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/zenitheditor/zenith/agents-mdgit clone --depth 1 https://github.com/zenitheditor/zenithWhat 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 | $0.01537 | $0.01537 |
| Opus 5 | $0.00768 | $0.00768 |
| Sonnet 5 | $0.00307 | $0.00307 |
| Haiku 4.5 | $0.00154 | $0.00154 |
Grade A, and why
zenith 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 2d 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 — 79 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Repository Guidelines
This file is the source of truth for working in the Zenith repository — for human contributors and AI agents alike. Read it before making changes.
Project Structure & Module Organization
Zenith is a Rust workspace (edition = "2024"). Each crate owns one concern and exposes a
stable contract; zenith-geometry depends on no other Zenith crate; zenith-core may depend only on pure zenith-geometry for path math (validation / fill queries).
zenith-core/— KDL parser adapter, semantic AST, canonical formatter, tokens, validation, the full diagnostic set. May depend on purezenith-geometryonly among Zenith crates.zenith-geometry/— pure geometry (paths, contours, booleans). C-free; depends on no other Zenith crate; used by core, layout, scene, and tx.zenith-layout/— text shaping & font metrics (rustybuzz+ttf-parser); all third-party shaping types confined here.zenith-raster/— raster surface, blend modes, adjustments used by perception and render.zenith-perception/— visual QA / perception reports over geometry + raster.zenith-scene/— backend-neutral scene IR and compilation (geometry, text wrap, anchors, opacity/clip, text outlines).zenith-render/— CPU PNG backend (tiny-skia) and vector PDF backend; raster-time determinism rules.zenith-tx/— transaction op set, apply/dry-run engine, diffs, audit-record contract. Pure AST; no scene/layout dependency.zenith-session/— local doc identity (ULID), ephemeral session DAG, durable content-addressed version store. Never on the render path.zenith-zpx/— packaged design export (manifest + bake).zenith-producers/— higher-level produce/export helpers (SVG native, ZPX bake).zenith-cli/— thezenithbinary (crate package namezenith-tool): command dispatch, clap, JSON/human output, MCP.src/main.rsis thin; logic lives insrc/lib.rsandsrc/commands/.examples/— runnable.zendocuments (keep them valid against the current parser).assets/— bundled fonts (assets/fonts/) and embedded library presets (assets/libraries/). Committed.conformance/— regenerable rendered proof of simulation scenarios. Gitignored; never stage it.resource/,.agents/,.claude/,.codex/— local planning/research/session scratch. Gitignored.
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.
- 2d ago First seen · 79 lines · 1,537 tokens per session scan A 8924c8efb196
zenith AGENTS.md is an instructions file published in the GitHub repository zenitheditor/zenith (22 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 1,537 tokens to every session, about $0.0077 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 2026-08-30.
Other instructions, from other repositories
llm-context.py CLAUDE.md
Instructions for cyberchitta/llm-context.py, covering claude.md, working notes (gitignored) and draining the field notes.
openrouter-mcp-multimodal AGENTS.md
Instructions for stabgan/openrouter-mcp-multimodal, covering agent instructions, before you ship, releasing (read this before publishing), short version and version files (must all match package.json).
Silex AGENTS.md
AGENTS.md instructions for silexlabs/Silex, covering agents.md, tech stack, run it locally, building the desktop app and when writing code for silex (editing source).
seekstone CLAUDE.md
Instructions for shaqmughal/seekstone, covering claude.md, what this repo is, commands, the harness itself (run after npm install) and architecture.
Plonk AGENTS.md
Instructions for ostapondo/Plonk, covering agent rules, layout, adding a module, build & verify and code style.
mcp-dockhand copilot-review.instructions.md
Instructions for strausmann/mcp-dockhand: When reviewing pull requests in this repository.