agentmods.dev

launch-report

launch-report is a skill for Claude Code from iampawan/Manifest. It costs 74 tokens per session (2,732 once invoked), scanned A, original, MIT.

A post-launch report that decides whether a software change landed, partly landed, or did not land. It compares the change’s goals with telemetry, errors, and user feedback at set points after release.

In plain words
What is it for?
Use it to review a contract’s success metrics and behavior after launch, typically on days 1, 7, 14, or 28, and produce a defensible verdict.
Why use it?
It answers whether a released feature actually worked, using evidence instead of relying only on the fact that it was deployed.

Skill for Claude Code

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

Part of the manifest plugin — 28 skills, 15 commands shipped together

not rated 5 3d ago A scan 74 tokens original MIT
View the source file iampawan/Manifest
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.

agentmods
npx agentmods add skills/iampawan/manifest/launch-report
Any agent
npx skills add iampawan/Manifest --skill launch-report
Clone the repo
git clone --depth 1 https://github.com/iampawan/Manifest

Made for: Claude Code.

Or install manifest, the plugin that ships this one along with the rest of its 28 skills, 15 commands.

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 launch-report

README.md
[![agentmods](https://agentmods.dev/badge/skills/iampawan/manifest/launch-report.svg)](https://agentmods.dev/skills/iampawan/manifest/launch-report)
Your own site
<a href="https://agentmods.dev/skills/iampawan/manifest/launch-report"><img src="https://agentmods.dev/badge/skills/iampawan/manifest/launch-report.svg" alt="Measured on agentmods" height="20"></a>
Per session 74 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,732 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00074 $0.02732
Opus 5 $0.00037 $0.01366
Sonnet 5 $0.00015 $0.00546
Haiku 4.5 $0.00007 $0.00273

Measured 6d ago against content hash a8485f007d21, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

launch-report 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/launch-report/SKILL.md · 289 lines

How it starts

The opening of the file, as written. The whole thing — 289 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Launch report agent

You produce the report that tells a dev owner whether their feature has actually landed. Quantitative side reads telemetry; qualitative side samples user feedback. The verdict has to be defensible — every claim ties back to evidence.

Inputs

  • Contract ID
  • Day index since launch: 1, 7, 14, or 28 (informs the report depth)
  • Optional: time window override

Process

1. Read the contract

.manifest/contracts/<ID>.md and the latest revision. Pull:

  • Success metrics with their eventName, target, window
  • Behaviors with instrumentation events and perf budgets
  • The launch date (from the deploy record or the contract frontmatter)

2. Pull quantitative data — auto-detect the best source

Not every project has client-side analytics. The skill picks the richest available source per contract and notes which one was used, so the report is honest about its data foundation.

Source priority (use the first available):

  1. Firebase Analytics MCP — if connected for this project. Query event counts per eventName from the success metric. Best for client-side user behavior.

  2. Amplitude MCP — same shape, alternative SDK.

  3. Server-side logs (Google Cloud Logging, Datadog, Loki) — if the success metric's eventName is emitted server-side, query the log aggregator for counts. Works for any backend-observable metric (most are).

  4. Database query — if the contract's success metric maps to a record-count question (e.g., "saved cards added in last 7 days"), run a direct query via a Postgres / database MCP. The contract's successMetrics can include a dbQuery field for this; if present, prefer it.

  5. Sentry's performance + release adoption — for "feature shipped without regression" metrics, Sentry alone is enough. Query release adoption % and error rate per release tag.

  6. Manual input — if none of the above is connected, read the contract's Slack thread for a message tagged [metric] <number> posted by a team member. Lowest-quality fallback but allows the report to run.

Read the full file on GitHub · 289 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. 6d ago First seen · 289 lines · 74 tokens per session scan A a8485f007d21

Subscribe to this mod's changes

launch-report is a skill published in the GitHub repository iampawan/Manifest (5 stars, last pushed 3d ago), licensed MIT. It adds 74 tokens to every session and 2,732 once invoked, about $0.0004 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.

Analytics and metricsGit and workflowReleases
Related

Other skills, from other repositories

agent-release-swarm

Agent skill for release-swarm - invoke with $agent-release-swarm.

ruvnet/ruflo · 19 tokens

release-announcement

Write a release announcement — changelog, blog post, in-app note, or social post — that leads with user impact, names the audience, and includes upgrade/migration steps without filler.

paperclipai/paperclip · 42 tokens

release

Cut a Symphony release by bumping the committed version, landing it, tagging the merged commit, and verifying the Burrito release workflow. Use when asked to release, tag, or retag Symphony.

openai/symphony · 42 tokens

changelog

Create changelog files for important commits in a PR.

pipecat-ai/pipecat · 13 tokens

multi-agent-release-manager

Cleans up the workspace, formats code, runs presubmit checks, and uploads CLs to Gerrit.

chromium/chromium · 27 tokens

refresh-arm-sdk-release

WORKFLOW SKILL — Prepares Azure.ResourceManager SDK refresh pull requests in azure-sdk-for-net. WHEN: "prepare sdk refresh", "refresh Azure.ResourceManager package", "update ARM SDK from autorest tag", "refresh changelog dependencies". INVOKES: git and GitHub pull request tools for branch, commit, push, and PR…

Azure/azure-sdk-for-net · 91 tokens