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 agentmods add skills/rabithua/feedbackserverplugin/setup-feedback-servernpx skills add Rabithua/FeedbackServerPlugin --skill setup-feedback-servergit clone --depth 1 https://github.com/Rabithua/FeedbackServerPluginWhat 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 | $0.00059 | $0.00887 |
| Opus 5 | $0.00030 | $0.00443 |
| Sonnet 5 | $0.00012 | $0.00177 |
| Haiku 4.5 | $0.00006 | $0.00089 |
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 yesterday.
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 — 71 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Set up FeedbackKit
FeedbackKit uses the hosted https://api.feedkit.cn/mcp connector. Do not look for or run a local
MCP process, Bun runtime, CLI, local authentication store, or credential file. OAuth credentials
belong to the host and must never be requested, displayed, copied, or written by the Agent.
OAuth connection and account binding
Anonymous access is limited to MCP discovery and health. The authenticate tool is
OAuth2-protected with an empty scopes list. Its first invocation lets the host complete OAuth, but
OAuth success leaves the connection unbound and grants no FeedbackKit account access.
Install or upgrade the trusted feedback-server plugin, then select exactly one authentication
method from explicit user input. Do not guess between methods.
- Call
authenticate({ method: "email", value: email })with the user's exact email asvalue. The protected call causes the host to complete OAuth when needed; once OAuth returns, call the same method to bind the account. - Expect
pending_verification. Tell the user to click the one-time link in the email. Never ask the user to paste the link or any verification material into the conversation. - Observe completion with
authentication_status, respecting any returned retry timing. Continue only when the status reports that the account is bound.
Invitation
- Read the invitation code from the user-supplied invitation Prompt and call
authenticate({ method: "invitation", value: invitationCode }). Pass the code only asvalue; do not repeat it in chat, logs, commands, previews, or the final response. - The protected call causes the host to complete OAuth when needed; once OAuth returns, call the same method to bind the account.
- Successful invitation authentication binds immediately. Do not ask the user to enter anything in the OAuth browser or complete email verification.
After either method binds the account, call connection_status. If it still reports an unbound
connection, return to authenticate or authentication_status as directed; do not enter Product
onboarding early.
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.
- yesterday 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 2d ago), licensed MIT. It adds 59 tokens to every session and 887 once invoked, about $0.0003 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.
Other skills, from other repositories
trulens-evaluation-setup
Configure feedback functions and selectors for TruLens evaluations.
honesty-communication
当用户问怎么真诚沟通/拒绝别人/给反馈/不想说场面话、或发现自己在隐瞒时调用。 核心理念: 撒谎会先骗到自己(费曼: 你最容易愚弄的人是你); 彻底诚实=所想与所说一致; 具体表扬、一般批评; 秘密越少快乐越多。 不适用于: 需要外交辞令的谈判策略(可以诚实但不必全说)。 Triggers: 诚实/沟通/拒绝/批评/表扬/秘密/场面话/honesty/communication/feedback.
human-review
Open an HTML file, Markdown file, or localhost page in the browser so the user can edit text directly and leave comments on specific parts, then send all edits and comments back to you. Use after writing or updating something the user will read — specs, plans, reports, newsletter drafts, landing pages, slide decks…
Effective Memory
The essential habits for an AI agent with memory — session bookends, learning triggers, verification, safety, and the operational discipline that turns raw recall into compounding intelligence. Pinned, always-injected.
structured-code-review
Performs a structured five-stage code review covering requirements compliance, correctness, code quality, testing, and security/performance. Each stage uses targeted checklists and categorized feedback (Blocker/Major/Minor/Nit) with actionable suggestions and rationale. Use when the user asks for code review, PR…
self-improver
Review affiliate campaign results and improve strategy. Triggers on: "review my results", "what went wrong", "how to improve conversions", "analyze my campaign", "affiliate retrospective", "why am I not converting", "improve my strategy", "what should I change", "campaign review", "optimize my approach", "learn from…