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.
npx skills add Rabithua/FeedbackServerPlugin --skill setup-feedback-servergit clone --depth 1 https://github.com/Rabithua/FeedbackServerPluginWrote 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.
[](https://agentmods.dev/skills/rabithua/feedbackserverplugin/setup-feedback-server)<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.
<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>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.
| Model | Per session | Once 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 |
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.
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:
- Enter the intended account email on the FeedbackKit login page.
- Open the one-time magic link sent to that inbox without pasting it into the conversation.
- 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, ordeferred. Do not infer a choice from silence or reuse waitlist metadata. Derive and show a readable slug, then callcreate_productwithname,slug,defaultLocale, andnotificationSetupPreference. 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 withset_notification_setup_preferencebefore declaring server-side setup complete.
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.
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.
- 2mo ago Changed · -8 lines · -1 tokens per session 82d019bd1ec4
- 2mo ago First seen · 71 lines · 59 tokens per session scan A 6276030bb8bc
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.
setup-feedback-server compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| setup-feedback-serverRabithua/FeedbackServerPlugin | Skill | 0 | 2mo ago | MIT | A | 58 | Claude Code, Codex |
| trulens-evaluation-setuptruera/trulens | Skill | 3.7k | 2d ago | MIT | A | 17 | Claude Code, Codex |
| honesty-communicationkangarooking/cangjie-skill | Skill | 13k | 1mo ago | MIT | A | 151 | Claude Code, Codex |
| agent-self-evalcoco-research/coco | Skill | 632 | yesterday | Apache-2.0 | A | 46 | Claude Code, Codex |
| code-review-qualityproffesor-for-testing/agentic-qe | Skill | 529 | yesterday | MIT | A | 33 | Claude Code |
| self-improverAffitor/affiliate-skills | Skill | 786 | 27d ago | MIT | A | 87 | Claude Code |
| Effective Memoryplur-ai/plur | Skill | 317 | yesterday | Apache-2.0 | A | 43 | Claude Code |