spec-analytics

spec-analytics is a skill for Claude Code from tomzx/agents. It costs 35 tokens per session (483 once invoked), scanned A, original, MIT.

A workflow for defining how a product initiative will be measured, including events, conversion funnels, dashboards, success metrics, and guardrails. Guardrails are limits that help detect harmful side effects while a target metric improves.

In plain words
What is it for?
Use it to specify the data events needed for measurement, map where users convert or drop off, design dashboards, set alerts, and plan measurement windows.
Why use it?
It prevents a team from improving one number while accidentally worsening other important parts of the product.

Skill for Claude Code

Written for Claude Code: argument-hint in frontmatter.

Good fit Use it to specify the data events needed for measurement, map where users convert or drop off, design dashboards, set alerts, and plan measurement windows.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/tomzx/agents/spec-analytics
View source ↗ tomzx/agents
Install

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.

Any agent
npx skills add tomzx/agents --skill spec-analytics
Clone the repo
git clone --depth 1 https://github.com/tomzx/agents

Made for: Claude Code.

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 spec-analytics

README.md
[![agentmods](https://agentmods.dev/badge/skills/tomzx/agents/spec-analytics/github.svg)](https://agentmods.dev/skills/tomzx/agents/spec-analytics)
Your own site
<a href="https://agentmods.dev/skills/tomzx/agents/spec-analytics"><img src="https://agentmods.dev/badge/skills/tomzx/agents/spec-analytics/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 spec-analytics

Your own site · 80×15
<a href="https://agentmods.dev/skills/tomzx/agents/spec-analytics"><img src="https://agentmods.dev/badge/skills/tomzx/agents/spec-analytics.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 35 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 483 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 $0.00035 $0.00483
Opus 5 $0.00017 $0.00242
Sonnet 5 $0.00007 $0.00097
Haiku 4.5 $0.00003 $0.00048

Measured 6d ago against content hash 06550776d6fd, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

spec-analytics 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 6d 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.

skills/pdlc/skills/spec-analytics/SKILL.md · 44 lines

What it actually says

Spec Analytics

Defines how an initiative will be measured at runtime. It is guardrail-first: it specifies the guardrail metrics (what must not regress) alongside the success metrics, because the classic failure is moving the metric you measured while breaking three you did not. This artifact is the PDLC counterpart to SDLC's telemetry plan; it can feed SDLC instrumentation.

Prerequisites

  • Apply the shared PDLC conventions in skills/pdlc/references/shared.md.
  • acceptance-contract.md and goals.md (the SM-N and GM-N definitions).

Steps

  1. List the analytics events required to compute every success metric (SM-N) and guardrail metric (GM-N) from goals.md. Each event has a name, trigger, and payload.
  2. Define the conversion funnels that reveal where value is created or lost.
  3. Define the dashboards: one per objective, showing success and guardrail metrics together so regressions are visible next to gains.
  4. For each guardrail, define the alert threshold and the response (who is paged, what is the rollback).
  5. Define the measurement windows: the early-window launch signals (from launch-plan.md) and the steady-state cadence.
  6. Flag metrics whose measurement source is not yet instrumented; route these to SDLC as instrumentation work.
  7. Write analytics-spec.md to the initiative directory.

Output Format

Use the template at skills/pdlc/templates/initiatives/analytics-spec.md. Reference SM-N / GM-N IDs from goals.md.

Outcome

If $OUTCOME_YAML is set, emit verdict: drafted.

Completion Checklist

  • Every SM-N and GM-N has a defined event source
  • Guardrails have alert thresholds and a response owner
  • Dashboards pair success and guardrail metrics
  • Uninstrumented metrics flagged for SDLC

Next Step

After launch, load review-metrics to read the actuals.

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. 6d ago First seen · 44 lines · 35 tokens per session scan A 06550776d6fd

Subscribe to this mod's changes

spec-analytics is a skill published in the GitHub repository tomzx/agents (6 stars, last pushed yesterday), licensed MIT. It adds 35 tokens to every session and 483 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 2026-09-03.

Related

Other skills, from other repositories