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 Alice-space/alice --skill alice-goalgit clone --depth 1 https://github.com/Alice-space/aliceWrote 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/alice-space/alice/alice-goal)<a href="https://agentmods.dev/skills/alice-space/alice/alice-goal"><img src="https://agentmods.dev/badge/skills/alice-space/alice/alice-goal/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/alice-space/alice/alice-goal"><img src="https://agentmods.dev/badge/skills/alice-space/alice/alice-goal.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 | $0.00015 | $0.02130 |
| Opus 5 | $0.00008 | $0.01065 |
| Sonnet 5 | $0.00003 | $0.00426 |
| Haiku 4.5 | $0.00002 | $0.00213 |
Grade A, and why
alice-goal 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 — 101 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Alice Goal
在当前 work session 中设定并自动迭代执行的长期目标。
命令
scripts/alice-goal.sh get- 查看当前目标scripts/alice-goal.sh create '{"objective":"为项目补充单元测试","deadline_in":"48h"}'- 创建目标（deadline_in 可选，默认 48h）scripts/alice-goal.sh delay <duration> <reason>- 每一轮对话必须调用，设置下一轮迭代的延迟唤醒时间scripts/alice-goal.sh pause- 暂停scripts/alice-goal.sh resume- 恢复scripts/alice-goal.sh complete- 仅限audit_completionsubagent 调用，Main Agent 在任何情况下都不得直接调用此命令scripts/alice-goal.sh clear- 删除目标
核心机制
自动循环原理
每次 Main Agent（即本次设定 alice-goal 的 Agent）迭代完成后，系统通过 delay 机制调度下一次唤醒。Main Agent 必须在每轮迭代结尾显式调用 alice-goal delay 来声明下一次唤醒时间。不调用 delay 的迭代视为违规。
三个合法出口（每轮迭代必须且只能选择其一）：
| 出口 | 调用 | 效果 |
|---|---|---|
| 立即继续 | alice-goal delay 0s "继续推进 <具体任务>" |
当前有明确工作可做，立即进入下一轮 |
| 延迟等待 | alice-goal delay 17m "等待 <具体外部资源>" |
当前在等待外部资源就绪，延迟后再唤醒检查 |
| 目标完成 | 由 audit_completion 调用 alice-goal complete |
审计确认目标已全部完成 |
delay 命令详细说明
alice-goal delay <duration> <reason> 设置目标下一次被引擎唤醒的时间。
核心约束：delay 只能用于等待外部资源。
没有需要等待的外部资源（CI、构建、部署、数据文件、API 配额、第三方服务等），就必须用 0s 立即继续推进，或触发僵局重新规划。严禁用正延迟来偷懒或躲避工作。
参数：
duration（必填）：Go duration 格式的相对延迟，类型为字符串- 格式：
"Ns","Nm", 可组合如"1m30s" - 范围：
"0s"或1m ~ 30m（引擎强制校验） "0s"= 立即进入下一轮迭代（当前有明确工作可推进）- 最小正延迟为
"1m"，最大延迟为"30m"（不在此范围内的 duration 会被拒绝）
- 格式：
reason（必填）：用引号括起来的一句话，必须明确写明正在等待的具体外部资源"0s"时必须说明下一步具体要做什么- 正延迟时 必须 写明等待的具体外部资源名称（如 CI pipeline、GitHub PR、构建系统、数据文件路径、API 端点等）
选取延迟的指导：
- 等待 CI/构建/部署完成 →
"7m"~"17m"（选"8m"/"13m"/"17m"等非整点值） - 等待 code review / PR 状态更新 →
"13m"~"27m"（选"13m"/"19m"/"27m"等非整点值） - 等待外部资源就绪（数据文件、权限、API 配额等） →
"7m"~"19m"（选"8m"/"13m"/"19m"等） - 严禁选取的值：
- 不要选
"5m""10m""15m""20m""30m"等整数边界值——选临近的非整点值如"7m""13m""17m""23m""28m" - 不要选
< 1m的正值（引擎直接拒绝） - 不要选
> 30m的值（引擎直接拒绝）
- 不要选
- 严禁以下场景使用正延迟：
- "当前无实质工作可推进" → 触发僵局重新规划，而不是设一个延迟混过去
- "需要用户确认或输入" → 用户可能不会回复，设正延迟等于空转。此时应设
0s并明确说明需要用户输入，或暂停目标 - "审计确认目标已完成" → 必须走 audit_completion → alice-goal complete 流程
What ships with it
2 files 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 · 101 lines · 15 tokens per session scan A 29be7615fdf6
alice-goal is a skill published in the GitHub repository Alice-space/alice (5 stars, last pushed 1mo ago), licensed MIT. It adds 15 tokens to every session and 2,130 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 2026-08-31.
Other skills, from other repositories
codebase-classification
Classify codebases before modification to choose appropriate development approach.
python-repl
Interactive Python REPL automation with common helpers and best practices.
expert-agent-manager
Manage octo's agent profiles through conversation — create, modify, delete, list, and bind agents to IM chats by calling REST APIs. This skill is exclusive to the Default Agent (full-access). Use when the user wants to manage agents conversationally, e.g. "create a code review agent", "list all agents", "bind agent X…
onboard
Onboard a new user OR curate a single piece of the assistant's inner state. Without arguments, runs the full first-run ceremony (AI name, personality, user profile, soul.md + user.md). With scope:soul or scope:user, runs a quick chat to update just that one profile file. With path: , runs a quick chat to update / keep…
queue-workflow
Queue-first continuation and review workflow for clisbot queues. Use when work needs deliberate follow-up against early stopping, shallow passes, prompt echoing, history leaking, duplicate files/functions/sections, naming drift, DRY/KISS regressions, missing docs/tests, or bad fallback behavior.
web-diff-review
A skill for opening diffs in difit for user review, or for reviewing a specific diff or PR first and preloading findings into difit as inline comments. Use it after code changes, for commit or branch comparisons, or when a human-readable web diff with anchored comments is the best review surface.