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 skills add psyduckler/aeo-skills --skill aeo-baselinegit clone --depth 1 https://github.com/psyduckler/aeo-skillsWrote 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/skills/psyduckler/aeo-skills/aeo-baseline)<a href="https://agentmods.dev/skills/psyduckler/aeo-skills/aeo-baseline"><img src="https://agentmods.dev/badge/skills/psyduckler/aeo-skills/aeo-baseline/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/psyduckler/aeo-skills/aeo-baseline"><img src="https://agentmods.dev/badge/skills/psyduckler/aeo-skills/aeo-baseline.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00152 | $0.02026 |
| Opus 5.5 | $0.00061 | $0.00810 |
| Sonnet 5.5 | $0.00030 | $0.00405 |
| Haiku 4.5 | $0.00015 | $0.00203 |
Grade A, and why
aeo-baseline 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 2mo 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 — 161 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AEO Baseline
Source: github.com/psyduckler/aeo-skills Part of: AEO Skills Suite Methodology: aeo-v1 Output schema: aeo-evidence-v1
The atomic measurement primitive for AI visibility tracking. One command, one run, one evidence file with every signal you can extract from 20 grounded Gemini responses per prompt.
The Retrieval Framework
You cannot edit a model's training data. But for search-grounded models like Gemini, you can influence what enters the candidate set the model selects from when it grounds an answer. That candidate set — the recurring retrieval set for a prompt — is what this skill measures.
Every metric in the output traces back to a saved raw response. If you disagree with the score, recompute it from the evidence file — components are stored separately.
Requirements
- Gemini API key (free from aistudio.google.com) — set as
GEMINI_API_KEY - Python 3.9+ — stdlib only, no pip install needed
- A workspace config — either an existing
aeo.config.json(produced byaeo-init) or a one-off via--prompt
Usage
# Default: read aeo.config.json, run 20 samples per prompt, write to aeo-data/
GEMINI_API_KEY="$GEMINI_API_KEY" python3 scripts/baseline.py
# Verify the API key works without running a measurement
python3 scripts/baseline.py --doctor
# Print projected cost without making any API calls
python3 scripts/baseline.py --estimate-cost
# Run a single ad-hoc prompt (skips most of the config)
GEMINI_API_KEY="$GEMINI_API_KEY" python3 scripts/baseline.py --prompt "best CRM for small business"
# Override sample count for higher-confidence measurements
GEMINI_API_KEY="$GEMINI_API_KEY" python3 scripts/baseline.py --runs 50
# Skip the cost confirmation prompt (for cron / CI use)
GEMINI_API_KEY="$GEMINI_API_KEY" python3 scripts/baseline.py --yes
What ships with it
5 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 2mo ago First seen · 161 lines · 152 tokens per session scan A c6da9d28cccc
aeo-baseline is a skill published in the GitHub repository psyduckler/aeo-skills (13 stars, last pushed 5mo ago), licensed MIT. It adds 152 tokens to every session and 2,026 once invoked, about $0.0006 per session on Opus 5.5. 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.
aeo-baseline compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| aeo-baselinepsyduckler/aeo-skills | Skill | 13 | 5mo ago | MIT | A | 152 | Claude Code, Codex |
| imagegenopenai/codex | Skill | 133k | yesterday | Apache-2.0 | A | 113 | Codex |
| playwright-climicrosoft/playwright | Skill | 99k | yesterday | Apache-2.0 | A | 19 | Claude Code |
| local-ai-agentsmicrosoft/ai-agents-for-beginners | Skill | 79k | 4d ago | MIT | A | 200 | Claude Code, Codex |
| systematic-debuggingobra/superpowers | Skill | 313k | 3d ago | MIT | A | 21 | Claude Code |
| next-cache-components-adoptionvercel/next.js | Skill | 143k | yesterday | MIT | A | 95 | Claude Code |
| next-partial-prefetching-adoptionvercel/next.js | Skill | 143k | yesterday | MIT | A | 103 | Claude Code |