Getting it into your agent
This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.
/plugin marketplace add ZachArticulateV/designer-pro-and-seo/plugin install designer-pro-and-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/zacharticulatev/designer-pro-and-seo/seo-drift)<a href="https://agentmods.dev/skills/zacharticulatev/designer-pro-and-seo/seo-drift"><img src="https://agentmods.dev/badge/skills/zacharticulatev/designer-pro-and-seo/seo-drift/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/zacharticulatev/designer-pro-and-seo/seo-drift"><img src="https://agentmods.dev/badge/skills/zacharticulatev/designer-pro-and-seo/seo-drift.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 | $0.00106 | $0.02026 |
| Opus 5 | $0.00053 | $0.01013 |
| Sonnet 5 | $0.00021 | $0.00405 |
| Haiku 4.5 | $0.00011 | $0.00203 |
Grade A, and why
seo-drift 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 12d 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 — 123 lines — stays where its author put it; the contents beside it link to each section on GitHub.
seo-drift
Family: seo Status: Stable
Purpose
Baseline + diff for SEO state — "git for SEO." Capture a page's SEO-critical elements,
store the snapshot, then after a deploy or content change diff a fresh capture against
the stored baseline to catch silent regressions before they cost rankings. Two modes:
a quick one-off JSON baseline (drift_tools.py), or a local SQLite history
(drift_baseline/compare/history) that remembers every snapshot so you can compare and
trend over time. Works offline on local HTML or by fetching a URL through the shared
SSRF guard.
Triggers
- "seo drift" / "baseline" / "deployment check"
- "track changes" / "did anything break" / "seo regression"
- "compare seo" / "before and after" / "monitor seo changes"
Inputs
- A URL (fetched, SSRF-guarded) or local HTML file
- Mode: a one-off JSON baseline+diff, or a stored SQLite baseline / compare / trend
- Optional: a
--dbpath (default<cwd>/.seo-drift/baselines.dbunder your workspace; it refuses to default inside the plugin — run from your project, or pass--dbto a path under your workspace), a--label(e.g.prod,pre-deploy), a--baseline-id
Steps
- Capture a baseline into the SQLite store (before a deploy, or at handoff):
Records title, meta description, h1, canonical, meta robots, OG tags, schema-block count, h2 count, and word count (the canonical capture set frompython3 "${CLAUDE_PLUGIN_ROOT}/scripts/seo/drift_baseline.py" --url <URL> --db .seo-drift/baselines.db --label pre-deploy # or --file page.htmldrift_tools.py), tagged with a timestamp and label, indexed by URL. - Compare after a change against the stored baseline:
Resolves the latest baseline for that URL (orpython3 "${CLAUDE_PLUGIN_ROOT}/scripts/seo/drift_compare.py" --url <URL> --db .seo-drift/baselines.db--label/--baseline-id), captures fresh, and runs the severity engine. It treats addingnoindex/nofollowand a canonical flip or drop as critical, title / h1 / schema-loss changes as high, and meta-description / OG / h2 / word-count drift as advisory (word-count moves under 20% are suppressed as editing noise). Full rationale:references/seo-drift/severity-model.md. - Trend the history to see drift across deploys:
Lists stored baselines, or withpython3 "${CLAUDE_PLUGIN_ROOT}/scripts/seo/drift_history.py" --url <URL> --db .seo-drift/baselines.db --trend--trendreports the per-transition change count and critical/high/advisory tally — a regression timeline where a deploy that quietly added noindex shows up as a critical-count spike. - Quick one-off (no store): for a single before/after without history, use the
original JSON path —
drift_tools.py --capture --out baseline.json, thendrift_tools.py --diff --baseline baseline.json. Same capture set; the JSON baseline is a plain file you can commit. - Interpret. Walk the regressions worst-first: intended change or accident? Fix any
critical/high immediately. The store design is documented in
references/seo-drift/sqlite-schema.md.
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.
- 12d ago First seen · 123 lines · 106 tokens per session scan A acb3f052a9d2
seo-drift is a skill published in the GitHub repository ZachArticulateV/designer-pro-and-seo (8 stars, last pushed 2mo ago), licensed MIT. It adds 106 tokens to every session and 2,026 once invoked, about $0.0005 per session on Opus 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 2026-08-31.
Other skills, from other repositories
release-retrospective
Produce a structured look-back after a major release or deprecation — capturing what the plan got right, what it missed, and what to do differently. Trigger when someone says: release retrospective, post-release review, what went wrong with the release, how did the deprecation go, release post-mortem, retro on the…
version-bump-advisor
Recommend the correct semver bump with reasoning and a generated changelog entry. Trigger when someone says: what version bump, is this a breaking change, semver recommendation, should this be major or minor, version this release, changelog entry, what kind of release is this, or anything about versioning a design…
parallel-execution-strategy
Use when 3+ independent tasks are ready in .forge/tasks.yaml and multiple agents will work concurrently, when assessing file-conflict risk before dispatching parallel work, when planning branch and merge sequencing for a sprint, or when prior parallel runs have caused merge nightmares.
git-workflow
Use when committing work, creating branches, preparing PRs, resolving merge conflicts, when grouping related changes into commits, when cleaning up history before merging, or when deciding what should be a separate commit vs squashed.
pick-up-task
Pick up or resume a task from dev/TODO.md — marks [WIP], creates or switches to the task's feature branch, rebases with main. Use when the user invokes /pick-up-task or asks to grab/resume a pastiche task.
release-pastiche
Ship a pastiche release — version bump, plugin build, CHANGELOG entry, release commit, tag, GitHub Release, milestone close. Use when the user invokes /release-pastiche after a TODO group's final feat→main merge. Human-triggered only; never run from an automated routine.