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 skills add ryanzhao1011/workframe --skill obsidian-link-auditgit 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-link-audit)<a href="https://agentmods.dev/skills/ryanzhao1011/workframe/obsidian-link-audit"><img src="https://agentmods.dev/badge/skills/ryanzhao1011/workframe/obsidian-link-audit/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/skills/ryanzhao1011/workframe/obsidian-link-audit"><img src="https://agentmods.dev/badge/skills/ryanzhao1011/workframe/obsidian-link-audit.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 | $0.00138 | $0.01251 |
| Opus 5.5 | $0.00055 | $0.00500 |
| Sonnet 5.5 | $0.00028 | $0.00250 |
| Haiku 4.5 | $0.00014 | $0.00125 |
Grade A, and why
obsidian-link-audit 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 1mo 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 — 98 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Obsidian Link Audit
定位
本 skill 是 Obsidian CLI 增强层,只做链接语义审计,不写文件。
主链路仍是本地 Markdown + rg / Read。当 Obsidian CLI 可用时,用官方 CLI 获取 Obsidian 视角下的 backlinks、outgoing links、unresolved、orphans、deadends;CLI 不可用时回退到 rg 近似查询。
触发场景
- 修改正式
spec/plan/decision前后,需要确认影响面。 - 发布到外部平台前检查坏链(由项目配备的
<platform>-publish发布器调用)。 - 单文件
rename/move前后检查引用是否更新。 - 用户问“哪些文档引用了它”“有没有坏链”“有没有孤岛文档”。
何时不用
- 只读单篇正文:直接
Read。 - 简单关键词全文检索:直接
rg更快。 - 写正文、改 frontmatter:不用本 skill,交给业务 skill /
obsidian-safe-write。 - 外部平台发布:本 skill 不负责发布,只做发布前校验。
CLI Probe
优先读取 .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。
若不可用,记录 fallback 原因并改用 rg / Read。
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
以本机 obsidian help <command> 输出为准,常用命令:
obsidian backlinks path="<file>" format=json
obsidian links path="<file>" format=json
obsidian unresolved verbose format=json
obsidian orphans format=json
obsidian deadends format=json
若本机参数名是 file= 而不是 path=,按 obsidian help backlinks / obsidian help links 调整。
Fallback
rg '\[\[[^\]]*<目标文件名>[^\]]*\]\]' projects docs
rg '\[\[' "<当前文件>"
rg "\]\([^)]*\.md\)" projects docs
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.
- 1mo ago Changed · -4 lines · +80 tokens per session 738f2e54296c
- 2mo ago First seen · 102 lines · 58 tokens per session scan A a6f8afc009f7
obsidian-link-audit is a skill published in the GitHub repository ryanzhao1011/workframe (8 stars, last pushed yesterday), licensed MIT. It adds 138 tokens to every session and 1,251 once invoked, about $0.0006 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 2026-08-31.
obsidian-link-audit compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| obsidian-link-auditryanzhao1011/workframe | Skill | 8 | yesterday | MIT | A | 138 | Claude Code |
| knowledge-structuresjtprogru/bear-skills | Skill | 1 | yesterday | MIT | A | 84 | Claude Code |
| html-prototypemayuemarsha-del/pm-skills | Skill | 4 | 5mo ago | MIT | A | 97 | Claude Code |
| feature-acceptancemayuemarsha-del/pm-skills | Skill | 4 | 5mo ago | MIT | A | 192 | Claude Code |
| prdmayuemarsha-del/pm-skills | Skill | 4 | 5mo ago | MIT | A | 202 | Claude Code |
| ui-walkthroughmayuemarsha-del/pm-skills | Skill | 4 | 5mo ago | MIT | A | 231 | Claude Code |
| gbgcielebak/goal-by-goal | Skill | 1 | 4mo ago | MIT | A | 150 | Claude Code |