setup-feedback-server

setup-feedback-server is a skill for Claude Code, Codex from Rabithua/FeedbackServerPlugin. It costs 58 tokens per session (810 once invoked), scanned A, original, MIT.

A setup assistant for FeedbackKit, a service for collecting and managing app feedback. It connects your account, creates the first product, and helps add the Apple app connection.

In plain words
What is it for?
Use it when installing or upgrading FeedbackKit, authenticating by email or invitation, creating the first product, integrating the Apple SDK, or checking setup status.
Why use it?
It removes the guesswork from first-time installation, sign-in, account linking, and diagnosing connection problems.

Skill for Claude CodeCodex

Written for Claude Code and Codex: shipped in a Claude Code plugin, but also agents/openai.yaml present. Also seen: $skill-name invocation.

Part of the feedback-server plugin — 7 skills shipped together

Good fit Use it when installing or upgrading FeedbackKit, authenticating by email or invitation, creating the first product, integrating the Apple SDK, or checking setup status.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/rabithua/feedbackserverplugin/setup-feedback-server
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 Rabithua/FeedbackServerPlugin --skill setup-feedback-server
Clone the repo
git clone --depth 1 https://github.com/Rabithua/FeedbackServerPlugin

Made for: Claude Code, Codex.

Or install feedback-server, the plugin that ships this one along with the rest of its 7 skills.

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 setup-feedback-server

README.md
[![agentmods](https://agentmods.dev/badge/skills/rabithua/feedbackserverplugin/setup-feedback-server/github.svg)](https://agentmods.dev/skills/rabithua/feedbackserverplugin/setup-feedback-server)
Your own site
<a href="https://agentmods.dev/skills/rabithua/feedbackserverplugin/setup-feedback-server"><img src="https://agentmods.dev/badge/skills/rabithua/feedbackserverplugin/setup-feedback-server/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 setup-feedback-server

Your own site · 80×15
<a href="https://agentmods.dev/skills/rabithua/feedbackserverplugin/setup-feedback-server"><img src="https://agentmods.dev/badge/skills/rabithua/feedbackserverplugin/setup-feedback-server.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 58 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 810 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 $0.00058 $0.00810
Opus 5.5 $0.00023 $0.00324
Sonnet 5.5 $0.00012 $0.00162
Haiku 4.5 $0.00006 $0.00081

Measured 2mo ago against content hash 82d019bd1ec4, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

setup-feedback-server 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 2mo 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.

plugins/feedback-server/skills/setup-feedback-server/SKILL.md · 63 lines

How it starts

The opening of the file, as written. The whole thing — 63 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Set up FeedbackKit 2.0

FeedbackKit uses the remote Streamable HTTP MCP at https://api.feedkit.cn/mcp. Do not run a local MCP process, install a runtime, configure an API token, or create a credential file. OAuth tokens, browser sessions, and emailed magic links belong to the host and user; never request, display, copy, or persist them.

Connect and sign in

For an ordinary existing account, connect the trusted feedback-server plugin to the hosted MCP. For invitation onboarding, read only mcp_server and account_email from the supplied invitation instructions, connect to that server, and use that email in the browser. Do not look for any other invitation credential.

Call whoami as the first protected MCP tool. When the host needs a connection, that call starts Better Auth OAuth 2.1 in the browser. Tell the user to:

  1. Enter the intended account email on the FeedbackKit login page.
  2. Open the one-time magic link sent to that inbox without pasting it into the conversation.
  3. Return to the browser flow and approve the requested scopes.

When the host reports a successful connection, call whoami. For an invitation, require its returned email to match account_email; on a mismatch, stop Product work and reconnect with the correct account. Do not treat the browser redirect alone as proof of the active identity.

Create or select a Product

Call list_products immediately after whoami:

  • With no Products, ask for the App name, platform (iOS, iPadOS, macOS, Android, or Web), default locale, and one explicit notification preference: bark, webhook, or deferred. Do not infer a choice from silence or reuse waitlist metadata. Derive and show a readable slug, then call create_product with name, slug, defaultLocale, and notificationSetupPreference. Leave status active, feedback private, and diagnostics disabled unless the user requested otherwise.
  • With one Product, read its current settings and verify that it is the requested App. With several, ask the user to select one and never guess an ID.
  • If the selected Product still reports notificationSetupPreference: "unresolved", collect the missing choice and persist it with set_notification_setup_preference before declaring server-side setup complete.

Read the full file on GitHub · 63 lines

Files

What ships with it

1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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. 2mo ago Changed · -8 lines · -1 tokens per session 82d019bd1ec4
  2. 2mo ago First seen · 71 lines · 59 tokens per session scan A 6276030bb8bc

Subscribe to this mod's changes

setup-feedback-server is a skill published in the GitHub repository Rabithua/FeedbackServerPlugin (0 stars, last pushed 2mo ago), licensed MIT. It adds 58 tokens to every session and 810 once invoked, about $0.0002 per session on Opus 5.5. 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

setup-feedback-server compared with skills from other repositories

setup-feedback-server next to 6 skills from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
setup-feedback-serverRabithua/FeedbackServerPluginSkill02mo agoMITA58Claude Code, Codex
trulens-evaluation-setuptruera/trulensSkill3.7k2d agoMITA17Claude Code, Codex
honesty-communicationkangarooking/cangjie-skillSkill13k1mo agoMITA151Claude Code, Codex
agent-self-evalcoco-research/cocoSkill632yesterdayApache-2.0A46Claude Code, Codex
code-review-qualityproffesor-for-testing/agentic-qeSkill529yesterdayMITA33Claude Code
self-improverAffitor/affiliate-skillsSkill78627d agoMITA87Claude Code
Effective Memoryplur-ai/plurSkill317yesterdayApache-2.0A43Claude Code