OpenSEO is an open-source SEO platform for keyword research, rank tracking, competitor analysis, backlink analysis, site audits, and AI visibility work. It connects SEO data to AI agents through an MCP server and reusable agent skills, while allowing users to supply their own DataForSEO API key and self-host the tool. Catalogue add-ons guide agents through OpenSEO's SEO workflows.
Borrowing it
Nothing to install: this file belongs to every-app/open-seo. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/every-app/open-seo/main/.agents/skills/evaluate-skill/SKILL.mdgit clone --depth 1 https://github.com/every-app/open-seoWrote 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/every-app/open-seo/evaluate-skill)<a href="https://agentmods.dev/skills/every-app/open-seo/evaluate-skill"><img src="https://agentmods.dev/badge/skills/every-app/open-seo/evaluate-skill/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/every-app/open-seo/evaluate-skill"><img src="https://agentmods.dev/badge/skills/every-app/open-seo/evaluate-skill.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 | $0.00066 | $0.01527 |
| Opus 5.5 | $0.00026 | $0.00611 |
| Sonnet 5.5 | $0.00013 | $0.00305 |
| Haiku 4.5 | $0.00007 | $0.00153 |
Grade A, and why
evaluate-skill 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 27d 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 — 90 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Evaluate a skill
A skill edit is only as good as the reports it produces. This workflow runs the candidate skill in sessions that know nothing except the skill file, a one-line business brief, and a locked-down local MCP endpoint, then compares what came back.
Prerequisites
- Local server in no-auth mode:
AUTH_MODE=local_noauthin.env.local, thenpnpm db:migrate:localandpnpm dev(orpnpm dev:agents). Pass the URL it prints, with/mcpappended, as--endpoint. Default local D1, never remote bindings or remote Postgres. Keep it private; it has no login. codexCLI on the path. Runs use its configured default model at high reasoning; record the resolved model from the events log if you need to name it.- Research credits: the local server still calls DataForSEO. An audit run makes 20 to 40 tool calls. Do not run more sessions than the comparison needs.
Run
node .agents/skills/evaluate-skill/scripts/run.mjs \
--skill seo-audit \
--site example.com --site holdout.example \
--brief "Evaluation brief: Acme at example.com sells <what>. The goal is relevant organic visitors who could become customers. No first-party analytics are connected." \
--brief "Evaluation brief: <the holdout business>. ..." \
--endpoint http://<local-dev-host>/mcp
Runs take about 10 to 14 minutes and execute in parallel. Launch the script detached, because a tool-call timeout that kills the shell kills the sessions too:
(nohup node .agents/skills/evaluate-skill/scripts/run.mjs ... > .logs/eval.log 2>&1 &)
What the script does, per site:
- Copies the candidate skill and
seo-reportinto a fresh temp folder. Edits during the run cannot change its instructions; the manifest records the skill hashes. - Creates a new local project seeded only with the brief.
- Starts a gateway in front of the local MCP that allows a fixed tool list and rejects any call for another project id, then probes that rejection before starting.
- Runs
codex execephemeral, ignoring user config, memories, apps, plugins, and multi-agent, with the skill's self-review as the only reviewer. - Captures the saved report HTML, every MCP call and response, the event stream, and the final message under the output folder.
What ships with it
2 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.
- 27d ago First seen · 90 lines · 66 tokens per session scan A b422c5c36578
evaluate-skill is a skill published in the GitHub repository every-app/open-seo (23,850 stars, last pushed 3d ago), licensed MIT. It adds 66 tokens to every session and 1,527 once invoked, about $0.0003 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 2026-09-20.
Other skills, from other repositories
playground
Launches a local WordPress Playground site with The SEO Framework mounted, captures front-end SEO artifacts, and compares before/after plugin states. Use when testing regressions, reproducing bugs, changing meta/sitemap/robots/ schema/oEmbed/admin SEO output, checking WordPress version behavior, plugin conflicts, or…
wp-finalize-run
The check detail of the /wp-finalize run, split out of commands/wp-finalize.md so the command stays a short map — bilingual coverage, theme structure, the WP-CLI runtime validation, the GEO and agent-readiness report, and the three demo-parity layers (static, WP-CLI, measured visual parity). Use when /wp-finalize…
wp-demo-verify-run
The step detail of the /wp-demo-verify run, split out of commands/wp-demo-verify.md so the command stays a short map — Step 2a (the impeccable detector and its gate), Step 2b (the scroll walk, Firefox pass, --no-motion, fractional widths and the exit-code 2 fallback) and Step 3 (reading every finding kind). Use when…
test-master
Generates test files, creates mocking strategies, analyzes code coverage, designs test architectures, and produces test plans and defect reports across functional, performance, and security testing disciplines. Use when writing unit tests, integration tests, or E2E tests; creating test strategies or automation…
verify-omnigent
Drive Omnigent the way a user does and prove a behavior with recorded evidence, using an isolated server, runner, and mock model plus a feature map of every user entry point. Load before reproducing a user-facing bug, before claiming a fix works, or when reviewing whether a change covered every surface (session vs.…
dogfood
Systematically explore and test a mobile app on iOS/Android with agent-device to find bugs, UX issues, and other problems. Use when asked to dogfood, QA, exploratory test, find issues, bug hunt, or test this app on mobile.