onsite-measure

onsite-measure is a skill for Claude Code from shalintripathi/organic-os. It costs 40 tokens per session (474 once invoked), scanned A, original, MIT.

A follow-up measurement process for website changes after they have been published. It compares search clicks, views, click rate, and position after 7 or 28 days with an earlier period, while recording when the cause is uncertain.

In plain words
What is it for?
Use it to measure approved page changes through Google Search Console, Google's service for website search data. It records results when data is available and honestly marks them as unmeasured when no connection to that data exists.
Why use it?
It closes the loop between a change and its result without treating a before-and-after movement as proof that the change caused it.

Skill for Claude Code

Written for Claude Code: $CLAUDE_PLUGIN_ROOT variable.

Runs only inside its plugin — its command needs a path that Claude Code sets for a plugin’s own hooks and for nothing else. Install the plugin, not this.

Part of the organic-os plugin — 24 skills, 24 commands, 14 agents shipped together

Good fit Use it to measure approved page changes through Google Search Console, Google's service for website search data. It records results when data is available and honestly marks them as unmeasured when no connection to that data exists.

Compare 6 skills from other repositories ↓
Install

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.

Claude Code
/plugin marketplace add shalintripathi/organic-os
Claude Code
/plugin install organic-os

Made for: Claude Code.

Or install organic-os, the plugin that ships this one along with the rest of its 24 skills, 24 commands, 14 agents.

Wrote 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.

agentmods badge for onsite-measure

README.md
[![agentmods](https://agentmods.dev/badge/skills/shalintripathi/organic-os/onsite-measure/github.svg)](https://agentmods.dev/skills/shalintripathi/organic-os/onsite-measure)
Your own site
<a href="https://agentmods.dev/skills/shalintripathi/organic-os/onsite-measure"><img src="https://agentmods.dev/badge/skills/shalintripathi/organic-os/onsite-measure/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.

agentmods 80×15 button for onsite-measure

Your own site · 80×15
<a href="https://agentmods.dev/skills/shalintripathi/organic-os/onsite-measure"><img src="https://agentmods.dev/badge/skills/shalintripathi/organic-os/onsite-measure.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 40 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 474 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00040 $0.00474
Opus 5 $0.00020 $0.00237
Sonnet 5 $0.00008 $0.00095
Haiku 4.5 $0.00004 $0.00047

Measured 12d ago against content hash 71911de7aa65, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

onsite-measure 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.

plugin/skills/onsite-measure/SKILL.md · 34 lines

What it actually says

Measure outcomes (closing the loop)

  1. Scan outcomes/ for records with a due measurement date <= today that lack that measurement.
  2. Per record: pull GSC for the target URL - clicks/impressions/CTR/position for the 7 (or 28) days after the change vs the same window before. GSC data lags 2-3 days: fetch the day-7 window no earlier than day 10, and the day-28 window no earlier than day 31. No GSC connector: record "unmeasured (no GSC)" honestly.
  3. Append the delta to the outcome record + one signal line ("outcome : position 8.2 -> 5.9 after title rewrite"). "After" is a sequence, not a cause. Attributing the move to the change follows the attribution rule (canonical in hoo-daily's anomaly section, step 2.7): the claim, the comparison actually run, and what would falsify it - for example "compared the 28 days after against the same 28-day window before, same URL; if the site-wide trend moved the same way over those windows, the change is not what did it." Where that comparison was not run, the record reads cause: unknown (before/after window not compared) and keeps the delta. A measured number with an honest unknown is what lets the reflector score a skillbook entry later; a confident story that nobody checked teaches the loop the wrong lesson.
  4. Wins and losses BOTH matter: the reflector reads outcomes to score skillbook entries helpful/harmful. At day-28, set the item to measured via PYTHONPATH="$CLAUDE_PLUGIN_ROOT/lib" python3 -m core status <item-path> measured --actor agent. Never edit brain frontmatter directly. The contract CLI is the only write path for status and approvals.
Changes

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.

  1. 12d ago First seen · 34 lines · 40 tokens per session scan A 71911de7aa65

Subscribe to this mod's changes

onsite-measure is a skill published in the GitHub repository shalintripathi/organic-os (5 stars, last pushed 4d ago), licensed MIT. It adds 40 tokens to every session and 474 once invoked, about $0.0002 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.

Related

Other skills, from other repositories

seo-vertical-detect

Classify a website as ecommerce, local-business, blog-publisher, saas, docs, or generic (multiple may apply), and report detected locales, from the persisted PageSnapshot plus the platform detector's vertical hints. Used by seo-orchestrator to decide which conditional modules to run and how to reweight the scores.

Hainrixz/claude-seo-ai · 71 tokens

seo-fix-apply

Writer protocol preloaded into the seo-fixer-writer agent — how confirmed SEO/AI-search fixes are applied (git pre-flight, backup, Edit/Write for local diffs, ticketed adapter CLIs for remote targets, re-verify, publish only on a second ticket, rollback) and the findings-array output contract. Used only by the fix…

Hainrixz/claude-seo-ai · 91 tokens

audit

Audit a website or web codebase for SEO and AI-search (GEO/AEO) — produces two independent 0-100 scores (Search SEO + AI Visibility) plus a prioritized, evidence-backed report persisted on disk. Read-only; never writes to the project. Use when the user asks to audit, analyze, check, or score a site's SEO, structured…

Hainrixz/claude-seo-ai · 127 tokens

ai-visibility

Fast-path AI visibility — get a brand's 0–100 Akii Visibility Score (computed by an open-source LLM judge against the brand's public footprint) with four-dimension breakdown AND a per-engine proxy map for ChatGPT, Claude, Gemini, Perplexity, Copilot, and Google AI Overviews based on FirstPageSage signal weights.…

akii-technologies-ltd/akii-seo-ai-search-optimizer · 290 tokens

seo-audit

Single audit entry point — surface-level scorecard or deep infrastructure dive depending on the requested mode. Default full mode produces a multi-layer scorecard across all 9 areas (crawlability, indexation, meta tags, headings, images, Core Web Vitals, JS rendering, mobile + security, structured data, internal…

akii-technologies-ltd/akii-seo-ai-search-optimizer · 321 tokens

optimize-page

Comprehensive single-page optimization across all three layers — traditional SEO (title / meta / H1 / internal links), AEO (chunk quality, direct-answer leads, FAQ extraction), and GEO rewrites using the tactics published by the Princeton/IIT Delhi GEO study (citation integration, expert quotes, statistics enrichment…

akii-technologies-ltd/akii-seo-ai-search-optimizer · 199 tokens