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 agentmods add commands/jasonhnd/life_os/searchgit clone --depth 1 https://github.com/jasonhnd/life_OSWrote 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/jasonhnd/life_os/search)<a href="https://agentmods.dev/commands/jasonhnd/life_os/search"><img src="https://agentmods.dev/badge/commands/jasonhnd/life_os/search.svg" alt="Measured on agentmods" 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 | $0.00026 | $0.00644 |
| Opus 5 | $0.00013 | $0.00322 |
| Sonnet 5 | $0.00005 | $0.00129 |
| Haiku 4.5 | $0.00003 | $0.00064 |
Grade A, and why
search 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 4d 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
/search · 历史会话搜索 (v1.8.0 pivot)
v1.8.0 pivot 注解:之前调用
python -m tools.session_search(SQLite FTS5),但tools/session_search.py在 v1.8.0 pivot 中被删除。Search 现在用 Grep tool 直接搜meta/sessions/*.md,没有 python 中间层。
Backup mode: 主要路径是 ROUTER 在 Cortex pull-based 调度下 launch
hippocampussubagent,结果出现在[COGNITIVE CONTEXT]块里。这个命令是给"我想精确搜某个关键词不走 Cortex"的备份。详见hosts/CLAUDE.md→ §0.5 (Cortex pull-based)。
User invoked: /search $ARGUMENTS
你要做的
-
用 Grep 工具直接搜:
Grep(pattern="$ARGUMENTS", path="meta/sessions/", output_mode="files_with_matches", head_limit=10) -
对每个命中文件,Read frontmatter + 摘录命中行的上下文:
- session 日期 + 标题(从 frontmatter)
- 命中行 + 前后 2 行(用 Grep 的
-C 2) - 当时是否有 SOUL 评分 / commitment / decision(看 frontmatter 的
outcome_score/commitments字段)
-
报告给用户:
🔍 找到 N 条相关 session: 1. 📅 <date> · <title> 命中行:<excerpt> 当时承诺:<commitment if any> ⤷ 现在兑现状态:<check via Read journal/decisions> [Read <session_file>] 看完整 ... -
如果 0 命中:建议拓宽关键词或先
/memory read看短期记忆。
多关键词搜索
如果用户给多个关键词(空格分隔),用 Grep 的正则 OR:
Grep(pattern="(关键词1|关键词2|关键词3)", ...)
中文/日文关键词
Grep 支持 Unicode。无需特殊处理。
Anti-pattern
- 不要只读出文件名 — 必须打开 session 文件提取 commitment 和兑现状态
- 不要超过 10 条结果 — 太多反而让用户淹没
- 不要尝试调用已删除的
tools/session_search.py、tools/cli.py、tools/rebuild_session_index.py(部分已删,部分没用)—— 直接 Grep
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.
- 4d ago First seen · 60 lines · 26 tokens per session scan A 1ab869a39977
search is a command published in the GitHub repository jasonhnd/life_OS (5 stars, last pushed 27d ago), licensed Apache-2.0. It adds 26 tokens to every session and 644 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 commands, from other repositories
learn
Command "learn" from datacore-one/datacore, covering /learn, purpose, when to use, usage and quick capture.
memory-commands
Commands for viewing, updating, and managing the entrepreneur's persistent context — identity, company profile, decision history, follow-ups, and session data. These commands read from and write to the five-layer memory system.
vault
Promote a completed thinking session into a versioned personal archive.
minutes-ideas
Surface recent voice memos and ideas captured from any device. Use when the user asks "what ideas did I have?", "what were my recent memos?", "what did I record while walking?", or wants to recall a captured thought.
learn
Force claude-smart to extract learnings from this session now.
session-end
I'll summarize this coding session and update the memory system with our accomplishments.