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 skills/ryanzhao1011/workframe/obsidian-safe-writenpx skills add ryanzhao1011/workframe --skill obsidian-safe-writegit clone --depth 1 https://github.com/ryanzhao1011/workframeWrote 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/ryanzhao1011/workframe/obsidian-safe-write)<a href="https://agentmods.dev/skills/ryanzhao1011/workframe/obsidian-safe-write"><img src="https://agentmods.dev/badge/skills/ryanzhao1011/workframe/obsidian-safe-write.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 | $0.00057 | $0.01565 |
| Opus 5 | $0.00028 | $0.00783 |
| Sonnet 5 | $0.00011 | $0.00313 |
| Haiku 4.5 | $0.00006 | $0.00156 |
Grade A, and why
obsidian-safe-write 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.
How it starts
The opening of the file, as written. The whole thing — 118 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Obsidian Safe Write
定位
本 skill 只做 Obsidian-aware 的小范围安全写入,不负责业务正文创作。
适合写入标准 Properties、使用模板创建新文档、在 frontmatter 后追加标准块,以及用户明确确认后的单文件 move / rename。
触发场景
- 修改正式文档后更新
updated(格式与「何时不更新」的例外见document-norms§2.7)。 - 项目配备的发布器(
<platform>-publish)发布成功后回写该平台的同步状态字段。 - 新建
spec/plan/decision/overview时用模板创建。 - 用户明确要求重命名或移动某个单文件。
何时不用
- 大段正文写作:用业务 skill +
Edit/Write。 - 批量目录重命名:不要默认使用本 skill;先做方案和用户确认。
- 链接审计:用
obsidian-link-audit。 - 历史恢复:不用本 skill,恢复类操作必须单独确认。
CLI Probe
优先读取 .claude/workframe-state/obsidian-cli-status.json(schema 权威定义见 skill: obsidian-doc-structure §status.json schema):
do_not_probe: true→ 永不重新 probe(不设 TTL、不做过期自判),直接按cli_available决定走 CLI 还是 fallback;重新启用 CLI 的唯一入口 = 用户手动删除该文件- 缓存缺失 → 执行非执行检测(全程不运行任何 obsidian 命令):定位命令(
Get-Command obsidian/command -v obsidian)→ 判定是否 GUI 启动器(所在目录存在Obsidian.exe/resources.pak特征文件)→ 不可用则写入 status.json(cli_available: false、do_not_probe: true、reason)并 fallback - 仅当非执行检测确认存在独立 CLI shim 时,才允许执行
obsidian version/obsidian vault info=path验证并写入commands_verified
⚠️ 未通过非执行检测时禁止执行任何
obsidian命令——在「装了 GUI 但未启用 CLI」的机器上会误启动 Obsidian 窗口。
不可用时 fallback 到 Edit / Write,但必须先说明 fallback 原因。
调用前检查
执行任一 Obsidian CLI 命令前,必须依序确认:
status.json存在且do_not_probe: true且cli_available: false→ 直接 fallback,不做任何 probe。- 命令在
commands_verified数组中 → 可以使用 CLI。 - 命令不在数组中 → 直接 fallback,不尝试执行。
status.json不存在或 schema 不匹配 → 按「CLI Probe」的非执行检测流程重新检测(禁止直接执行 obsidian 命令)。
官方 CLI 命令
obsidian property:set path="<file>" name=updated value="2026-04-29T23:12:40+08:00" type=datetime
obsidian property:remove path="<file>" name="<field>"
obsidian prepend path="<file>" content="..."
obsidian create path="<file>" template="<template>"
obsidian move path="<old-file>" to="<new-file>"
obsidian rename path="<file>" name="<new-name>"
以本机 obsidian help <command> 的参数名为准。
模板协同
使用 create template= 时,不建立新的 Obsidian-only 模板体系。优先复用:
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 · 118 lines · 57 tokens per session scan A 8e6222d2ff05
obsidian-safe-write is a skill published in the GitHub repository ryanzhao1011/workframe (4 stars, last pushed 17d ago), licensed MIT. It adds 57 tokens to every session and 1,565 once invoked, about $0.0003 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 skills, from other repositories
decision-ledger
Maintain an append-only decision ledger (DECISIONS.md). Use when the user confirms a decision, reverses or changes a past decision, asks what was decided and why, or at session start to load standing decisions.
knowledge-base
Keep verified findings in memory/knowledge/ so the same research is never done twice. Use before researching any topic, when a finding passes the verify gate, or when about to answer from something learned in an earlier session.
pin
Turn a correction or working preference the user just expressed into a permanent ballast rule. Use when the user corrects your behavior, says "don't do X" / "always do Y" / "I told you before", or asks you to remember how they want things done.
brain-init
Scaffold a file-based memory system (index, decision ledger, open questions, session log, optional product truth file) so a project can serve as a durable second brain. Use when the user wants to set up memory, an external brain, or the ballast structure in a project.
recall
Sweep everything the project already holds before answering — at the first message of a session, and again whenever the subject shifts to something the current thread was not about. Use before replying, not only before researching.
project-model
When working in a codebase you've touched before, consult and update the persistent project model maintained by presence. The model lives at /.claude/presence/projects/ /model.md and contains terse notes about architecture, conventions, and verified facts. Use it BEFORE re-deriving things you've already learned, and…