Borrowing it
Nothing to install: this file belongs to capad-xyz/searchts. 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/capad-xyz/searchts/main/AGENTS.mdgit clone --depth 1 https://github.com/capad-xyz/searchtsWrote 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/capad-xyz/searchts/agents-md)<a href="https://agentmods.dev/instructions/capad-xyz/searchts/agents-md"><img src="https://agentmods.dev/badge/instructions/capad-xyz/searchts/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/capad-xyz/searchts/agents-md"><img src="https://agentmods.dev/badge/instructions/capad-xyz/searchts/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 | $0.04048 | $0.04048 |
| Opus 5.5 | $0.01619 | $0.01619 |
| Sonnet 5.5 | $0.00810 | $0.00810 |
| Haiku 4.5 | $0.00405 | $0.00405 |
Grade A, and why
searchts 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 5d 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 — 201 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
Standing rules for anyone changing this repo (Cursor, Codex, Claude, Grok, cheap-scouts).
This is not a skill. Skills (SKILL.md) are how to use searchts (read_url). This file is how to change it.
- What is not done:
PLAN.mdfor searchts,docs/hare-next.mdfor Hare - What already shipped:
docs/plan-shipped.mdanddocs/freeze-log.md. Not the plan. - Commands and Python conventions:
CLAUDE.md - Who is who:
NAMES.md - How to prove the CLI works:
.agents/skills/verify-searchts/
Where to write
A plan says what is true now and what is next. A log says what already happened. Do not append a build note to either plan.
| You are writing | File |
|---|---|
| Work that is not done yet | PLAN.md. Open boxes only. |
| A box that already shipped, kept so the id is not lost | docs/plan-shipped.md. Do not add. |
| Hare's behavior, the model list, cadence, what Hare should do next | docs/hare-next.md |
| What merged, a build note, a dated "we did X" | docs/freeze-log.md |
| A post | docs/comms.md |
| Direction, not the task list | ROADMAP.md |
| What a user sees in a release | CHANGELOG.md |
Plans land on main
A plan or an idea is not done until it is on main. Other agents read main, not a chat. Open the PR and merge it once the docs checks are green. Do not hold it for a later pass on the wording.
Look at the open PRs first.
- If one already edits the same lines, stack on that branch or wait. Do not merge a second copy over it.
- Landing the plan does not merge a code PR that is still open. The rules can be on
mainwhile the code is still in review. - Do not rewrite a shipped box in
docs/plan-shipped.mdto match a new idea. The open rule goes inPLAN.md. One dated line goes indocs/freeze-log.md.
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.
- 5d ago Changed · +5 lines · +91 tokens per session 448202aa463c
- 8d ago Changed · +113 tokens per session a9612e4943d2
- 9d ago Changed · +6 tokens per session 484cc0502ba6
- 17d ago Changed · +29 lines · +456 tokens per session 9fabbc3369ad
- 18d ago Changed · +10 lines · +172 tokens per session 58ab0cd243b5
- 19d ago Changed · +15 lines · +359 tokens per session 33a1dcb9405e
- 23d ago Changed · +97 tokens per session a226f6b4f00d
- 24d ago Changed · +32 tokens per session 8f553d4c7816
- 26d ago Changed · +186 tokens per session f1b4778daa00
- 28d ago First seen · 142 lines · 2,536 tokens per session scan A 661cec208e96
searchts AGENTS.md is an instructions file published in the GitHub repository capad-xyz/searchts (2 stars, last pushed yesterday), licensed MIT. It adds 4,048 tokens to every session, about $0.0162 per session on Opus 5.5. 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 2026-09-06.
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.