deploy-radar

deploy-radar is a skill for Claude Code from reatlat/fullstory-claude-plugin. It costs 38 tokens per session (879 once invoked), scanned A, original, MIT.

A post-deployment validation workflow for comparing user and product signals before and after a software release. It checks errors, conversion, and user frustration around a deployment time.

In plain words
What is it for?
Use it after a deployment to compare error rates, network or console failures, conversion, and frustration signals before and after the release.
Why use it?
It helps reveal regressions and newly introduced problems that may not be visible from the release notes. Comparing time windows shows whether the release may have changed important outcomes.

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 after a deployment to compare error rates, network or console failures, conversion, and frustration signals before and after the release.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/reatlat/fullstory-claude-plugin/deploy-radar
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 deploy-radar
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 deploy-radar

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

Your own site · 80×15
<a href="https://agentmods.dev/skills/reatlat/fullstory-claude-plugin/deploy-radar"><img src="https://agentmods.dev/badge/skills/reatlat/fullstory-claude-plugin/deploy-radar.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 38 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 879 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 $0.00038 $0.00879
Opus 5 $0.00019 $0.00439
Sonnet 5 $0.00008 $0.00176
Haiku 4.5 $0.00004 $0.00088

Measured 10d ago against content hash 8efa4a8ccfc4, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

deploy-radar 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 10d 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/deploy-radar/SKILL.md · 92 lines

How it starts

The opening of the file, as written. The whole thing — 92 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Deploy Radar

Post-deploy health check: compare key metrics before and after a deploy to catch regressions, new errors, and conversion changes.

When to Use

  • "I just deployed — did anything break?"
  • "Check if the 3pm deploy caused any issues"
  • "Compare error rates before and after the July 15 deploy"
  • "Did the checkout change improve or hurt conversion?"

Workflow

Step 1: Define the deploy window

Get the deploy timestamp from the user. If they say "3pm today" or "just deployed", pin to the nearest hour.

Define two time windows:

  • Before: e.g., 24 hours before deploy (or last 7 days if it was a big release)
  • After: e.g., from deploy time to now

Ask: "I'll compare the 24 hours before and after the deploy. That OK, or do you want a wider window?"

Step 2: Check errors

Build an error metric and compute it for both windows:

fullstory:build_metric(query="console errors and network failures", output_type="single_number")
fullstory:compute_metric(metric_id, time_range=before_window)
fullstory:compute_metric(metric_id, time_range=after_window)

Also check for new errors that didn't exist before:

fullstory:build_metric(query="console errors", output_type="top_n")
→ compute for after window, compare to before window
→ flag error types that appear only in the after window

Step 3: Check frustrations

Call fullstory:get_opportunities for the after window. For each, call fullstory:get_opportunity_stats. Check if any opportunity's rate-of-change vs the before window shows a spike.

Quick sanity check: rage click count before vs after. If it doubled, the deploy introduced friction.

Step 4: Check conversion

Pick 1-2 key funnels (checkout, signup):

fullstory:compute_metric(funnel_metric_id, time_range=before_window)
fullstory:compute_metric(funnel_metric_id, time_range=after_window)

Step 5: Report

## Deploy Health — v2.3.0 (Aug 4 15:00 UTC)

### Errors
- Before: 12 errors (24h window)
- After: 14 errors (+17%) 🟡
- New: TypeError on /checkout (3 occurrences, did not exist before) 🔴

### Frustrations
- Rage clicks: 87 before → 92 after (+6%) 🟢 (within normal variance)
- Dead clicks: stable
- No new opportunity signals detected 🟢

### Conversion
- Checkout completion: 21% before → 20% after (-5%) 🟡
- Signup completion: 64% → 63% (-2%) 🟢

### Verdict: Deploy is mostly clean. The new TypeError on /checkout is worth investigating — 3 users in 24h, looks like a null check regression. Want me to dig into those sessions?

Read the full file on GitHub · 92 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. 10d ago First seen · 92 lines · 38 tokens per session scan A 8efa4a8ccfc4

Subscribe to this mod's changes

deploy-radar is a skill published in the GitHub repository reatlat/fullstory-claude-plugin (62 stars, last pushed 28d ago), licensed MIT. It adds 38 tokens to every session and 879 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 2026-08-30.