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/davidmosiah/agent-seo-engine/agents-mdgit clone --depth 1 https://github.com/davidmosiah/agent-seo-engineWhat 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 | $0.00152 | $0.00152 |
| Opus 5 | $0.00076 | $0.00076 |
| Sonnet 5 | $0.00030 | $0.00030 |
| Haiku 4.5 | $0.00015 | $0.00015 |
Grade A, and why
agent-seo-engine 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.
What it actually says
Agent Development Notes
Scope
This repo is a Python CLI plus optional MCP server for agent-first SEO scoring, intent classification and opportunity prioritization.
Commands
- Install dev deps:
pip install -e ".[dev]" - Test:
pytest - Build package:
python -m build - Check dist:
twine check dist/* - CLI smoke:
agent-seo-engine doctor
Rules
- Never commit private analytics exports, customer drafts, API keys, or credentials.
- Keep CLI output deterministic and JSON-first unless
--format markdownis requested. - Keep PyPI publishing on Trusted Publishing; do not add long-lived PyPI tokens.
- Keep MCP tools dry-run/local-first by default.
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 · 21 lines · 152 tokens per session scan A 1e3166ceb54b
agent-seo-engine AGENTS.md is an instructions file published in the GitHub repository davidmosiah/agent-seo-engine (0 stars, last pushed 4d ago), licensed MIT. It adds 152 tokens to every session, about $0.0008 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
aaron-marketing-skills AGENTS.md
AGENTS.md instructions for aaron-he-zhu/aaron-marketing-skills, covering agents.md, repository overview, the system — a four-layer marketing operating system, skill format specifications and required frontmatter.
open-seo CLAUDE.md
Instructions for every-app/open-seo, covering agent guidance, engineering principles, testing, log papercuts and preserve review learnings.
the-seo-framework docs.instructions.md
Use when editing README.md, readme.txt, or other user-facing documentation for this repository. Covers readme wording constraints, WordPress readme format, changelog prose style, and public API naming requirements.
pipulate AGENTS.md
AGENTS.md instructions for pipulate/pipulate, covering agents.md — pipulate, setup (the executable version of "dev environment tips"), tools, context (how this repo talks to ai) and edits (the executable version of "pr instructions").
claude-code-seo-starter CLAUDE.md
Instructions for AntonioBlago/claude-code-seo-starter, covering claude.md — seo agency / freelancer workspace, golden rules, data sources — visibly ai mcp, the four workflows and folder conventions & knowledge base.
press-rank CLAUDE.md
Instructions for VUVAX/press-rank, covering pressrank — claude code context, skills (auto-activate from intent), commands (/press:), operating principles and security rules (public repo).