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/rockorager/zigdoc/agents-mdgit clone --depth 1 https://github.com/rockorager/zigdocWhat 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 | $0.01501 | $0.01501 |
| Opus 5 | $0.00750 | $0.00750 |
| Sonnet 5 | $0.00300 | $0.00300 |
| Haiku 4.5 | $0.00150 | $0.00150 |
Grade A, and why
zigdoc 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 — 163 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
Design Priorities
Prioritize correctness, simplicity, and developer experience, in that order. Prefer explicit control flow and the smallest abstraction that clearly models the domain.
Zig Development
Use zigdoc to discover current APIs for the Zig standard library and any
third-party dependencies before coding.
Examples:
zigdoc std.fs
zigdoc std.posix.getuid
For imported dependencies, use the module name exposed by build.zig:
zigdoc <module>.<symbol>
Verification
- Run
zig build testafter code changes; it also checks formatting. - Use
zig build fmtwhen only a formatting check is needed. - Run
zig build readmewhen CLI usage or help text changes, and include the resultingREADME.mdupdate.
Zig Style
- Use
camelCasefor functions and methods. - Use lower-case
snake_casefor variables, parameters, and constants. - Use
PascalCasefor types, structs, and enums. - Prefer
const foo: Type = .{ .field = value };overconst foo = Type{ .field = value };. - Pass allocators explicitly; use
errdeferfor cleanup on error. - Keep unit tests close to the code they cover. Ensure
zig build testdiscovers and runs every test-bearing module. - Avoid abbreviations unless they are established domain terms.
- Include units and qualifiers in names when values could otherwise be
ambiguous, such as
timeout_ms,buffer_size, oroffset_bytes. - Treat indexes, counts, and byte sizes as distinct concepts; name conversions between them explicitly.
- Use an options struct when positional arguments of the same type are easy to confuse.
- Make division semantics explicit with
@divExact,@divFloor, or deliberate ceiling division when rounding affects correctness.
Files and Types
- Treat every
.zigfile as a namespace. Make the file itself a type only when its root represents one primary stateful abstraction with fields and methods. - Name a file-backed type
PascalCase.zig, import it directly withconst Widget = @import("Widget.zig");, and begin it with an optional//!container doc followed byconst Widget = @This();. Prefer the concrete type name overSelfso signatures remain clear out of context. - Use lower-case
snake_case.zigfor namespace modules: related free functions, constants, multiple peer types, or package facades. Export named types from these modules and import them as@import("widget.zig").Widget. - Do not put a sole
pub const Widget = struct { ... };insideWidget.zig; the file root already provides that container. Conversely, do not create a file-backed type merely to enforce one-type-per-file organization. - Preferred file start:
//!container docs when needed, the file-backed type alias when applicable, imports and local aliases, then scoped logging declarations when needed.
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 · 163 lines · 1,501 tokens per session scan A 70517c1b2573
zigdoc AGENTS.md is an instructions file published in the GitHub repository rockorager/zigdoc (144 stars, last pushed 1mo ago), licensed MIT. It adds 1,501 tokens to every session, about $0.0075 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
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.
buildNext
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
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, applying the notice (cutover) and fallback chain (never fail the build).
spec-kit 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.
langchain 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.