetches a single page (absorbed from the retiredmodfetchproject).-uplus-qfetches with an answer focus. - Schema-enforced JSON output: subprocess engines are invoked with
--json-schema, so the structured result comes back guaranteed, no markdown scraping. grok-cli is the exception: that flag disables its search loop, so the result is salvaged from the final text. - Selectable automatic chain: every engine participates by default.
engines.<name>.enabled: falseexcludes one from automatic search, fetch, or X routing. An explicit--enginestill forces a one-off run.doctorreports readiness and enabled state separately. - Hidden Windows children: the core and standalone dsh plugin each own one child-process wrapper that forces
windowsHide: true. A contract test rejects directchild_processaccess anywhere else in shipped code. - Single responsibility: this project handles the live web (search + fetch). Image parsing lives in
modlens. - X handling: X-flavored
-qqueries route entirely to Grok Build (grok-cli) when it is installed and signed in, spending no agy quota. When Grok is missing or fails, a web engine answers instead, and that entry is markedstatus: "degraded"withsource: "web"andrequestedSource: "x"so the second-hand nature is explicit, never silent. On a--source web,xrun with X unreachable, the X slot returns a separatestatus: "unavailable"entry rather than vanishing. An explicit-e/--engineis a hard force: exactly that engine, no fallback, an error if it cannot do the job. One shared output contract for every engine.
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 Changed · +1 lines · +20 tokens per session da64786a04dd
- 1mo ago Changed · +44 tokens per session 03fcfb8646e5
- 1mo ago Changed · -2 tokens per session 2324b5256321
- 1mo ago Changed · +25 tokens per session d7eca8ce0c77
- 1mo ago First seen · 117 lines · 1,878 tokens per session scan A 709f0a4af067
modsearch AGENTS.md is an instructions file published in the GitHub repository liustack/modsearch (846 stars, last pushed 9d ago), licensed MIT. It adds 1,965 tokens to every session, about $0.0079 per session on Opus 5.5. A static security scan graded it A with 1 finding (runs shell commands). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other instructions, from other repositories
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).
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.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, cache eligibility and rollout and applying the notice (cutover).
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.
vscode copilot-instructions.md
Copilot instructions for microsoft/vscode, covering vs code copilot instructions, project overview, root folders, core architecture (src/ folder) and built-in extensions (extensions/ folder).
deno copilot-instructions.md
Copilot instructions for denoland/deno, covering deno development guide for github copilot, network access, high level overview, key directories and key files to understand first.