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/axelfreeman/blog/agents-mdgit clone --depth 1 https://github.com/axelfreeman/blogWrote 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/axelfreeman/blog/agents-md)<a href="https://agentmods.dev/instructions/axelfreeman/blog/agents-md"><img src="https://agentmods.dev/badge/instructions/axelfreeman/blog/agents-md.svg" alt="Measured on agentmods" 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 | $0.01421 | $0.01421 |
| Opus 5 | $0.00711 | $0.00711 |
| Sonnet 5 | $0.00284 | $0.00284 |
| Haiku 4.5 | $0.00142 | $0.00142 |
Grade A, and why
blog 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 3d 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 — 185 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md — axelfreeman/blog
Instructions for AI agents (Claude Code, Codex, Hermes, etc.) working with this repository.
What This Repo Is
This is the blog articles repository for axelfreeman.com — Axel Freeman's personal site about AI agents, AEO, automation, and marketing. Every article is real experience, not recycled content. No fluff.
Default branch:masterLicense:MIT (seeLICENSE)Owner:@axelfreeman
Article Structure
Articles are plain Markdown (.md). Each follows this structure:
# Article Title<br><span style="...">Optional Subtitle</span>
Category · Subcategory
Article Title Repeated
(Optional Subtitle)
Axel Freeman · DATE · X min read
**Bold summary paragraph.** The key takeaway, 2-4 sentences.
## Section Heading
Content paragraphs...
### Callout Box Title
Callout content with key insight or actionable advice.
Key Conventions
- Title line — uses
<br> for line breaks,for styled subtitles - Category line —
Category · Subcategory(e.g.,AI Marketing · Opinion,AI Marketing · Content) - Author line —
Axel Freeman · DATE · X min read(indented with 4 spaces) - Summary paragraph — bold, 2-4 sentences, indented with 8 spaces, captures the article's core argument
- Section headings —
## Heading(H2), no H1 after the title - Callout boxes —
### Emoji Callout Titlefollowed by content, indented - Paragraphs — indented with 4 spaces
- Emphasis — bold for key phrases, sparing inline code for terms
Bilingual Convention
- English articles:
<slug>-en.md(e.g.,claude-vs-hermes-marketing-en.md) - Russian articles:
<slug>.md(e.g.,claude-vs-hermes-marketing.md)
When creating a new article, always produce both versions. English is the primary public-facing version; Russian serves the RU-speaking audience on axelfreeman.ru.
Article Naming
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.
- 3d ago First seen · 185 lines · 1,421 tokens per session scan A f12818afa3ae
blog AGENTS.md is an instructions file published in the GitHub repository axelfreeman/blog (14 stars, last pushed 13d ago), licensed MIT. It adds 1,421 tokens to every session, about $0.0071 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
evc AGENTS.md
Instructions for SaigonXIII/evc, covering evc — cross-platform agent config, for claude code, for cursor, for codex cli and for gemini cli.
taketomarket AGENTS.md
Instructions for ranjanrishikesh/taketomarket, covering project, target audience, constraints, technology stack and recommended stack.
agentic-marketing CLAUDE.md
Instructions for dzivkovi/agentic-marketing, covering claude.md, system instructions, what this repo is, confidentiality guardrail and gitignored content.
taketomarket GEMINI.md
Instructions for ranjanrishikesh/taketomarket, covering taketomarket for gemini cli, target audience, installation, invocation and quick start.
claude-founder-brand AGENTS.md
Instructions for cmj-hub/claude-founder-brand, covering agents.md — behavior rules for claude-founder-brand, rules, what the agent never does and onboarding flow.
taketomarket CLAUDE.md
Instructions for ranjanrishikesh/taketomarket, covering project, target audience, constraints, technology stack and recommended stack.