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 onebrain-ai/onebrain --skill tasksgit clone --depth 1 https://github.com/onebrain-ai/onebrainWrote 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/onebrain-ai/onebrain/tasks)<a href="https://agentmods.dev/skills/onebrain-ai/onebrain/tasks"><img src="https://agentmods.dev/badge/skills/onebrain-ai/onebrain/tasks/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/onebrain-ai/onebrain/tasks"><img src="https://agentmods.dev/badge/skills/onebrain-ai/onebrain/tasks.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00079 | $0.01389 |
| Opus 5.5 | $0.00032 | $0.00556 |
| Sonnet 5.5 | $0.00016 | $0.00278 |
| Haiku 4.5 | $0.00008 | $0.00139 |
Grade A, and why
tasks 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 — 166 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Task Dashboard
Creates or updates a permanent TASKS.md at the vault root using Obsidian Tasks plugin live query blocks. The file is always current : no vault scanning needed. Mark tasks complete directly in Obsidian by clicking the checkboxes.
Usage:
/tasks: open the full dashboard
Step 1: Locate vault root
Read onebrain.yml from the current working directory. The directory containing onebrain.yml is the vault root. If onebrain.yml does not exist, warn the user:
"onebrain.yml not found : using current working directory as vault root: [path]. Run
/onboardingto set up your vault configuration."
Then proceed with cwd as vault root.
.claude is always excluded as a hardcoded literal (not in onebrain.yml) : it is the plugin host directory and is not user-configurable.
Step 2: Ensure TASKS.md exists and frontmatter is current
Determine tasks_path = {vault_root}/TASKS.md.
If TASKS.md does not exist:
Create it with this exact content (replace YYYY-MM-DD with today's date and substitute all five bracket-notation variables : [logs_folder], [archive_folder], [knowledge_folder], [resources_folder], [agent_folder] : with their session config values; .claude is a hardcoded literal and requires no substitution):
---
tags: [dashboard, tasks]
created: YYYY-MM-DD
updated: YYYY-MM-DD
---
# Task Dashboard
## 🔴 Overdue
```tasks
not done
path does not include [logs_folder]
path does not include [archive_folder]
path does not include [knowledge_folder]
path does not include [resources_folder]
path does not include [agent_folder]
path does not include .claude
due before today
sort by priority
sort by due
```
## 🗓 Due This Week
```tasks
not done
path does not include [logs_folder]
path does not include [archive_folder]
path does not include [knowledge_folder]
path does not include [resources_folder]
path does not include [agent_folder]
path does not include .claude
due after yesterday
due before in 8 days
sort by priority
sort by due
```
## 📋 Unscheduled
```tasks
not done
path does not include [logs_folder]
path does not include [archive_folder]
path does not include [knowledge_folder]
path does not include [resources_folder]
path does not include [agent_folder]
path does not include .claude
no due date
sort by priority
```
## 🔵 Due Later
```tasks
not done
path does not include [logs_folder]
path does not include [archive_folder]
path does not include [knowledge_folder]
path does not include [resources_folder]
path does not include [agent_folder]
path does not include .claude
due after in 7 days
sort by due
sort by priority
```
## ✅ Completed
```tasks
done
path does not include [logs_folder]
path does not include [archive_folder]
path does not include [knowledge_folder]
path does not include [resources_folder]
path does not include [agent_folder]
path does not include .claude
sort by done date
limit 20
```
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 First seen · 166 lines · 79 tokens per session scan A cfab67a06a6f
tasks is a skill published in the GitHub repository onebrain-ai/onebrain (30 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 79 tokens to every session and 1,389 once invoked, about $0.0003 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 2026-08-30.
Other skills, from other repositories
project-sync
On-demand AI-powered sync of a project's repo state into the brain vault. Reads live git/GitHub/Jira data, updates the project status doc, and makes targeted edits to relevant brain docs where content is clearly stale. Triggered by "/project-sync [name]", "sync [project]", "what's the current state of [project]".
project-creator
A project setup process that creates a new project in a vault with planning, task, context, log, and README files, and updates project indexes.
log-decision
Log cross-cutting business/product/hiring/vendor decisions to decisions/ directory with context and alternatives.
obsidian-task-orchestration
Use when managing tasks, projects, multi-agent workflows, or knowledge persistence in an Obsidian vault via MCP. This skill should be used when creating tasks, claiming work, updating progress, completing deliverables, decomposing projects into sub-tasks, monitoring project status, logging decisions or discoveries, or…
initialize
Generate a GEMINI.md file for any codebase by scanning project structure, detecting tech stack, and documenting conventions. Use when onboarding a new project.
refine
Refine epics and stories through cross-functional analysis and requirements gathering.