Borrowing it
Nothing to install: this file belongs to josesepulvedapino/zahori. 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/josesepulvedapino/zahori/main/AGENTS.mdgit clone --depth 1 https://github.com/josesepulvedapino/zahoriWrote 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/josesepulvedapino/zahori/agents-md)<a href="https://agentmods.dev/instructions/josesepulvedapino/zahori/agents-md"><img src="https://agentmods.dev/badge/instructions/josesepulvedapino/zahori/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/josesepulvedapino/zahori/agents-md"><img src="https://agentmods.dev/badge/instructions/josesepulvedapino/zahori/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 | $0.00421 | $0.00421 |
| Opus 5 | $0.00211 | $0.00211 |
| Sonnet 5 | $0.00084 | $0.00084 |
| Haiku 4.5 | $0.00042 | $0.00042 |
Grade A, and why
zahori 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 10d 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
zahori: guide for coding agents
TypeScript ESM library + CLI (Node ≥ 22, pnpm). Finds the media stream behind a web page with a real browser (Playwright), declarative site profiles, and an ffmpeg oracle.
Commands
pnpm install
pnpm typecheck # tsc --noEmit (strict)
pnpm test # unit tests, fast, no browser
pnpm build # tsup → dist/ (required before test:e2e)
pnpm test:e2e # hermetic: headless Chrome vs a local fixture server + MCP protocol smoke
Always run pnpm typecheck && pnpm test after changes; run pnpm build && pnpm test:e2e when touching src/runtime.ts, src/discover.ts, src/browser.ts or src/mcp.ts.
Design rules (do not break)
- Profiles are data, not code. The engine interprets them deterministically; no AI at runtime.
- Models propose, the oracle disposes. Nothing is saved unless the oracle passes it.
- Never store a stream URL. Profiles describe how to re-derive it; resolved URLs may be signed/expiring.
- Refuse DRM.
DrmErroron Widevine/PlayReady/FairPlay markers is intentional and must stay. - Version lives only in
package.json(src/version.tsreads it); never hardcode it elsewhere. - Public API surface is
src/index.ts; anything exported there is a semver commitment.
Layout
src/runtime.ts engine · src/profile.ts schema + generic profile · src/oracle.ts ffmpeg validation · src/discover.ts probe/test/save primitives · src/ai/ BYO-key loop · src/mcp.ts MCP server · src/cli.ts CLI · tests/ unit · tests/e2e/ browser + MCP suites.
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.
- 10d ago First seen · 29 lines · 421 tokens per session scan A fd7775431443
zahori AGENTS.md is an instructions file published in the GitHub repository josesepulvedapino/zahori (3 stars, last pushed 8d ago), licensed MIT. It adds 421 tokens to every session, about $0.0021 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
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.
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
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).
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).
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.