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/yagomp/seoagent/agents-mdgit clone --depth 1 https://github.com/yagomp/seoagentWhat 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 | $0.01018 | $0.01018 |
| Opus 5 | $0.00509 | $0.00509 |
| Sonnet 5 | $0.00204 | $0.00204 |
| Haiku 4.5 | $0.00102 | $0.00102 |
Grade A, and why
seoagent 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 — 115 lines — stays where its author put it; the contents beside it link to each section on GitHub.
SEOAgent — Agent Instructions
This file provides instructions for AI coding agents (Claude Code, Codex, Gemini, Cursor, etc.) working on the SEOAgent codebase.
Quick Start
pnpm install && pnpm build && pnpm test
Where Things Live
| What | Where |
|---|---|
| All business logic | packages/core/src/ |
| Public API | packages/core/src/index.ts (barrel export) |
| Types | packages/core/src/types.ts |
| Database schema | packages/core/src/schema.ts |
| Tests | packages/core/src/__tests__/*.test.ts |
| CLI commands | packages/cli/src/commands/ |
| MCP tool handlers | packages/mcp/src/tools/ |
| Dashboard API | packages/dashboard/src/server/routes.ts |
| Dashboard pages | packages/dashboard/src/app/pages/ |
Adding a New Feature
- Add types to
packages/core/src/types.ts(if needed) - Write failing test in
packages/core/src/__tests__/ - Implement in
packages/core/src/(new file or existing module) - Export from
packages/core/src/index.ts - Add CLI command in
packages/cli/src/commands/ - Add MCP tool in
packages/mcp/src/tools/ - Add dashboard endpoint + page if applicable
Testing Patterns
- Mock HTTP calls with
vitest.mock("undici")orvitest.mock("googleapis") - Mock DataForSEO with
vitest.mock("../dataforseo.js") - Use
SEOAGENT_HOMEenv var pointing to temp dir for isolated tests - Database tests: create temp dir,
openDatabase(), cleanup inafterEach
let tmpDir: string;
beforeEach(() => {
tmpDir = fs.mkdtempSync(path.join(os.tmpdir(), "seoagent-test-"));
process.env.SEOAGENT_HOME = tmpDir;
});
afterEach(() => {
fs.rmSync(tmpDir, { recursive: true, force: true });
});
MCP Server
24 tools prefixed seoagent_. Install config:
{
"mcpServers": {
"seoagent": {
"command": "node",
"args": ["<absolute-path>/packages/mcp/dist/index.js"],
"env": { "SEOAGENT_PROJECT": "<project-slug>" }
}
}
}
CLI
seoagent project add mysite --domain example.com --niche tech
seoagent project use mysite
seoagent config set dataforseo.login <login>
seoagent config set dataforseo.password <password>
seoagent keywords research "seo tips" --format json
seoagent audit crawl --max-pages 100
seoagent strategy generate
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 · 115 lines · 1,018 tokens per session scan A 95d4841f78af
seoagent AGENTS.md is an instructions file published in the GitHub repository yagomp/seoagent (0 stars, last pushed 4mo ago), licensed MIT. It adds 1,018 tokens to every session, about $0.0051 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
crawlseo AGENTS.md
Instructions for crawlseo/crawlseo, a project described as: Open-source SEO monitoring. GSC + Site Crawler + Core Web Vitals in one dashboard.
backlink-pilot CLAUDE.md
Instructions for s87343472/backlink-pilot, covering backlink pilot v2.1 — claude code instructions, first-time user flow, step 1: check prerequisites, step 2: create config.yaml and step 3: start chrome.
seo-survival-kit CLAUDE.md
Instructions for maxschottke-spec/seo-survival-kit, covering seo-survival-kit: project instructions for claude code, what this repository is, architecture, routing and skill-naming convention.
local-competitor-map AGENTS.md
Instructions for AgriciDaniel/local-competitor-map, covering agents.md, what this is, layout, workflow and house rules.
agentic-seo-skills AGENTS.md
Instructions for agencia-conversion/agentic-seo-skills, covering agentic seo — agent runtime contract, mission, six pillars, audience and delivery — web companion first.
claude-seo-skills CLAUDE.md
Instructions for lionkiii/claude-seo-skills, covering claude seo skills, structure, install, mcp dependencies and dev commands.