Borrowing it
Nothing to install: this file belongs to hatefsystems/search-engine-core. 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/hatefsystems/search-engine-core/master/AGENTS.mdgit clone --depth 1 https://github.com/hatefsystems/search-engine-coreWrote 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/hatefsystems/search-engine-core/agents-md)<a href="https://agentmods.dev/instructions/hatefsystems/search-engine-core/agents-md"><img src="https://agentmods.dev/badge/instructions/hatefsystems/search-engine-core/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/hatefsystems/search-engine-core/agents-md"><img src="https://agentmods.dev/badge/instructions/hatefsystems/search-engine-core/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 | $0.00749 | $0.00749 |
| Opus 5.5 | $0.00300 | $0.00300 |
| Sonnet 5.5 | $0.00150 | $0.00150 |
| Haiku 4.5 | $0.00075 | $0.00075 |
Grade A, and why
search-engine-core 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 — 54 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Agent instructions
Frontend typography and readability
Apply these rules to new and modified UI in templates/ and public/. Preserve
existing behavior and localization. Use the shared tokens in
public/assets/css/typography.css; do not create independent compact text
scales. The pixel equivalents below assume the browser's default 16px root, not
a fixed root size.
| Role | Size | Line height |
|---|---|---|
| Page title | 1.5–1.75rem (24–28px) | 1.5–1.6 |
| Section title | 1.125–1.25rem (18–20px) | 1.6 |
| Main editor heading | 1.375rem (22px), 1.25rem on mobile | 1.6 |
| Body copy and form values | 1rem (16px) | 1.75–1.9 |
| Labels, buttons and navigation | .875–1rem (14–16px) | 1.6–1.7 |
| Help, errors, privacy states and save status | .875rem (14px) | 1.8 |
| Nonessential metadata and character counters | .75rem (12px) | 1.6 |
- Keep the browser root size unchanged. Use
remand shared role tokens for text. Never shrink functional text to 8–11px to make a mobile layout fit. - Keep form values at 1rem on desktop and mobile. Check computed styles after all stylesheets and media queries load, including the identity panel overrides.
- Use at least 4.5:1 contrast for normal text, including help, placeholders and status text, against its actual background. Size increases alone do not fix contrast. This product scale is not a WCAG minimum-font-size requirement.
- Use single columns, wrapping, flexible heights and spacing when space is tight. Do not hide essential labels or states. Reserve 12px for genuinely secondary metadata; all instructions and privacy states remain at least 14px.
- Display explicit public/private text alongside privacy controls. Preserve their accessible name, keyboard operation and visible focus. Email and phone require explicit user consent before public display.
- Keep the sidebar rollout intact: one active basic section, six locked items, no inner menu scrolling, completion only for currently editable fields, and the upcoming-sections card. Preserve the two media editing rows.
- Keep save/draft/publish wording consistent with actual persistence behavior. Do not imply a draft or publication boundary that the API does not implement.
- Fixed save bars must leave the final controls visible and focusable. Verify at 320px and 390px, desktop, and 200% text enlargement. Check for clipped labels, horizontal page scrolling and footer overlap. Also check 400% desktop zoom reflow using a 320 CSS-pixel viewport.
- Load and inspect the real templates, CSS, JavaScript and local Persian font. Label fixture API screenshots accurately; they do not prove backend integration.
- Run the affected browser suites and
node tests/profile/typography-browser-check.cjsfor typography changes. Refresh stylesheet query versions when changing long-cached production assets.
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 First seen · 54 lines · 749 tokens per session scan A 852dcd56fc0a
search-engine-core AGENTS.md is an instructions file published in the GitHub repository hatefsystems/search-engine-core (5 stars, last pushed yesterday), licensed Apache-2.0. It adds 749 tokens to every session, about $0.0030 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 2026-11-01.
search-engine-core AGENTS.md compared with instructions from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| search-engine-core AGENTS.mdhatefsystems/search-engine-core | Instructions file | 5 | yesterday | Apache-2.0 | A | 749 | Codex, OpenCode |
| vscode buildNext.instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 9,719 | GitHub Copilot |
| next.js AGENTS.mdvercel/next.js | Instructions file | 143k | today | MIT | A | 7,461 | Codex, OpenCode |
| langchain AGENTS.mdlangchain-ai/langchain | Instructions file | 149k | yesterday | MIT | A | 4,680 | Codex, OpenCode |
| vscode oss-third-party-notices.instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 5,516 | GitHub Copilot |
| vscode copilot-instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 3,093 | GitHub Copilot |
| deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness | Instructions file | 274k | 2d ago | MIT | A | 4,313 | Codex, OpenCode |