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/techwolf-ai/ai-first-toolkit/priority-plannernpx skills add techwolf-ai/ai-first-toolkit --skill priority-plannergit clone --depth 1 https://github.com/techwolf-ai/ai-first-toolkitWhat 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 | $0.00068 | $0.01083 |
| Opus 5 | $0.00034 | $0.00541 |
| Sonnet 5 | $0.00014 | $0.00217 |
| Haiku 4.5 | $0.00007 | $0.00108 |
Grade A, and why
priority-planner 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 3d 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 — 126 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Priority Planner
Principle: "You are responsible." The skill proposes, the manager decides. This is not a task manager. It's a thinking partner for prioritisation.
Aggregates signals from multiple sources to surface the manager's highest-leverage actions.
When to Use
- Start of day: "what should I focus on today?"
- Start of week: "plan my week"
- When overwhelmed: "help me prioritise"
- After a triage: "fold these into my priorities"
Instructions
If any MCP connector is unavailable, follow the connector unavailability protocol in references/operating-principles.md.
1. Determine Scope
Ask or infer whether this is a daily or weekly plan:
- Daily: focus on today's calendar, current triage, immediate needs
- Weekly: broader view including upcoming deadlines, OKRs, team development
2. Load Goals
Before gathering signals, load the manager's goals. These are the lens through which everything gets prioritised.
From manager-context/manager-goals.md:
- The manager's own OKRs and goals
- Their manager's key priorities
- Upcoming personal milestones and deadlines
From Notion/Drive (if goals location is known):
- Pull the latest version of OKRs in case they've been updated since setup
If no goals are found:
⚠️ I don't have your goals on file. Without them I can prioritise by urgency, but not by impact alignment.
Run /setup or tell me your current OKRs so I can connect your priorities to what matters most.
3. Gather Signals
Pull from multiple sources:
Calendar (today or this week):
- Meetings scheduled and their topics
- Free blocks (potential focus time)
- Deadlines tied to calendar events
Triage results (if /triage-messages was recently run):
- Any 🔴 "Needs Decision" items still unresolved
- 🟡 Team needs awaiting attention
- Customer items flagged
Manager Context (from manager-context/):
- Team members' current projects and any known blockers
- Development conversations due
- 1:1s this week and prep status
- Triage rules (VIPs, hot channels) from
triage-rules.md
What ships with it
2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 3d ago First seen · 126 lines · 68 tokens per session scan A 32660722ed29
priority-planner is a skill published in the GitHub repository techwolf-ai/ai-first-toolkit (96 stars, last pushed 1mo ago), licensed MIT. It adds 68 tokens to every session and 1,083 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 2026-08-30.
Other skills, from other repositories
snip
You are an expert at writing declarative YAML filters for snip, a CLI proxy that reduces LLM token consumption by filtering shell output.
agentnotify
Send local desktop notifications through AgentNotify when a coding agent needs human input, permission, a decision, or attention, or when it completes, fails, or becomes blocked. Use during autonomous coding work to surface actionable state changes from Windows, PowerShell, Command Prompt, WSL, macOS, or Linux without…
caveman
Ultra-compressed communication mode. Cuts output tokens 65% (measured) by speaking like caveman while keeping full technical accuracy. Supports intensity levels: lite, full (default), ultra, wenyan-lite, wenyan-full, wenyan-ultra. Use when user says "caveman mode", "talk like caveman", "use caveman", "less tokens"…
google-calendar
Read and manage Google Calendar events / agenda / free-busy / invitations via the Calendar v3 REST API. Use when the user mentions Google Calendar events, today's agenda, this week's meetings, finding conflicts, listing invitations, checking free time, or scheduling / rescheduling / cancelling a meeting.
google-gmail
Read, search, triage, label, archive and send Gmail mail / threads / labels / attachments via the Gmail v1 REST API. Use when the user mentions Gmail, "my inbox", unread mail, recent emails from someone, summarising a thread, downloading an attachment, finding mail by label / query, archiving or labelling a thread, or…
microsoft-outlook
Read, search, draft, send and manage Outlook / Microsoft 365 email AND calendar events via Microsoft Graph. Use when the user mentions Outlook (mail or calendar), Microsoft 365 inbox, sending mail, replying / forwarding, today's agenda, scheduling a meeting, finding free time, or modifying / cancelling an event.