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/manage-waitlistnpx skills add Rabithua/FeedbackServerPlugin --skill manage-waitlistgit 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 | $0.00055 | $0.00563 |
| Opus 5 | $0.00028 | $0.00282 |
| Sonnet 5 | $0.00011 | $0.00113 |
| Haiku 4.5 | $0.00006 | $0.00056 |
Grade A, and why
manage-waitlist 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.
What it actually says
Manage the FeedbackServer waitlist
Waitlist entries belong to the connected administrator and are not Product-scoped. Do not ask for a
Product. Use status, platform, and search filters; archived entries are hidden unless explicitly
requested. Follow nextCursor for the requested range. Treat email as private contact data and
include it only when the task needs it.
update_waitlist_status and add_waitlist_note are direct internal writes after resolving the exact
entry. Valid status values are new, contacted, invited, converted, and archived. Do not
substitute archive for a requested permanent deletion or vice versa.
Invitation email is a protected external effect. Use invite_waitlist_entry to preview the exact
recipient, language, App, subscription grant, invitation expiry, and email summary. The default is
Free. Solo and Studio require an explicit month, year, or perpetual term; ask when the user names a
paid plan without a term and never infer one. Show that preview, wait for explicit approval, then call
execute_confirmation with the returned ID. Apply the same confirmation gate to
retry_waitlist_invitation_email. Use revoke_waitlist_invitation when the user asks to cancel a
pending invite; revocation prevents acceptance but cannot recall mail already accepted by the
provider. These tools require both the OAuth scope waitlist:invite and a current database
super_admin role. The recipient may paste the complete invitation Prompt into the current Agent
conversation. Pass its invitation code only to
authenticate({ method: "invitation", value: invitationCode }); do not repeat it in chat,
commands, logs, previews, tool output, or the final response.
An invited signup cannot be permanently deleted until its pending invitation is revoked. Acceptance
uses the setup workflow: host OAuth first creates an unbound connection, then invitation
authentication binds it immediately and onboarding continues through connection_status. Never ask
the recipient to enter the invitation code in a browser or complete email verification. Never ask
for a username, display name, or password.
Permanent deletion requires confirmation. Show the returned App, platform, and note-count preview,
wait for explicit approval, then call execute_confirmation with the returned ID. Confirmation is
single-use and expires after ten minutes. For stale state, reread and prepare a new preview; never
retry writes automatically.
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 · 40 lines · 55 tokens per session scan A 82f68d48eca3
manage-waitlist is a skill published in the GitHub repository Rabithua/FeedbackServerPlugin (0 stars, last pushed 3d ago), licensed MIT. It adds 55 tokens to every session and 563 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…