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.
git clone --depth 1 https://github.com/1EchA/context-sync-mcpWrote 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/rules/1echa/context-sync-mcp/context-sync)<a href="https://agentmods.dev/rules/1echa/context-sync-mcp/context-sync"><img src="https://agentmods.dev/badge/rules/1echa/context-sync-mcp/context-sync/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/rules/1echa/context-sync-mcp/context-sync"><img src="https://agentmods.dev/badge/rules/1echa/context-sync-mcp/context-sync.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 | $0.00725 | $0.00725 |
| Opus 5.5 | $0.00290 | $0.00290 |
| Sonnet 5.5 | $0.00145 | $0.00145 |
| Haiku 4.5 | $0.00072 | $0.00072 |
Grade A, and why
context-sync 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 2mo 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
上下文记忆规则（Context Sync MCP）
实时记录（自动，无需用户触发）
发现以下信息时，调用 write_context 工具批量写入：
-
避雷点/踩坑 →
file:"gotchas", action:"append"- 必须包含：现象、原因、解决方案、影响文件
- 写入后告知用户："⚠️ 已记录避雷点：[标题]"
-
架构决策 →
file:"architecture", action:"append"- 必须包含：决策、原因、权衡
- 写入后告知用户："📐 已记录架构决策：[决策]"
-
接口行为/限制 →
file:"api_notes", action:"append"- 包含：接口路径、行为特征、限制条件
-
完成待办项 →
file:"progress", action:"overwrite"- 更新完整的待办清单状态
-
如果新记录与已有记录有关联，在
related_to中标注（如["ADR-1", "踩坑#2"]）
可以在一次 write_context 调用中批量写入多个文件，减少工具调用次数。
/sync-init（用户手动，首次初始化）
当用户输入 /sync-init、“初始化上下文同步”、“初始化这个仓库的 context sync” 时：
- 调用
sync_init工具建立初始progress和summary - 如果项目已有
.context/，不要覆盖，提示用户改用/sync-load - 初始化完成后，告知用户后续使用
/sync-save保存增量、/sync-load恢复上下文
/sync-save（用户手动，推送到远程）
当用户输入 /sync-save、sync push、“保存上下文”、"上传上下文" 时：
- 确保 progress 和 summary 是最新的（如有需要先 write_context）
- 调用
sync_push工具推送到远程 - 告知用户推送结果
/sync-load（用户手动，从远程拉取）
当用户输入 /sync-load、sync pull、“拉取上下文”、"恢复上下文"、"新设备恢复上下文" 时：
- 调用
sync_load工具获取上下文 - 如返回引导信息，展示引导步骤
- 成功后重点关注：gotchas（避免踩坑）和 progress（继续进度）
- 向用户汇报恢复的上下文，询问继续哪个任务
命名约束
sync_push/sync_load是 MCP 内部工具名，不是给用户看的 slash 命令- 面向用户时，推送统一说
/sync-save - 面向用户时，拉取统一说
/sync-load；其中sync pull视为/sync-load的自然语言别名
主动提醒
- 完成大任务后提醒："如果要切换设备，可以
/sync-save推送上下文" - 本地有多条未推送记录时提醒用户
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.
- 2mo ago First seen · 57 lines · 725 tokens per session scan A 9c9ea711438f
context-sync is a cursor rule published in the GitHub repository 1EchA/context-sync-mcp (20 stars, last pushed 7mo ago), licensed MIT. It adds 725 tokens to every session, about $0.0029 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 cursor rules, from other repositories
mempalace-recall-always
Always-on MemPalace recall — search the palace before answering about past work, people, projects, or prior decisions.
dreamd-recall
Search dreamd at the start of a task and quote a hit. Append when the user corrects you or states a decision.
session-memory
Use at conversation wrap-up or when the user explicitly indicates end-of-session — capture residual lessons not captured in-flight.
common_memory_bank
I am Cursor, an expert software engineer with a unique characteristic: my memory resets completely between sessions. This isn't a limitation - it's what drives me to maintain perfect documentation. After each reset, I rely ENTIRELY on my Memory Bank to understand the project and continue work effectively. I MUST read…
self-improving-obsidian-llm-wiki
LLM Wiki OS operating rules.
memsprout
Cursor rule "memsprout" from memsprout/agents, covering using memsprout, search first, capturing, spaces and topics and files.