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/yuin/goldmark/agents-mdgit clone --depth 1 https://github.com/yuin/goldmarkWhat 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 | $0.00492 | $0.00492 |
| Opus 5 | $0.00246 | $0.00246 |
| Sonnet 5 | $0.00098 | $0.00098 |
| Haiku 4.5 | $0.00049 | $0.00049 |
Grade A, and why
goldmark 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 yesterday.
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 — 30 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Instructions for agents
Testing instructions
- use
make testto run tests - use
make lintto run linters
Benchmark instructions
- use
make benchto run benchmarks- this will output cpu profiler data to
cpu.pproffile
- this will output cpu profiler data to
Coding conventions
- Make sure to pass
make lint - Use
util.StringToReadOnlyBytesandutil.ReadOnlyBytesToStringwhen converting between readonly strings and readonly byte slices to avoid unnecessary allocations. - Before making changes, you must run
make bench. After making changes, you should runmake benchagain to compare the performance before and after your changes.- If your changes cause a significant performance regression, you should analyze
cpu.pprofto identify the bottlenecks and optimize your code accordingly.
- If your changes cause a significant performance regression, you should analyze
Key point of CommonMark spec
-
In most cases, punctuation characters can be escaped with a backslash (
\) to prevent them from being interpreted as Markdown syntax. For example,\*will render as*instead of starting an emphasis. -
Spec defines sets of character categories. Use
utilpackage to check if a character belongs to a specific category. For example,util.IsPunctcan be used to check if a character is a punctuation character. DO NOT use standard library functions likeunicode.IsPunctas they may not cover all cases defined in the CommonMark spec. -
Most of inline elements (like emphasis, links, etc.) can exist within multiple lines. And they can be nested. So inline elements probably have multiple divided segments:
> [lin > nk](https://example.com)In this case, the link element has two divided segments:
linandnk. When parsing, you should keep track of these segments and combine them when necessary. This kind of elements should havetext.MultiLineValueinstead oftext.SingleLineValue. -
Paragraph rendering can be changed by parent elements. For example, a paragraph inside a tight list item should not have
<p>tags, while a paragraph inside a block quote should have<p>tags. -
Tabs can be 1,2,3,4 spaces or raw tab character, depending on its position. When parsing block elements, you should aware of this and calculate the correct indentation level.
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.
- yesterday First seen · 30 lines · 492 tokens per session scan A 3913ef5c91d2
goldmark AGENTS.md is an instructions file published in the GitHub repository yuin/goldmark (4,979 stars, last pushed 2d ago), licensed MIT. It adds 492 tokens to every session, about $0.0025 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
ollama AGENTS.md
Instructions for ollama/ollama, covering agents.md and building.
go-micro CLAUDE.md
Instructions for micro/go-micro, covering claude.md - go micro project guide, project overview, build & test, run all tests and run tests for a specific package.
ollama CLAUDE.md
Instructions for ollama/ollama: See AGENTS.md for the shared agent instructions for this repository.
sq AGENTS.md
Instructions for neilotoole/sq, covering agents.md, about sq, key documents, common commands and conventions.
azure-sdk-for-go go-examples.instructions.md
Instructions for Azure/azure-sdk-for-go, a project described as: This repository is for active development of the Azure SDK for Go. For consumers of the SDK we recommend visiting our public developer docs at.
azure-sdk-for-go go-code.instructions.md
Instructions for Azure/azure-sdk-for-go: All code should follow the guidelines from the Azure Go SDK Guidelines. This document is a summary of the most important guidelines to follow when contributing to the Azure Go SDK.