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 Playa-0v0/Cyrene-Agent --skill cyrene-plan-modegit clone --depth 1 https://github.com/Playa-0v0/Cyrene-AgentWrote 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/playa-0v0/cyrene-agent/cyrene-plan-mode)<a href="https://agentmods.dev/skills/playa-0v0/cyrene-agent/cyrene-plan-mode"><img src="https://agentmods.dev/badge/skills/playa-0v0/cyrene-agent/cyrene-plan-mode/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/playa-0v0/cyrene-agent/cyrene-plan-mode"><img src="https://agentmods.dev/badge/skills/playa-0v0/cyrene-agent/cyrene-plan-mode.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 | $0.00037 | $0.02755 |
| Opus 5 | $0.00018 | $0.01378 |
| Sonnet 5 | $0.00007 | $0.00551 |
| Haiku 4.5 | $0.00004 | $0.00276 |
Grade A, and why
cyrene-plan-mode 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 — 432 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Cyrene Plan Mode(计划模式)
概述
Plan Mode(计划模式)用于在真正动手修改之前,帮助 Cyrene:
- 理解用户真正想解决的问题;
- 调查当前项目的实际实现;
- 和用户讨论重要方案与取舍;
- 找出遗漏、风险与边界;
- 将讨论收敛为一份可供用户审批的实施计划。
目标不是“尽快写出一份计划”。
目标是:
让用户能够放心点击批准,因为重要事实、关键决策、实现边界和验证方式都已经讨论清楚。
核心流程:
理解 → 落地事实 → 讨论 → 查漏 → 收敛 → 写计划
不要从用户最初提出的一个想法,直接跳到最终计划。
1. 先理解用户真正的目标
开始设计实现方案之前,先判断用户真正想得到什么结果。
需要区分:
- 目标:用户最终希望得到的行为或结果。
- 提议:用户当前提出的一种可能实现方式。
- 约束:必须保持不变、不能违反的条件。
- 偏好:用户倾向某个方向,但仍可能继续讨论。
- 验收标准:满足什么条件才算真正完成。
不要把“用户提出的一种实现方式”自动当成最终需求。
例如:
“能不能加一个 finish tool(结束工具)?”
这可能只是一个实现提议。
用户真正想解决的问题可能是:
“避免 Executor(执行器)在任务还没真正完成时就提前结束。”
讨论实现方式时,始终记住真正目标。
保留用户已经拍板的决定
用户明确确认过的决定,应视为 Confirmed Decision(已确认决策)。
除非:
- 用户之后主动修改;
- 或新的项目事实证明该决定无法成立。
不要因为“还有其他合理方案”,就不断重新打开已经结束的讨论。
如果新的事实与用户已确认决定发生冲突,应明确指出冲突,而不是偷偷替换用户决定。
2. 先确认项目事实,再讨论项目实现
涉及现有代码库时,任何项目特定结论都应优先建立在真实代码与工具观察之上。
使用只读工具建立 Workspace Ground Truth(工作区事实依据)。
优先确认:
- 实际源文件;
- 配置;
- 类型与接口;
- 调用点;
- 当前状态流转;
- 权限检查;
- 测试;
- UI(用户界面)流程;
- 项目已经存在的设计模式。
不要因为“类似项目一般会这样做”,就假设当前项目中存在某个:
- 文件;
- 目录;
- 函数;
- 状态;
- 模块;
- API(接口);
- 生命周期。
始终区分三类信息
Confirmed(已确认)
来自:
- 用户明确决定;
- 或当前项目实际代码/工具结果。
Assumption(假设)
目前合理,但尚未验证。
Open Question(待确认)
仍然需要:
- 继续调查;
- 或由用户拍板。
不得把 Assumption(假设)和 Open Question(待确认)写成 Confirmed(已确认事实)。
3. 能自己查到的,不要先问用户
在向用户提出技术问题之前,先判断:
- 这个答案能不能通过只读工具从当前项目中确认?
- 项目里是否已经存在类似实现,可以作为约定参考?
- 这个问题到底是技术事实,还是只有用户才能决定的产品取舍?
如果能通过项目调查得到答案,优先调查。
真正需要询问用户的情况通常包括:
- 两种行为都合理,需要用户选择产品语义;
- 范围存在真实歧义;
- Compatibility(兼容性)行为必须由用户选择;
- 存在不可逆或高成本取舍;
- 用户偏好本身决定正确架构。
询问时应尽量把选择说具体。
推荐:
批准 Plan(计划)后有两个合理行为:
A. 立即开始执行;
B. 只解除限制,等待用户下一条消息再执行。
你希望哪个?
不要只问:
“你想怎么做?”
4. 讨论目标,而不是只优化第一个方案
用户或模型提出方案后,不要立即围绕这个方案继续堆细节。
先确认:
- 它真正解决了什么问题?
- 是否真的满足用户目标?
- 是否引入新的 State(状态)?
- 是否改变 Lifecycle(生命周期)?
- 是否可以复用项目已有机制?
- 谁是 Source of Truth(事实来源)?
- 失败时发生什么?
- 重复触发时发生什么?
- 跨 Turn(对话轮)或 Run(执行轮)时发生什么?
- 用户能看到什么?
- 哪些决定继续交给模型?
- 哪些不变量必须由 Runtime(运行时)保证?
优先选择:
能够满足需求的最小机制。
What ships with it
4 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 · 432 lines · 37 tokens per session scan A f144214f7a80
cyrene-plan-mode is a skill published in the GitHub repository Playa-0v0/Cyrene-Agent (581 stars, last pushed today), licensed MIT. It adds 37 tokens to every session and 2,755 once invoked, about $0.0002 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
project-setup-info-local
Comprehensive setup steps to help the user create complete project structures in a VS Code workspace; this tool is designed for full project initialization and scaffolding, not for creating individual files. When to use this tool: user wants to create a new complete project from scratch; setting up entire project…
github-copilot-upgrader
Use this to update the Github Copilot CLI/SDK.
commit
Commit staged or unstaged changes with an AI-generated commit message that matches the repository's existing commit style. Use when the user asks to 'commit', 'commit changes', 'create a commit', 'save my work', or 'check in code'.
sync
Sync the current session branch with its upstream branch, or publish the current session branch to a remote. Use when the user asks to sync a branch, pull latest changes, rebase onto upstream, push current branch, publish branch, or set upstream.
generate-run-commands
Generate or modify run commands for the current session. Use when the user wants to set up or update run commands that appear in the session's Run button.
merge
Merge changes from the topic branch to the merge base branch. Use when the user wants to merge their session's work back to the base branch.