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 tmargolis/career-navigator --skill focus-careergit 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/focus-career)<a href="https://agentmods.dev/skills/tmargolis/career-navigator/focus-career"><img src="https://agentmods.dev/badge/skills/tmargolis/career-navigator/focus-career/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/tmargolis/career-navigator/focus-career"><img src="https://agentmods.dev/badge/skills/tmargolis/career-navigator/focus-career.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 | $0.00039 | $0.01192 |
| Opus 5 | $0.00019 | $0.00596 |
| Sonnet 5 | $0.00008 | $0.00238 |
| Haiku 4.5 | $0.00004 | $0.00119 |
Grade A, and why
focus-career 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 10d 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 — 81 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Run when the user opens a new Cowork session with Career Navigator, or when they have scheduled this skill via Cowork /schedule (optional — for tighter proactive critical checks).
Host integration: Claude Cowork’s SessionStart hook (see hooks/hooks.json) injects hooks/context/session-start.md so this workflow is explicitly requested at session open. If the user invokes this skill manually without that hook, follow the same steps below.
Manual fallback: In environments where the SessionStart hook does not auto-fire reliably, run /career-navigator:focus-career at the start of the task/session.
This skill is the critical-only counterpart to daily-schedule. It does not replace the daily digest.
Workflow
1. Locate {user_dir} and core files
Look at the current working directory and any user-provided path. Use that as {user_dir}.
Check for:
{user_dir}/CareerNavigator/profile.md{user_dir}/CareerNavigator/ExperienceLibrary.json{user_dir}/CareerNavigator/tracker.json{user_dir}/CareerNavigator/artifacts-index.json
If these are missing, treat as first run and output:
Welcome to Career Navigator
Run
/career-navigator:launchto initialize yourCareerNavigatordata files and enable automation.
2. Returning session: critical-only checks
Application data uses the split layout defined in references/tracker-schema.md — read it before any read or write.
Read {user_dir}/CareerNavigator/tracker.json. Checks 1 and 2 below are answered by the summary rows alone (status, offer.deadline, follow_up_date, latest_stage, latest_stage_date, notes_count); only check 3 opens a detail file, and only for applications that already qualify. This skill must stay cheap — never walk every applications/<application_id>.json.
Only surface critical notifications:
- Imminent offer deadline
- Any application with
status: "offer"andoffer.deadlinewithin the next 24 hours. - If
{user_dir}/CareerNavigator/offer-context-{application_id}.jsonis not present for that application, label the critical reason as: "Offer evaluation due (run/career-navigator:evaluate-offer)."
- Any application with
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.
- 10d ago First seen · 81 lines · 39 tokens per session scan A b715280f2953
focus-career is a skill published in the GitHub repository tmargolis/career-navigator (13 stars, last pushed 11d ago), licensed Apache-2.0. It adds 39 tokens to every session and 1,192 once invoked, about $0.0002 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…
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…
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.
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.