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 jenningsallen-art/second-brain-os --skill tactical-tasksgit clone --depth 1 https://github.com/jenningsallen-art/second-brain-osWrote 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/jenningsallen-art/second-brain-os/tactical-tasks)<a href="https://agentmods.dev/skills/jenningsallen-art/second-brain-os/tactical-tasks"><img src="https://agentmods.dev/badge/skills/jenningsallen-art/second-brain-os/tactical-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/jenningsallen-art/second-brain-os/tactical-tasks"><img src="https://agentmods.dev/badge/skills/jenningsallen-art/second-brain-os/tactical-tasks.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 | $0.00172 | $0.02119 |
| Opus 5 | $0.00086 | $0.01059 |
| Sonnet 5 | $0.00034 | $0.00424 |
| Haiku 4.5 | $0.00017 | $0.00212 |
Grade A, and why
tactical-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 11d 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 — 140 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Tactical Tasks
Keep TASKS.md alive and connected to Active Priorities. This skill bridges the gap between "we decided X" and "X actually got done" by extracting commitments from meetings, connecting tasks to projects and people, and surfacing what's slipping.
Works in both Claude Code CLI and Cowork. Find the vault root by checking for CLAUDE.md, PARA folders, or .obsidian/ in the working directory.
Three-Altitude Task System
The user maintains three canonical artifacts. Respect the distinction.
Active Priorities.md (Strategic, 2 - Areas/Active Priorities.md)
- What matters this week and ongoing. The user maintains this manually.
- Read by the Morning Brief scheduled task as the AUTHORITATIVE source.
- Typical sections: This Weekend, Today, This Week, Resolved Recently, Ongoing, Watching.
- This skill reads Active Priorities. It does NOT write to it without explicit permission. It is the user's manual strategic list.
TASKS.md (Tactical, vault root)
- Specific next-actions with assignees, dates, and priority flags. Managed by this skill.
- Load-bearing sections (dashboard queries depend on these headings — do not rename without updating dashboard): Now, Active, Ongoing, Watching. Plus Completed for archive.
- Flexible sections (organizational only, no dashboard dependency): topic-based (Hiring, Board, etc.), day-of-week, sprint-based, or whatever helps the user triage. The dashboard's Action Zone routes by date metadata, not heading name.
- Uses Tasks-plugin emoji metadata inline: 📅 due, 🛫 start, ⏳ scheduled, 🔁 recurring, 🔺 highest, ⏫ high, 🔼 medium, 🔽 low, ⏬ lowest, ✅ done date. Example:
- [ ] **Senior hire decision** 🔺 📅 2026-04-25. - Every task needs a 📅 date. Undated high-priority tasks fall into the Orphans sweep view on the dashboard — that's the forcing function for date discipline.
- Every item should trace back to an Active Priority. If it doesn't, question whether it belongs.
Tasks Dashboard.md (Live view, vault root)
- Live rendering of TASKS.md via the Tasks + Dataview plugins.
- The user opens this daily, including on mobile. Three zones:
- Action (time-based, pivots on 📅 date metadata): Now+Overdue, Today, This Week, Next Week.
- Tracking (heading-based): Active, Ongoing, Watching.
- Sweep (catch-all): Orphaned high-priority (no date), Everything Open (grouped by heading), Completed This Week.
- The Action Zone uses relative date filters (
due today,due this week,due next week), so dates never rot. - Tracking Zone pivots on load-bearing headings: Now, Active, Ongoing, Watching. Rename any of these only with a matching update to the dashboard queries in the same edit.
- Dashboard has a Quick Capture block. Freeform items typed there get picked up by the "Everything Open" view. When you see orphan tasks in Quick Capture, offer to file them under the right section.
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.
- 11d ago First seen · 140 lines · 172 tokens per session scan A 0e19e21d1b8e
tactical-tasks is a skill published in the GitHub repository jenningsallen-art/second-brain-os (2 stars, last pushed 1mo ago), licensed MIT. It adds 172 tokens to every session and 2,119 once invoked, about $0.0009 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
recipe-create-meet-space
Create a Google Meet meeting space and share the join link.
workthreads
SpecStory Workthreads - a weekly work-thread rollup across a team's repos from SpecStory coding histories (any agent - Claude Code, Codex, Cursor, Gemini, and more). It groups the window's sessions into threads of work per project and labels each new / open / recently closed, so a lead sees what shipped, what is still…
atmos-config
Atmos root configuration: atmos.yaml discovery, precedence, deep merging, basepath, imports, minimal bootstrap, and routing to narrower Atmos skills.
story-readiness
Validate that a story file is implementation-ready. Checks for embedded GDD requirements, ADR references, engine notes, clear acceptance criteria, and no open design questions. Produces READY / NEEDS WORK / BLOCKED verdict with specific gaps. Use when user says 'is this story ready', 'can I start on this story', 'is…
autotask-creator
Rules for automation CRUD from the group-chat commander. The commander does not call mutation tools and does not edit cloud/autotasks files directly. It emits one or more top-level ... containers in its final text; the bus parses and applies them after the turn.
projects
List all managed projects with status, branch, open PRs, and open issue counts — portfolio-level view.