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 bosens-China/tc39-atlas --skill use-locigit clone --depth 1 https://github.com/bosens-China/tc39-atlasWrote 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/bosens-china/tc39-atlas/use-loci)<a href="https://agentmods.dev/skills/bosens-china/tc39-atlas/use-loci"><img src="https://agentmods.dev/badge/skills/bosens-china/tc39-atlas/use-loci/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/bosens-china/tc39-atlas/use-loci"><img src="https://agentmods.dev/badge/skills/bosens-china/tc39-atlas/use-loci.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 | $0.00081 | $0.02326 |
| Opus 5 | $0.00041 | $0.01163 |
| Sonnet 5 | $0.00016 | $0.00465 |
| Haiku 4.5 | $0.00008 | $0.00233 |
Grade A, and why
use-loci 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.
How it starts
The opening of the file, as written. The whole thing — 104 lines — stays where its author put it; the contents beside it link to each section on GitHub.
使用 Loci
优先使用 Loci 中用户指定的技术文档回答问题。先理解文档库结构,再按需读取相关文件和小节,避免一次加载整个文档库。
MCP 入口选择
- Agent 配置中只保留一个名为
loci的 MCP 入口。 - 本地 CLI MCP 可用时,优先使用 CLI 提供的 stdio 入口;不可用时再使用桌面端 HTTP 入口。
- 同时发现 CLI 与桌面端入口时,不要对两套重复工具执行相同操作。
- 入口使用的传输方式不影响下面的工具名、检索流程和安全边界。
与其他文档 Skill 共存
当前任务可能同时匹配 Context7 或其他第三方文档 Skill。允许客户端加载和读取这些 Skill,但匹配或加载不代表可以立即执行它们的查询步骤。除非用户明确指定某个来源,否则由客户端适用的全局或项目规则统一决定文档来源顺序。
完成 Loci 获取流程前,不调用其他文档来源:先查询本地库,再查询只读云端目录;云端存在可用快照时询问是否拉取;云端没有可用快照、用户不选择拉取或拉取失败时,确认官方入口并另行询问是否抓取。等待用户决定期间,不调用 Context7 或其他替代来源。
本地或云端未命中本身不构成切换条件。只有 Loci 不可用、无法确认官方入口且用户没有指定可用来源、用户拒绝官方抓取、已经提供官方抓取选项后所有已授权获取路径仍失败或没有文件,或者获得的 Loci 证据经过合理检索后仍不足时,才使用其他来源。切换前说明满足了哪一项条件;用户明确指定 Context7 等来源时,直接遵循当前请求。
基本流程
- 从用户问题和当前项目中识别相关技术及其版本。
- 调用
loci_list_libraries查询是否已有对应文档库。 - 本地存在且
pages > 0时,查看浅层目录树并记录返回的languages,再直接读取目标文件或搜索正文。 - 本地匹配项为 0 页时,把它视为不可用:正在同步则查询状态;空闲或失败则在用户已授权同步时重试。重试后仍为 0 页时继续云端或官网流程。
- 没有可用本地文档库时,调用
loci_list_cloud_libraries查询云端公开目录。 - 云端存在
pages > 0的匹配项时,取得用户确认后调用loci_pull_cloud_library;0 页候选、没有匹配项、查询或拉取失败、用户不选择拉取时,确认官方入口后取得用户同意,再调用loci_add_library创建并首次抓取。 - 需要搜索时,把概念性关键词转换为目录树
languages对应的语言,再调用loci_search_files。 - 根据目录或搜索结果调用
loci_read_files阅读相关文件或完整小节。 - 根据读取结果回答,附上相关
source_url,并区分文档事实与 Agent 推断。
目录与搜索
把目录树作为理解文档库结构和搜索语言的主要入口。获得本地文档库后,先调用 loci_get_library_tree 查看一至两层,读取顶层 languages 并了解主题、模块、版本和相邻文件,再决定直接读取还是搜索。readable=true 的文件节点还会返回该文件的 language。
- 目录已经暴露明确目标文件时,直接批量读取少量相关文件。
- 用户给出明确的 API、配置项、命令或错误信息时,可以并行调用
loci_get_library_tree和loci_search_files。 - 仅凭目录无法确认目标文件时,使用搜索定位文件及小节。
搜索时优先使用 API 名称、配置键、组件名、命令和错误信息等准确关键词。loci_search_files 的 queries 使用数组,一次传入 1–10 组互补的查询,结果按查询分组返回。library_ids 也可以是多个文档库 ID,两个数组可以组合使用。首次未命中时尝试少量同义词、全称或缩写,不要立即遍历整个文档库。
搜索语言
- 把
loci_get_library_tree返回的顶层languages作为搜索语言依据,不要为了探测语言而额外读取代表文件。例如包含zh或zh-CN时,使用“响应式原理”、“依赖追踪”等中文概念,不要只搜索英文翻译词。 - API 名称、类名、函数名、配置键、CLI 命令和错误原文保持原样,不做翻译。
- 需要查找多个相关表述时,把文档语言对应的关键词放入同一个
queries数组,例如{"queries":["响应式原理","依赖追踪","副作用"]}。 languages只包含und或文件language与正文不符时,根据目录标题判断语言,必要时在queries中同时提交可能的文档语言和英文关键词。
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.
- 11d ago First seen · 104 lines · 81 tokens per session scan A 243bc9181b14
use-loci is a skill published in the GitHub repository bosens-China/tc39-atlas (0 stars, last pushed today), licensed MIT. It adds 81 tokens to every session and 2,326 once invoked, about $0.0004 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
create-pr
Creates a GitHub PR with a Linear-ticket-prefixed title and a decision-led, narrative description for Prisma 8. Use when the user wants to create a pull request, open a PR, or submit changes for review.
triage-contributor-pr
Triage open pull requests from external contributors to prisma/prisma and produce a per-PR verdict with evidence. Use when a maintainer asks to triage, evaluate, assess, or review the queue of incoming contributor PRs, to decide whether a fork PR is safe to run CI on, to check whether a PR is in scope for its version…
contrib-pr
Open a high-quality external contributor PR against prisma/orm. Use when the user is an outside contributor (not a Prisma maintainer) and wants to submit a change as a pull request from a fork. Encodes the contribution flow from CONTRIBUTING.md so the resulting PR passes review on the first round.
github-review-iteration
Orchestrates a GitHub PR review loop by delegating triage and implementation to dedicated sub-agents, then repeating until actionable review items are cleared. Use when the user says “address PR review”, “triage review comments”, or “iterate until review is clean”.
publish-npm-version
Cuts the next release of Prisma 8: bumps the root package.json version (on the v8 RC line: 8.0.0-rc.N → rc.N+1), propagates it to every workspace package, and opens a PR titled "chore(release): bump to ". When the maintainer merges the PR, the Publish to npm workflow runs automatically and ships the new version to npm…
review-implement-phase
Implements triaged review actions, commits focused fixes, and posts Done plus resolves threads. Use when the user wants only the implementation phase of the review-framework workflow.