changelog-detective

changelog-detective is a skill for Claude Code from reatlat/fullstory-claude-plugin. It costs 60 tokens per session (1,493 once invoked), scanned A, original, MIT.

A workflow for finding what actually changed in a product by comparing session data from before and after a deployment or date. It looks for new behavior, errors, altered flows, and side effects.

In plain words
What is it for?
Use it when something feels different, when you suspect a recent change, or when you want to find new errors and user behaviors that were absent in the earlier comparison period.
Why use it?
Release notes describe intended changes, while user data can reveal changes that were undocumented or unexpected. This helps identify regressions and other differences after a release.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the fullstory-claude-plugin plugin — 46 skills, 3 agents, 1 MCP server shipped together

Good fit Use it when something feels different, when you suspect a recent change, or when you want to find new errors and user behaviors that were absent in the earlier comparison period.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/reatlat/fullstory-claude-plugin/changelog-detective
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 reatlat/fullstory-claude-plugin --skill changelog-detective
Clone the repo
git clone --depth 1 https://github.com/reatlat/fullstory-claude-plugin

Made for: Claude Code.

Or install fullstory-claude-plugin, the plugin that ships this one along with the rest of its 46 skills, 3 agents, 1 MCP server.

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 changelog-detective

README.md
[![agentmods](https://agentmods.dev/badge/skills/reatlat/fullstory-claude-plugin/changelog-detective/github.svg)](https://agentmods.dev/skills/reatlat/fullstory-claude-plugin/changelog-detective)
Your own site
<a href="https://agentmods.dev/skills/reatlat/fullstory-claude-plugin/changelog-detective"><img src="https://agentmods.dev/badge/skills/reatlat/fullstory-claude-plugin/changelog-detective/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 changelog-detective

Your own site · 80×15
<a href="https://agentmods.dev/skills/reatlat/fullstory-claude-plugin/changelog-detective"><img src="https://agentmods.dev/badge/skills/reatlat/fullstory-claude-plugin/changelog-detective.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 60 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,493 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. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
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 $0.00060 $0.01493
Opus 5 $0.00030 $0.00746
Sonnet 5 $0.00012 $0.00299
Haiku 4.5 $0.00006 $0.00149

Measured 12d ago against content hash c88b5d93a1aa, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

changelog-detective 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.

skills/changelog-detective/SKILL.md · 134 lines

How it starts

The opening of the file, as written. The whole thing — 134 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Changelog Detective

Find what actually changed after a deploy — not what the release notes say, but what the session data shows. Catch undocumented changes, side effects, and surprises.

When to Use

  • "What actually changed after the deploy?"
  • "Something feels different since Tuesday — what changed?"
  • "Check for undocumented changes in the last release"
  • "Did the deploy introduce any new user behaviors?"
  • "What new errors appeared this week that weren't here last week?"

Mental Model

Release notes tell you what was intended to change. Session data tells you what actually changed. These often differ. A "minor CSS fix" might accidentally break form validation. A "performance improvement" might introduce a new race condition. This skill hunts for the gaps between intent and reality.

Workflow

Step 1: Define the comparison window

Two time periods:

  • Before: 24-72 hours before the deploy/change date
  • After: 24-72 hours after (but not including the deploy window itself — things are chaotic during rollout)

Ask: "I'll compare 48 hours before and after the deploy (excluding the deploy hour). That OK?"

Step 2: Before/After diff — Errors

What errors existed before vs after?

fullstory:build_metric(query="errors by type", output_type="top_n")
fullstory:compute_metric(metric_id, time_range=before)
fullstory:compute_metric(metric_id, time_range=after)

Look for:

  • New errors: Error types that appear in After but not Before → these are deploy regressions
  • Resolved errors: Error types in Before but not After → these are fixed (celebrate these)
  • Changed errors: Same error type, different frequency → possible impact change

Step 3: Before/After diff — Frustrations

fullstory:get_opportunities(time_range=before)
fullstory:get_opportunities(time_range=after)
→ compare the lists

Look for:

  • New frustration signals: Rage clicks or dead clicks on elements that weren't problematic before
  • Resolved frustrations: Frustrations that disappeared (fix worked!)
  • Changed patterns: Same frustration, different page or device distribution

Read the full file on GitHub · 134 lines

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 · 134 lines · 60 tokens per session scan A c88b5d93a1aa

Subscribe to this mod's changes

changelog-detective is a skill published in the GitHub repository reatlat/fullstory-claude-plugin (62 stars, last pushed 1mo ago), licensed MIT. It adds 60 tokens to every session and 1,493 once invoked, about $0.0003 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 2026-08-30.