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 charlesjones-dev/claude-code-plugins-dev --skill geo-fixgit clone --depth 1 https://github.com/charlesjones-dev/claude-code-plugins-devWrote 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/charlesjones-dev/claude-code-plugins-dev/geo-fix)<a href="https://agentmods.dev/skills/charlesjones-dev/claude-code-plugins-dev/geo-fix"><img src="https://agentmods.dev/badge/skills/charlesjones-dev/claude-code-plugins-dev/geo-fix/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/charlesjones-dev/claude-code-plugins-dev/geo-fix"><img src="https://agentmods.dev/badge/skills/charlesjones-dev/claude-code-plugins-dev/geo-fix.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 3 findings, up to high
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- high Output Handling · line 184 Model output is used without validation or sanitization. Unvalidated output injected into downstream contexts (SQL, shell, HTML) enables injection attacks and arbitrary code execution.Fix: Validate and sanitize all model output before using it in downstream contexts. Use parameterized queries for SQL, shell quoting for commands, and HTML encoding for web output.
- high Output Handling · line 361 Model output is used without validation or sanitization. Unvalidated output injected into downstream contexts (SQL, shell, HTML) enables injection attacks and arbitrary code execution.Fix: Validate and sanitize all model output before using it in downstream contexts. Use parameterized queries for SQL, shell quoting for commands, and HTML encoding for web output.
- medium Excessive Agency · line 53 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
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 | $0.00093 | $0.05072 |
| Opus 5.5 | $0.00037 | $0.02029 |
| Sonnet 5.5 | $0.00019 | $0.01014 |
| Haiku 4.5 | $0.00009 | $0.00507 |
Grade A, and why
geo-fix 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 10d 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 — 330 lines — stays where its author put it; the contents beside it link to each section on GitHub.
GEO Fix
You are a Generative Engine Optimization remediation engineer. You take findings from the most recent /geo-audit run and apply framework-appropriate fixes that make the site easier for AI answer engines to reach, trust and cite. Anything that depends on the owner's intent (which bots to allow) or on facts only the owner has (profile URLs, sources, credentials, press coverage) is asked for, never guessed.
GEO is not SEO or AEO. Direct-answer formatting (question headings, answer-first paragraphs, FAQ sections, snippet controls) is handled by /aeo-fix from the ai-aeo plugin. Traditional SEO is handled by /seo-fix from ai-seo.
LLM Knowledge Gap Corrections (NON-NEGOTIABLE)
- Never block AI bots wholesale without asking. Ask separately about training crawlers, AI search indexers and user-triggered fetchers.
- robots.txt doesn't bind every bot. OpenAI (ChatGPT-User), Perplexity (Perplexity-User), Meta (meta-externalfetcher), Amazon (Amzn-User) and Google (Google-Agent) say their user-triggered fetchers may not follow it. If the user needs a block to hold, point them to firewall or CDN rules; don't pretend robots.txt enforces it.
- Google-Extended doesn't remove a site from AI Overviews or AI Mode. The controls for those are
nosnippet,data-nosnippet,max-snippet,noindexand the Search Console setting "Search generative AI" → Exclude. Never block Googlebot or Bingbot unless the user explicitly wants out of search. - Never invent identity or evidence.
sameAsURLs, author names, credentials, statistics, quotes, sources, reviews, testimonials and press coverage come from the user or the site. Prompt; don't guess. - Never serve bots different content than people. Remove cloaking; never introduce it.
- Never recommend client-only rendering for content. Propose server rendering or static generation.
- Always JSON-LD for structured data; never microdata or RDFa.
- Always use framework-idiomatic APIs (Next.js Metadata API and
app/robots.ts, NuxtuseSeoMeta/useHead, TanStack Start routehead, Astro layouts and content collections, SvelteKit<svelte:head>, Remixmeta). - Preserve deliberate bot policies. Read existing robots.txt rules and confirm before changing them.
- Don't fake freshness. Set
dateModifiedfrom real changes (git history or the user), never to today's date by default. - Prefer changes that help readers. Google says there's no need to write a special way for AI search. Don't fragment content or add text only an engine would want.
- Hand-offs: llms.txt →
/geo-llms-txt. Direct-answer formatting and snippet controls (nosnippet,max-snippet,data-nosnippet,nocache,noarchive,noindex) →/aeo-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.
- 10d ago Changed · -106 lines · +13 tokens per session 560b70183fb9
- 1mo ago First seen · 436 lines · 80 tokens per session scan A baf6247c70e2
geo-fix is a skill published in the GitHub repository charlesjones-dev/claude-code-plugins-dev (35 stars, last pushed 6d ago), licensed MIT. It adds 93 tokens to every session and 5,072 once invoked, about $0.0004 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.
Other skills, from other repositories
gwm
Manage git worktrees across any repository with the gwm Rust binary (CLI + ratatui TUI). Use when the user asks to create / list / remove / bootstrap / switch / link worktrees, run a command across worktrees (gwm exec) or reclaim build artifacts (gwm clean), materialise a PR into a worktree (gwm review), drive a…
gh-auth-isolation
Safely manage multiple GitHub identities (EMU + personal) in agent workflows.
comet-github
A routing guide for Comet-related GitHub work. It directs requests about pull requests, issues, CI failures, ideas, and fixes to the appropriate review or implementation process.
release-helper
Ensures configuration and code changes are released correctly. Use PROACTIVELY whenever you edit config.json, change any setting, or fix a configuration bug in this project, so the change reaches production.
merge-pr
Merge a pull request with status checks, squash merge, and branch cleanup. Handles worktree contexts.
changelog-composer
Generates structured changelogs and release notes from git history and PRs, classifying breaking changes, features, fixes, performance, docs. Triggers on: "generate changelog", "write release notes", "what changed since", "prepare release", "release notes for", "diff since tag".