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-milestones/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-milestones)<a href="https://agentmods.dev/skills/fitlab-ai/agent-infra/init-milestones"><img src="https://agentmods.dev/badge/skills/fitlab-ai/agent-infra/init-milestones/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/fitlab-ai/agent-infra/init-milestones"><img src="https://agentmods.dev/badge/skills/fitlab-ai/agent-infra/init-milestones.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00027 | $0.00843 |
| Opus 5.5 | $0.00011 | $0.00337 |
| Sonnet 5.5 | $0.00005 | $0.00169 |
| Haiku 4.5 | $0.00003 | $0.00084 |
Grade A, and why
init-milestones 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 1mo 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
初始化 milestones
一次性初始化仓库的标准 milestones 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 - 请求的 milestone 参数已准备完成
如果任一条件失败,停止并输出对应错误。
2. 运行 milestones runtime intent
执行以下命令,完成整套里程碑初始化流程:
agent-infra-internal platform-metadata init-milestones $ARGUMENTS
runtime intent 与 .agents/rules/label-milestone-setup.md 共同负责:
- 接收
--history请求并规划目标里程碑 - 按既定基线、history、状态和标题幂等契约生成结果
- 由 runtime/provider 读取并写入当前里程碑
- 输出最终执行摘要
3. 标准里程碑定义
按固定描述创建以下里程碑:
General Backlog:All unsorted backlogged tasks may be completed in a future version.(state=open){major}.{minor}.x:Issues that we want to resolve in {major}.{minor} line.(state=open)- 具体版本:兼容默认来源使用基线
0.1.0;合法 tag 来源使用{major}.{minor}.{patch+1}。描述为Issues that we want to release in v{version}.(state=open)
当传入 --history 时,每个历史 vX.Y.Z tag 还会额外贡献:
X.Y.x作为开启状态的线里程碑X.Y.Z作为关闭状态的版本里程碑(state=closed)
4. 输出与行为保证
摘要必须包含:
- 版本基线
- 版本基线来源
- 是否启用
--history - 创建与跳过的里程碑数量
- 新创建的里程碑标题
- 已存在的里程碑标题
执行说明:
- Milestone titles are treated as the idempotency key.
- General Backlog 是未分类工作的兜底里程碑。
- 不带
--history时,只创建一个标准版本里程碑:兼容默认来源使用基线0.1.0,合法 tag 来源使用下一次 patch 版本。 - 历史
X.Y.Ztag 会生成开启状态的X.Y.x和关闭状态的X.Y.Z。 - 标签较多的仓库可能触发平台 API rate limit。
5. 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}。
输出 milestones 初始化摘要后,提示:
使用 agent-infra-internal agent-client next-steps --skill init-labels 生成本场景的 {next-step-commands}。
下一步 - 初始化 Labels(可选):
{next-step-commands}
错误处理
- 平台能力、认证或仓库访问失败:如实报告 runtime 的非零退出状态和诊断输出;不得声称远端已变更。
- 版本解析失败:报告 runtime 返回的版本基线错误
--history模式下未找到合法 SemVerv*git tags:报告 runtime 返回的 history 诊断- 权限不足:提示 "No permission to manage milestones in this repository"
- API 限流:提示 "platform API rate limit reached, please retry later"
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.
- 1mo ago Changed · -2 lines 311fa4aeeb1a
- 1mo ago Changed · -2 lines 9a6c5c396c3f
- 1mo ago First seen · 88 lines · 27 tokens per session scan A 59ea6be1f300
init-milestones is a skill published in the GitHub repository fitlab-ai/agent-infra (86 stars, last pushed yesterday), licensed MIT. It adds 27 tokens to every session and 843 once invoked, about $0.0001 per session on Opus 5.5. 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
plan-tree
Maintain a structured planning document tree made of roadmap/status files, implementation status or handoff TODO files, topic notes, decision records, open questions, ideas/inspiration pools, and repository/file-structure hygiene plans. Use when Codex needs to create, reorganize, audit, or update a multi-file plan…
tokenrip-cli
The rip CLI for Tokenrip, the shared workspace your AI agents work from: load a workspace and pick up where the work left off, publish artifacts (documents, HTML, code, CSV, PDFs, living tables) into it, organize folders, propose an action for a person to approve before it goes out, report finished work, decide…
quality
Evaluates whether a GitHub issue is spam, empty, needs more information, or is OK to proceed.
follow-up-after-call
Use after a completed customer, prospect, partner, or important internal sales call, discovery session, demo, or conversation, including when the user supplies or uploads a transcript, notes, recording summary, or other grounded evidence. Advise on, assess, qualify, recap, and produce seller-ready follow-up actions…
persona-event-coordinator
Plan and manage events — scheduling, invitations, and logistics.
persona-project-manager
Coordinate projects — track tasks, schedule meetings, and share docs.