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/tmargolis/career-navigator/setup-schedulenpx skills add tmargolis/career-navigator --skill setup-schedulegit clone --depth 1 https://github.com/tmargolis/career-navigatorWrote 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/tmargolis/career-navigator/setup-schedule)<a href="https://agentmods.dev/skills/tmargolis/career-navigator/setup-schedule"><img src="https://agentmods.dev/badge/skills/tmargolis/career-navigator/setup-schedule.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 | $0.00058 | $0.02578 |
| Opus 5 | $0.00029 | $0.01289 |
| Sonnet 5 | $0.00012 | $0.00516 |
| Haiku 4.5 | $0.00006 | $0.00258 |
Grade A, and why
setup-schedule 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 5d 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 — 262 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Create or update the Career Navigator daily brief as a Cowork scheduled task. When the task fires each morning, it delivers a full operating brief: pipeline digest, Gmail inbox scan (two-pass strategy to catch missed status emails), follow-up alerts, and top new job recommendations appended to recommendations.json.
1. Verify Career Navigator setup
Read {user_dir}/CareerNavigator/profile.md.
If the profile is missing, output:
Daily schedule not set up: run
/career-navigator:launchfirst to initialize Career Navigator.
Then stop.
2. Check for an existing scheduled task
Load and call mcp__scheduled-tasks__list_scheduled_tasks. Look for any task whose taskName contains career-navigator or whose prompt mentions Career Navigator.
If a matching task is found:
- Display its current schedule and a one-line summary of its prompt
- Ask: "A daily brief is already scheduled. Would you like to update the time, update the prompt, or keep it as-is?"
- If the user wants to update: follow Steps 3–5 but use
mcp__scheduled-tasks__update_scheduled_taskwith the existing task's ID instead of creating a new one - If the user wants to keep it: confirm "Your daily brief is already scheduled." and stop
3. Confirm preferred schedule
Ask: "What time would you like your daily brief? Default is 7:00 AM daily."
Accept natural language and convert to a cron expression:
| Input | Cron |
|---|---|
| "7am" / "7:00 AM" / default | 0 7 * * * |
| "6:30am" | 30 6 * * * |
| "8am weekdays" | 0 8 * * 1-5 |
| "6am every day" | 0 6 * * * |
If the user confirms the default, proceed without further prompting.
4. Build the self-contained task prompt
Application data uses the split layout defined in references/tracker-schema.md — read it before any read or write. The task prompt below carries its own copy of that instruction, because each scheduled run starts in a fresh session.
Resolve {user_dir} to its actual absolute path on disk (e.g. /Users/jane/career).
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.
- 5d ago First seen · 262 lines · 58 tokens per session scan A dbfe5ce16c39
setup-schedule is a skill published in the GitHub repository tmargolis/career-navigator (13 stars, last pushed 6d ago), licensed Apache-2.0. It adds 58 tokens to every session and 2,578 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
orbit-notion
Open Orbit briefing skill — selected by the Orbit pipeline when Notion is the user's only connected connector, or when the user explicitly scopes their daily digest to Notion. Pulls the past 24 hours of document edits, comments, mentions, and database row changes from the user's authenticated Notion connection and…
pinchtab-mcp
Use this skill when a task requires browser automation through PinchTab's MCP server connected to a remote browser instance. Covers navigation, element interaction, data extraction, form filling, multi-step flows, and session management via MCP tools.
feishu
Work with Feishu or Lark bots, docs, sheets, bitables, approval flows, and OpenAPI/MCP setup without hardcoding credentials.
Cortex
Operate Cortex, the LifeOS memory system — the typed Knowledge Archive (People, Companies, Ideas, Research with typed related: links) plus recall of prior work sessions, ISAs, and conversations. Search, add, harvest, develop, ingest, distill, graph-navigate, recall. USE WHEN cortex, knowledge, knowledge base, search…
peekaboo
Capture and automate macOS UI with the Peekaboo CLI.
mochi-remind
Handle due reminders — notify the user with natural language and mark them done.