manage-feedback-server

manage-feedback-server is a skill for Claude Code, Codex from Rabithua/FeedbackServerPlugin. It costs 62 tokens per session (418 once invoked), scanned A, original, MIT.

A routing guide for FeedbackServer, a service for managing app feedback, waitlists, roadmaps, releases, and notifications. It selects the focused tool for each request.

In plain words
What is it for?
Use it when a request spans several FeedbackServer areas or does not clearly belong to setup, feedback, waitlists, publishing, notifications, or administration.
Why use it?
It prevents broad or unclear requests from being sent to the wrong workflow or handled with unsupported methods.

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 a request spans several FeedbackServer areas or does not clearly belong to setup, feedback, waitlists, publishing, notifications, or administration.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/rabithua/feedbackserverplugin/manage-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 manage-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 manage-feedback-server

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

Your own site · 80×15
<a href="https://agentmods.dev/skills/rabithua/feedbackserverplugin/manage-feedback-server"><img src="https://agentmods.dev/badge/skills/rabithua/feedbackserverplugin/manage-feedback-server.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 62 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 418 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 $0.00062 $0.00418
Opus 5.5 $0.00025 $0.00167
Sonnet 5.5 $0.00012 $0.00084
Haiku 4.5 $0.00006 $0.00042

Measured 2mo ago against content hash 5e0738fc949d, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

manage-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/manage-feedback-server/SKILL.md · 32 lines

What it actually says

Route FeedbackServer 2.0 work

Use the smallest focused skill that covers the request:

  • $setup-feedback-server for installation, browser OAuth, magic-link sign-in, whoami, connection diagnosis, first-Product setup, and App integration.
  • $triage-feedback for inspecting, organizing, replying to, or deleting Product feedback and diagnostics.
  • $manage-waitlist for owner-scoped signup follow-up, invitation, and deletion.
  • $publish-roadmap-releases for Developer Posts, public roadmap Items, Releases, translations, or App Store changelog import.
  • $configure-notifications for Bark and Product webhook configuration or deliveries.
  • $administer-feedback-server for Products, subscriptions, account access, invitations, keys, audit, and attachments outside triage.

Use only documented remote feedback-server MCP tools. There is no local CLI exception. Never use direct SQL, production shell access, or undocumented HTTP routes. Start with whoami when identity matters, resolve exact IDs with list/get tools, and do not mutate for requests that only ask to inspect, draft, preview, plan, or summarize.

An explicit request to change Feedback status or visibility, or to send a specified Feedback reply, authorizes that exact ordinary write without a duplicate chat confirmation. Other tools marked risky prefer native MCP elicitation. If elicitation is unavailable and the tool returns confirmation_required, show its target and exact redacted effect, wait for explicit approval, then repeat the same operation with unchanged arguments plus confirm: true. Never use a confirmation identifier, change the payload on the confirmed call, or retry a mutation automatically.

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 · +6 lines · -1 tokens per session 5e0738fc949d
  2. 2mo ago First seen · 26 lines · 63 tokens per session scan A b9a5b6bd8d6f

Subscribe to this mod's changes

manage-feedback-server is a skill published in the GitHub repository Rabithua/FeedbackServerPlugin (0 stars, last pushed 2mo ago), licensed MIT. It adds 62 tokens to every session and 418 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

manage-feedback-server compared with skills from other repositories

manage-feedback-server next to 6 skills from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
manage-feedback-serverRabithua/FeedbackServerPluginSkill02mo agoMITA62Claude 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