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 tmj-90/gaffer --skill aeogit clone --depth 1 https://github.com/tmj-90/gafferWrote 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/tmj-90/gaffer/aeo)<a href="https://agentmods.dev/skills/tmj-90/gaffer/aeo"><img src="https://agentmods.dev/badge/skills/tmj-90/gaffer/aeo/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/tmj-90/gaffer/aeo"><img src="https://agentmods.dev/badge/skills/tmj-90/gaffer/aeo.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 | $0.00122 | $0.01571 |
| Opus 5.5 | $0.00049 | $0.00628 |
| Sonnet 5.5 | $0.00024 | $0.00314 |
| Haiku 4.5 | $0.00012 | $0.00157 |
Grade A, and why
aeo scanned grade A with 1 finding 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 20d 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
robots.txt, the CDN/WAF rules and the meta robots tags. Fetch the page with curl and How it starts
The opening of the file, as written. The whole thing — 112 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Optimise content to be cited by answer engines
Answer engines (ChatGPT search, Perplexity, Claude with web search, Google AI Overviews and AI Mode) mostly answer by retrieving live pages from a search index and citing them. They are not recalling training data. A page gets cited when three things hold:
- The engine's crawler can fetch it.
- It ranks in the engine's retrieval for the question.
- It contains a clear, quotable answer the model can attribute.
AEO is therefore mostly SEO fundamentals plus extractable answers. Treat claims of a secret ranking signal as unproven.
What primary sources say:
- Google (Search Central, "AI features and your website"): AI Overviews and AI Mode have no additional technical requirements. A page must be indexed and eligible for a snippet. The usual advice applies: helpful, reliable, people-first content, and structured data that matches visible text.
- GEO study (Aggarwal et al., KDD 2024): adding cited sources, quotations and statistics raised visibility in generative answers by up to ~40% on their benchmark, with effects varying by domain. Keyword stuffing did not help.
Crawler access (check first — blocked means uncitable)
| Engine | Search/citation crawler (allow for citation) | Training-only crawler (independent choice) |
|---|---|---|
| OpenAI / ChatGPT search | OAI-SearchBot (plus ChatGPT-User for user-triggered fetches) |
GPTBot |
| Anthropic / Claude | Claude-SearchBot (plus Claude-User) |
ClaudeBot |
| Perplexity | PerplexityBot (plus Perplexity-User) |
n/a |
| Google AI Overviews / AI Mode | Googlebot (normal Search indexing) |
Google-Extended (Gemini training; does not affect Search) |
| Microsoft Copilot | Bingbot |
n/a |
Blocking a training crawler does not block citation, and the reverse also holds. Check
robots.txt, the WAF/CDN bot rules and any noindex or nosnippet. A CDN "block AI bots"
toggle often blocks the search crawlers too. No major engine has confirmed that it uses
llms.txt, so treat that file as optional and never as a fix.
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.
- 20d ago Changed · +37 lines · +17 tokens per session 221b632982fc
- 1mo ago First seen · 75 lines · 105 tokens per session scan A 14b875584f59
aeo is a skill published in the GitHub repository tmj-90/gaffer (2 stars, last pushed 20d ago), licensed Apache-2.0. It adds 122 tokens to every session and 1,571 once invoked, about $0.0005 per session on Opus 5.5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
bulwark-brainstorm
Role-based brainstorming with dual modes: --scoped (sequential Task tool, 5 roles) and --exploratory (Agent Teams peer debate, 4 roles). Use for feasibility assessment and idea validation.
plan-creation
Create structured implementation plans via a 4-role scrum team (Product Owner, Architect, Eng/Delivery Lead, QA/Critic) with optional Agent Teams peer debate mode.
anthropic-validator
Validates Claude Code assets (skills, hooks, agents, commands, MCP servers, plugins) against official Anthropic standards. Fetches latest docs dynamically and produces structured validation reports.
code-review
Comprehensive code review with distinct aspect based sections. Use when reviewing code, checking for security issues, finding type safety problems, auditing code quality, or when user asks to review code, PRs or changes. Three-phase workflow runs static tools, LLM judgment, and writes diagnostic log.
create-subagent
Generates single-purpose Claude Code sub-agents for use via the Task tool. Use when creating dedicated sub-agents, scaffolding agent definitions, or generating agents with diagnostics and permissions setup.
test-audit
Audit test suites for T1-T4 violations using AST analysis, mock detection, and multi-stage synthesis. Invoke when user asks to audit tests, check test quality, find mock violations, review test effectiveness, or inspect test suites for over-mocking. Triggers automatic rewrites when quality gates fail.