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/franciszhangkk/claude-obsidian-multi-repo-trackerWrote 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/commands/franciszhangkk/claude-obsidian-multi-repo-tracker/update-active)<a href="https://agentmods.dev/commands/franciszhangkk/claude-obsidian-multi-repo-tracker/update-active"><img src="https://agentmods.dev/badge/commands/franciszhangkk/claude-obsidian-multi-repo-tracker/update-active/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/commands/franciszhangkk/claude-obsidian-multi-repo-tracker/update-active"><img src="https://agentmods.dev/badge/commands/franciszhangkk/claude-obsidian-multi-repo-tracker/update-active.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 | $0.00033 | $0.00916 |
| Opus 5 | $0.00016 | $0.00458 |
| Sonnet 5 | $0.00007 | $0.00183 |
| Haiku 4.5 | $0.00003 | $0.00092 |
Grade A, and why
update-active scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 11d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
What it actually says
/update-active — 更新当前焦点
何时调:切换任务、开始新功能、上次对话结束后。/commit 也会自动触发一次精简版。
设计原则:agent 产生草稿,用户只做确认或微调——不让用户从零打内容。
执行流程
1. 定位 vault 和项目
CODE_ROOT=$(git rev-parse --show-toplevel)
VAULT_PATH="${OBSIDIAN_VAULT_PATH:-}"
从 vault CLAUDE.md 映射表找到对应的 obsidian_project_path(同 sync-docs 第 2 步)。
找不到时用 AskUserQuestion 让用户选。
2. 读取信号(~300 token)
git log --oneline --no-merges -5 # 最近 commit 在做什么
git status --short # 现在改动的是哪些文件
git diff --stat HEAD # 未提交改动量级
同时读 activeContext.md 现有的"当前焦点"段(了解上一次写的是什么,避免重复)。
3. 生成焦点草稿
综合信号推断一句话草稿,格式:
<动作>:<具体在做什么>,<阶段>
例:
Memory 优化:去除幻觉 + 偏好晋升机制,联调测试中query-material-data skill 拆分:SQL 层完成,接入 skillruntime 中定时任务 API 联调:ad-plus-media-service ↔ ai-agents gRPC 接口对齐
推断规则:
- 最近 commit type 是
feat→ 功能开发阶段 - 最近 commit type 是
fix→ 修复阶段 - 有大量未提交改动(diff 行数 > 100)→ 开发进行中
- 文件路径含
test/_test.go→ 测试阶段 - 同一目录集中改动 → 聚焦该模块
4. 展示草稿,等待确认
当前焦点建议更新为:
"Memory 优化:去除幻觉 + 偏好晋升机制,联调测试中"
→ 回车确认 / 输入新内容替换 / s 跳过
用 AskUserQuestion,选项:
确认(使用以上内容)跳过(保持不变)自定义(other 输入)
5. 写入 activeContext.md
用 Edit 把"当前焦点"段内容替换:
## 当前焦点
<确认后的内容>
只动这一段,其他段(最近变更、下一步、阻塞)不动。
6. 输出报告
✅ 当前焦点已更新
Memory 优化:去除幻觉 + 偏好晋升机制,联调测试中
activeContext.md 已同步
如果用户跳过:
⏭️ 已跳过,当前焦点保持不变
注意事项
- 只改"当前焦点"段:不动最近变更(/sync-docs 维护)、不动下一步、不动阻塞
- 草稿推断失败时:直接让用户输入,不要强行生成无意义草稿
- 已有内容优先:如果现有焦点和推断结果差不多(关键词重叠 > 50%),不主动建议更新,直接输出
当前焦点未变更,无需更新
与 /commit 的关系
/commit 成功后会自动调用本流程的精简版(省略第 2 步读 git,直接用 commit message 推断),token 成本约 200。独立调用 /update-active 适合没有 commit 但切换了任务的场景。
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 · 106 lines · 33 tokens per session scan A 7b66d7c9082d
update-active is a command published in the GitHub repository franciszhangkk/claude-obsidian-multi-repo-tracker (2 stars, last pushed 4mo ago), licensed MIT. It adds 33 tokens to every session and 916 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 2026-08-31.
Other commands, from other repositories
unforgit
Show Unforgit repository-memory status and suggest the next useful action.
unforgit-curate
Review and improve Unforgit memory quality.
unforgit-health
Inspect Unforgit memory health.
unforgit-recall
Search Unforgit memory for context relevant to the user's current request.
sync
Sync memories with git remote (deprecated - SQLite is now authoritative).
unforgit-remember
Save durable project knowledge to Unforgit.