method

A command for managing a personal library of reusable methods, meaning documented ways of approaching recurring kinds of work. It can list existing methods or create and update method records.

In plain words
What is it for?
Use it to review the method library, count references across the knowledge base, or create and update a method using a short lowercase name.
Why use it?
It removes the need to track method notes manually and shows where each method is referenced. It also provides consistent naming and metadata for new entries.

Command

Install

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.

agentmods
npx agentmods add commands/jasonhnd/life_os/method
Clone the repo
git clone --depth 1 https://github.com/jasonhnd/life_OS
Per session 28 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,082 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00028 $0.01082
Opus 5 $0.00014 $0.00541
Sonnet 5 $0.00006 $0.00216
Haiku 4.5 $0.00003 $0.00108

Measured 2d ago against content hash 7771dc3e48e1, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

method 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 2d 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.

docs/history/v1.10-command-surfaces/scripts/commands/method.md · 100 lines

How it starts

The opening of the file, as written. The whole thing — 100 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/method · 方法论库管理 (v1.8.1 · zero-python)

⚠️ Backup mode. 主要路径是 archiver Phase 2 退朝时自动检测 method candidate 并 create/update。这个命令是给"我想现在立刻 seed 一个具体 method"的备份。详见 hosts/CLAUDE.md → Auto-Trigger Rules → Method auto-create。

User invoked: /method $ARGUMENTS

v1.8.1 zero-python 改造

之前 (v1.8.0 之前) 这个 prompt 调 python -m tools.skill_manager。 v1.8.1 把那个 .py 文件删了, 你现在用 LLM 直接做所有工作 — Read / Write / Glob / Grep。

你要做的

子命令 list (默认 — 无参数也按 list 处理)

  1. Glob 模式 meta/methods/**/*.md 列出所有 method 文件
  2. 对每个文件 Read 头 30 行抽 frontmatter (title: / description: / last_modified:)
  3. 同时 Grep 整个 second-brain (projects/** + areas/** + meta/journal/**) 数每个 method 被引用次数 (用 method id 或 wikilink [[method-X]] 当 query)
  4. 输出表:
    | method | description | last modified | refs |
    |---|---|---|---|
    | <name> | <one line> | <YYYY-MM-DD> | <N> |
    

子命令 create <name>

  1. Slug: lowercase kebab-case, ≤ 50 chars
  2. 检查 meta/methods/<domain>/<slug>.md 是否已存在 (Glob); 已存在 → 提示 user "已存在, 用 update 还是换 slug?"
  3. 如果新 method 跨 domain, 让 user 选 domain (从现有 meta/methods/ 下一级目录列表里挑, 或新建)
  4. Write 文件, 用以下 frontmatter 模板:
    ---
    title: "<one-line title>"
    description: "<≤ 80 chars 用途说明>"
    created: <YYYY-MM-DD>
    last_modified: <YYYY-MM-DD>
    status: tentative   # tentative | confirmed | deprecated
    triggers: []        # 什么场景触发用这个 method
    inputs: []          # 用之前需要什么信息
    outputs: []         # 用之后产出什么
    refs: []            # 引用的 wiki entries (wikilinks)
    ---
    
    # <title>
    
    ## When to use
    <2-3 行触发条件>
    
    ## Steps
    1. ...
    2. ...
    3. ...
    
    ## Failure modes
    - <这个 method 什么时候失效>
    
    ## Related
    - [[wiki/<domain>/<entry>]]
    
  5. 报告: ✏️ 已创建 method: <name>。路径: meta/methods/<domain>/<slug>.md

子命令 update <name>

  1. Glob 找到 meta/methods/**/<name>*.md (允许部分匹配)
  2. 多个匹配 → 让 user 选; 0 个匹配 → 提示 "没找到, 是不是要 create?"
  3. Read 当前内容
  4. 询问 user 改什么 (Steps 加一步? Failure modes 加一条? status 升 tentative→confirmed?)
  5. Edit 文件, 同时 bump last_modified 到今天
  6. 报告: 🔧 已更新 method: <name>。修订时间: <YYYY-MM-DD HH:MM>

Read the full file on GitHub · 100 lines

Changes

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.

  1. 2d ago First seen · 100 lines · 28 tokens per session scan A 7771dc3e48e1

Subscribe to this mod's changes

method is a command published in the GitHub repository jasonhnd/life_OS (5 stars, last pushed 24d ago), licensed Apache-2.0. It adds 28 tokens to every session and 1,082 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.