Borrowing it
Nothing to install: this file belongs to fitlab-ai/agent-infra. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/fitlab-ai/agent-infra/main/.agents/skills/init-labels/SKILL.mdgit clone --depth 1 https://github.com/fitlab-ai/agent-infraWrote 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/fitlab-ai/agent-infra/init-labels)<a href="https://agentmods.dev/skills/fitlab-ai/agent-infra/init-labels"><img src="https://agentmods.dev/badge/skills/fitlab-ai/agent-infra/init-labels.svg" alt="Measured on agentmods" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00026 | $0.01124 |
| Opus 5 | $0.00013 | $0.00562 |
| Sonnet 5 | $0.00005 | $0.00225 |
| Haiku 4.5 | $0.00003 | $0.00112 |
Grade A, and why
init-labels 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 today.
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 — 107 lines — stays where its author put it; the contents beside it link to each section on GitHub.
初始化 labels
一次性初始化仓库的标准 labels 体系。
执行流程
1. 验证前置条件
确认以下条件成立：
- 执行前先读取
.agents/rules/label-milestone-setup.md - 仓库配置和请求的映射已准备完成
如果任一条件失败，停止并输出对应错误。
2. 运行 labels runtime intent
执行以下命令，完成整套 label 初始化流程：
agent-infra-internal platform-metadata init-labels
runtime intent 与 .agents/rules/label-milestone-setup.md 共同负责：
- 读取配置的
labels.in映射并保留无关 label - 选择平台能力，或返回明确的 no-op/degraded 结果
- 创建或更新标准 label 集合并输出最终摘要
- 输出最终执行摘要
3. 标准分类体系
脚本管理以下通用 label 族：
type:labels，例如type: bug、type: enhancement、type: feature、type: documentation、type: dependency-upgrade、type: taskstatus:labels，例如status: waiting-for-triage、status: in-progress、status: waiting-for-internal-feedback- 明确覆盖的 平台默认同名 labels：
good first issue和help wanted - 额外通用 labels，例如
dependencies
适用范围
| Label 前缀 | Issue | PR | 说明 |
|---|---|---|---|
type: |
— | Yes | Issue 使用 平台原生 Type 字段；PR 无原生类型字段，需 type: label 驱动 changelog |
status: |
Yes | — | PR 有自身状态流转（Open/Draft/Merged/Closed）；Issue 使用 status: label 标记项目管理状态 |
in: |
Yes | Yes | Issue 和 PR 均需按模块筛选 |
4. 配置 in: label 映射
检查 .agents/.airc.json 中是否已有 labels.in 字段。
4.1 已有映射
展示当前映射，询问用户是否需要更新。
- 不需要：跳到步骤 4.3
- 需要：按步骤 4.2 处理
4.2 无映射或用户要求更新
- 扫描项目顶层目录，排除隐藏目录和常见构建目录。
- 分析目录内容，给出有意义的模块分组建议。
- 向用户展示建议的
in:label 映射，并根据自然语言反馈迭代调整。 - 如果用户拒绝配置，则为每个顶层目录生成 1:1 默认映射（
{dir}/）。
4.3 写入配置并创建 label
- 将最终映射写入
.agents/.airc.json的labels.in字段。 - 执行
agent-infra-internal platform-metadata init-labels，为每个映射 key 创建或更新in: {key}label。 - 询问用户确认后，再使用
--cleanup-stale-in重新执行 intent，清理不在最终映射中的旧in:label。
5. 输出与行为保证
摘要必须包含：
- 创建或更新的通用 labels 数量
- 写入的
labels.in映射结果 - 按映射 key 计算的
in:labels 数量 - 名称完全匹配的平台预置 labels 已被覆盖的说明
- 仍然存在的未匹配平台预置 labels
执行说明：
- 整个操作具备幂等性，因为 provider 叶子会按覆盖或更新方式处理已有 label。
in:labels 由 AI 引导步骤和.airc.json映射统一管理。
6. 告知用户
渲染下一步前先读取
.agents/rules/next-step-output.md，仅为已选场景调用统一 helper，并将 stdout 填入{next-step-commands}。
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.
- today Changed 617256aba2bf
- 4d ago Changed · -1 lines 26e582ffb009
- 8d ago First seen · 108 lines · 26 tokens per session scan A 7b3dcf9de66a
init-labels is a skill published in the GitHub repository fitlab-ai/agent-infra (83 stars, last pushed yesterday), licensed MIT. It adds 26 tokens to every session and 1,124 once invoked, about $0.0001 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
dream
Batch-execute SHIP-ready wishes overnight — pick wishes, orchestrate workers, review PRs, wake up to results.
clickup
Use when managing ClickUp tasks, sprints, or comments via the cup CLI tool. Triggers: task queries, status updates, sprint tracking, creating subtasks, posting comments, threaded replies, standup summaries, searching tasks, checking overdue items, assigning tasks, listing spaces and lists, opening tasks in browser…
sw-do
Implement a SpecWeave increment task by task through the ledger, with evidence per task and a verified close. Use for "implement this", "start working", "continue the increment", "keep going".
handoff
Write a portable, secret-scrubbed handoff doc so this work can continue in any AI tool or on any machine. Use when saying "handoff", "running out of tokens", or "continue elsewhere".
genie-orca-wish
Turn a brainstorm/design into an APPROVED-able wish whose Dispatch plan is the literal input to Orca tasks and Linear issues. High-reasoning pass: pre-decide everything so fast workers can execute without judgment calls.
auto
Run an increment unattended - the Stop hook feeds you back into the loop until every task is done. Use when saying "auto mode", "run until done", or "ship this while I sleep".