Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/borisvu/obsidian-vault-cowork-pluginsnpx agentmods add commands/borisvu/obsidian-vault-cowork-plugins/updateWrote 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/borisvu/obsidian-vault-cowork-plugins/update)<a href="https://agentmods.dev/commands/borisvu/obsidian-vault-cowork-plugins/update"><img src="https://agentmods.dev/badge/commands/borisvu/obsidian-vault-cowork-plugins/update.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 5.1 | $0.00008 | $0.01206 |
| Opus 5 | $0.00004 | $0.00603 |
| Sonnet 5 | $0.00002 | $0.00241 |
| Haiku 4.5 | $0.00001 | $0.00121 |
Grade A, and why
update 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 6d 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 — 165 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Update Command
See CONNECTORS.md for tool references.
Two modes:
- Default: Sync Jira tasks, triage stale items, check memory for gaps
--comprehensive: Deep scan of vault content, flag missed items, suggest new memories
Usage
/para-flow:update
/para-flow:update --comprehensive
Default Mode
1. Load Current State
Read CLAUDE.md. If they don't exist, suggest /para-flow:start first.
2. Sync from Jira
If Atlassian MCP is available, fetch issues assigned to user (open/in-progress).
Compare against task manager skill:
| Jira issue | tasks match? | Action |
|---|---|---|
| Found, not in tasks. | No match | Offer to add |
| Found, already in tasks. | Match by key or title | Skip |
| In tasks with Jira key, not in Jira results | Possibly completed | Offer to mark done |
| Completed in Jira | In Active section | Offer to mark done |
Present diff and let user decide.
3. Resolve Jira Links in Vault
Search for Obsidian-style Jira links ([[PROJECT-NNNN]], [[IDEA-NNNN]], or any [[PREFIX-NNNN]] matching Jira patterns) across the vault that don't have corresponding files.
For each unresolved link:
- Query Jira for the ticket summary, status, and assignee
- Determine placement:
- User is assignee OR user says they're working on it →
PARA/1 Projects/{KEY} - {Summary}/{KEY} - {Summary}.md - Otherwise →
PARA/3 Resources/Jira/{KEY} - {Summary}.md
- User is assignee OR user says they're working on it →
- Create the file with Jira metadata (see Jira Note Template in daily-report skill)
When searching for existing notes, use glob patterns like PARA/1 Projects/*/{KEY}* and PARA/3 Resources/Jira/{KEY}* to handle both flat files and subdirectories.
4. Triage Stale Items
If task management is available, review Active tasks and flag:
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.
- 6d ago First seen · 165 lines · 8 tokens per session scan A ca7f50367772
update is a command published in the GitHub repository borisvu/obsidian-vault-cowork-plugins (4 stars, last pushed 6mo ago), licensed Apache-2.0. It adds 8 tokens to every session and 1,206 once invoked, about $0.0000 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
checkpoint
Export, refresh, verify, or import a comprehensive cross-topic Project Knowledge Checkpoint for a repository, with privacy checks.
audit
Audit .flow/memory/ entries against the current codebase — Keep / Update / Consolidate / Replace / Delete / Harden per entry.
context-age
Envejecimiento semántico del decision-log — comprime y archiva decisiones antiguas.
finish-work
Command "finish-work" from DunCanYounG-1/auto-embedded, covering 1. 机械门禁（先跑，不通过不许进 review 结论）, 2. review 三层（缺一不可）, 3. 学习回流（promote，知识复利的关键）, 4. 会话记忆（journal，跨会话续上下文） and 5. 归档.
handoff
Create a handoff document for seamless session continuity.
continuar
Recuperar sesión previa y generar reporte de puesta al día.