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 joaoguirunas/team-os --skill seo-ahrefsgit clone --depth 1 https://github.com/joaoguirunas/team-osWrote 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/joaoguirunas/team-os/seo-ahrefs)<a href="https://agentmods.dev/skills/joaoguirunas/team-os/seo-ahrefs"><img src="https://agentmods.dev/badge/skills/joaoguirunas/team-os/seo-ahrefs/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/joaoguirunas/team-os/seo-ahrefs"><img src="https://agentmods.dev/badge/skills/joaoguirunas/team-os/seo-ahrefs.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 | $0.00061 | $0.00720 |
| Opus 5.5 | $0.00024 | $0.00288 |
| Sonnet 5.5 | $0.00012 | $0.00144 |
| Haiku 4.5 | $0.00006 | $0.00072 |
Grade B, and why
seo-ahrefs scanned grade B 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.
Reads MCP configurationmediumAgent snooping
mcp.json carries server URLs and auth tokens; reading it lets a mod discover and abuse other integrations.
- Register the Ahrefs MCP server in the project's `.mcp.json` (or `claude mcp add ahrefs -e API_KEY=<token> -- npx -y @ahrefs/[email protected]`), passing the token through the `API_KEY` environment variable. No installer scrip How it starts
The opening of the file, as written. The whole thing — 58 lines — stays where its author put it; the contents beside it link to each section on GitHub.
seo-ahrefs
Live Ahrefs data via the tested @ahrefs/[email protected] server.
Package check (2026-07-10): verify the current Ahrefs MCP package source before changing this tested version.
Prerequisites
- An Ahrefs API token (https://ahrefs.com/api).
- Register the Ahrefs MCP server in the project's
.mcp.json(orclaude mcp add ahrefs -e API_KEY=<token> -- npx -y @ahrefs/[email protected]), passing the token through theAPI_KEYenvironment variable. No installer script ships with this pack. - Node 18+ on
$PATHfor the MCP server.
Before calling any Ahrefs tool, verify the MCP is connected by checking
that any Ahrefs MCP tool is available in this session. If tools are
not available, tell the user the Ahrefs MCP server is not configured and
point to the .mcp.json / claude mcp add setup above.
Routing
| Command | Action |
|---|---|
/seo ahrefs metrics <url> |
Domain / URL rating, referring domain count, organic traffic estimate |
/seo ahrefs backlinks <url> |
Top referring domains, anchor distribution, follow/nofollow ratio |
/seo ahrefs organic <url> |
Organic keywords, ranking distribution, traffic by country |
/seo ahrefs content <topic> |
Content Explorer top results, social shares, referring domains |
Output conventions
- Cite the data source on every metric: "Ahrefs (live, confidence 1.00)".
- When Ahrefs and Moz disagree on the same metric, trust Ahrefs and note the discrepancy in the report.
- Toxic link assessment: combine Ahrefs backlink quality signals with the existing seo-backlinks Common Crawl + verify crawler signals.
Cross-skill delegation
- For multi-source confidence weighting across Moz + Bing + Common Crawl + Ahrefs, hand back to
seo-backlinks. - For SERP-feature analysis where Ahrefs and DataForSEO overlap, prefer DataForSEO for live SERP data.
Cost guardrails
Ahrefs API usage is metered per unit. Before running a batch (>= 50 URLs):
- Estimate cost with
"${CLAUDE_PROJECT_DIR}/.claude/skills/seo/scripts/claude-seo" run dataforseo_costs.py(the cost-tracker module is generic and supports Ahrefs unit accounting). - Surface the estimate to the orchestrator.
- Log actual cost after each call.
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 · +4 lines · +9 tokens per session scan A → B f8b3cdc7d52e
- 25d ago First seen · 54 lines · 52 tokens per session scan A c0721bf8f7d3
seo-ahrefs is a skill published in the GitHub repository joaoguirunas/team-os (4 stars, last pushed 2d ago), licensed MIT. It adds 61 tokens to every session and 720 once invoked, about $0.0002 per session on Opus 5.5. A static security scan graded it B with 1 finding (reads mcp configuration). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-21.
Other skills, from other repositories
jsonl-log-analyzer
Analyze large JSONL log files using schema-aware partitioned analysis. Discovers field schema, generates tailored jq extraction recipes, and orchestrates parallel chunk analysts with synthesis. Use when processing JSONL logs exceeding context limits, performing log analytics, or investigating incident logs.
orchestration-patterns
Apply proven orchestration patterns for agent teams including parallel specialists, pipelines, swarms, research+implementation, plan approval, and multi-file refactoring. Use when choosing a team structure, designing workflows, or implementing specific coordination patterns.
task-system
Manage shared task lists for agent teams including creating tasks, setting dependencies, claiming work, and tracking progress. Use when creating work items, building task pipelines, coordinating task ownership, or managing task dependencies.
spawn-backends
Configure how teammate agents run including in-process, tmux, and iTerm2 backends. Use when choosing a display mode, setting up split panes, troubleshooting backend issues, or configuring teammateMode.
error-handling
Debug and recover from agent team errors including common errors, hooks for quality gates, known limitations, and recovery strategies. Use when encountering team errors, enforcing quality gates with hooks, understanding limitations, or debugging agent issues.
messaging
Send messages between agents using SendMessage including direct messages, broadcasts, shutdown requests/responses, and plan approvals. Use when communicating between agents, understanding message formats, or handling structured protocol messages.