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 Zhong-y-j/Hubloom --skill account-accessgit clone --depth 1 https://github.com/Zhong-y-j/HubloomWrote 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/zhong-y-j/hubloom/account-access)<a href="https://agentmods.dev/skills/zhong-y-j/hubloom/account-access"><img src="https://agentmods.dev/badge/skills/zhong-y-j/hubloom/account-access/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/zhong-y-j/hubloom/account-access"><img src="https://agentmods.dev/badge/skills/zhong-y-j/hubloom/account-access.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 | $0.00094 | $0.00895 |
| Opus 5 | $0.00047 | $0.00447 |
| Sonnet 5 | $0.00019 | $0.00179 |
| Haiku 4.5 | $0.00009 | $0.00089 |
Grade A, and why
account-access 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 11d 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.
What it actually says
Account Access
本 Skill 规定：对话 Agent 不代办登录、改密、改用户资料；只处理权限失败时的说明，并引导用户到正确入口。
Hubloom 业务鉴权靠会话透传（侧栏「业务 Token」→ MCP）。聊天里收集密码、代调登录/改密/资料接口，一律禁止。
何时使用
- 工具结果为未登录 / Token 无效过期 / 无权限（401、403 等）
- 用户要：登录、退出、改密码、修改昵称/头像/手机/邮箱等资料
- 用户要 Agent：代调登录、发重置码、重置密码、更新用户资料等 Account/Identity 类接口
必须拒绝代办的操作（硬禁止）
以下需求 一律不要 list_api / call_api 去找或执行相关接口（即使 OpenAPI 里存在）：
- 登录 / 登出 / 刷新 Token（含账号密码登录、验证码登录）
- 修改密码、发送重置密码验证码、校验重置 Token、重置密码
- 修改用户资料（昵称、头像、手机、邮箱等账号属性）
- 任何「把密码/验证码交给我，我帮你调接口」的代办
拒绝时怎么回复（交 Respond）
用简短中文说明：
- 不能在对话里代办该操作（安全与产品约定）。
- 请用户自行处理：
- 业务调用无权限 → 到对话页**侧栏更新「业务 Token」**后重试原业务；
- 改密 / 改资料 / 登录 → 到产品官方账号中心 / App / 网页完成（不要在此聊天收集密码）。
- 不要追问邮箱、旧密码、新密码、验证码以便继续调工具。
- 不要提议「我先 list Account 工具再帮你走重置流程」。
Think 内部结论示例：「用户要改密 → account-access 禁止代办 → 交 Respond 拒绝并引导官方入口」。
唯一允许的相关处理：业务工具 401/403
当用户在办普通业务（小区、钥匙柜等）时工具返回未授权：
- 停止对同一调用死磕重试。
- 用人话说明登录态失效或权限不足（不回显 Token、不堆栈）。
- 引导更新侧栏「业务 Token」后重试原业务。
- 禁止因此去调用登录、改密、重置密码、改资料类工具「先登一下再继续」。
禁止项（红线）汇总
- 禁止为改密/登录/改资料去
list_api(Account|Identity|…)或call_api那些接口。 - 禁止在对话中收集或索要密码、验证码、完整 Token 以便代调。
- 禁止回显密钥；禁止声称已保存密码或可自动登录。
- 禁止用 schema 示例账号/假凭证尝试登录。
呈现
| 情况 | 建议 |
|---|---|
| 拒绝改密/登录/改资料 | 短 Markdown，无表单 |
| 业务 401/403，请更新侧栏 Token | 短 Markdown，无登录表单 |
Think：只写内部结论；完整对用户说明留给 Respond。勿输出 A2UI 改密/登录表单。
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.
- 11d ago First seen · 68 lines · 94 tokens per session scan A 04f32501b879
account-access is a skill published in the GitHub repository Zhong-y-j/Hubloom (14 stars, last pushed 28d ago), licensed Apache-2.0. It adds 94 tokens to every session and 895 once invoked, about $0.0005 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 2026-08-30.
Other skills, from other repositories
implementing-api-schema-validation-security
Implement API schema validation using OpenAPI specifications and JSON Schema to enforce input/output contracts and prevent injection, data exposure, and mass assignment attacks.
implementing-api-schema-validation-security
Implement API schema validation using OpenAPI specifications and JSON Schema to enforce input/output contracts and prevent injection, data exposure, and mass assignment attacks.
fastapi
FastAPI best practices and conventions. Use when working with FastAPI APIs, Pydantic models, dependencies, streaming responses including Server-Sent Events (SSE), and serving frontend apps. Keeps FastAPI code clean and up to date with the latest features and patterns.
printing-press-amend
Amend a published CLI from one of two input sources: (1) dogfood mode mines the active Claude Code session transcript for friction (missing flags, hand- rolled API payloads, silent-null returns); (2) direct-input mode accepts user-supplied asks (rename a command, add commands or feeds, fix a named bug, optionally…
datamodel-code-generator
Use this skill when the user wants Python data models, Pydantic models, dataclasses, TypedDicts, msgspec structs, or type-safe Python classes generated from OpenAPI, AsyncAPI, JSON Schema, GraphQL, JSON/YAML/CSV sample data, MCP tool schemas, Protocol Buffers, XML Schema, Apache Avro, or existing Python model objects.…
implementing-api-abuse-detection-with-rate-limiting
Implement API abuse detection using token bucket, sliding window, and adaptive rate limiting algorithms to prevent DDoS, brute force, and credential stuffing attacks.