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/interview-capturenpx skills add tmargolis/career-navigator --skill interview-capturegit 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/interview-capture)<a href="https://agentmods.dev/skills/tmargolis/career-navigator/interview-capture"><img src="https://agentmods.dev/badge/skills/tmargolis/career-navigator/interview-capture.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 5.1 | $0.00097 | $0.01952 |
| Opus 5 | $0.00048 | $0.00976 |
| Sonnet 5 | $0.00019 | $0.00390 |
| Haiku 4.5 | $0.00010 | $0.00195 |
Grade A, and why
interview-capture 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 — 108 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Scope (§13.1)
- User audio only. Do not capture or transcribe the employer’s side without appropriate consent and product scope—that remains out of scope.
- Opt-in: Run this skill only when the user explicitly asks to capture/log from audio or runs
/career-navigator:interview-capture. - Employer policy warning (once): Some employers prohibit any recording of interviews. Before the first capture session, show the warning from spec §13.1 and require acknowledgment. Persist to
{user_dir}/CareerNavigator/interview-capture-settings.json:
{
"employer_warning_acknowledged": true,
"acknowledged_at": "YYYY-MM-DD",
"user_opted_in": true
}
If employer_warning_acknowledged is already true, do not repeat the full warning—one line reminder max.
- Retention / jurisdiction: Use
profile.mdlocationfor GDPR/CCPA framing per spec. If unclear, ask once which retention stance applies and store underinterview-capture-settings.jsonasretention_note.
Workflow
1. Resolve {user_dir} and gate
Application data uses the split layout defined in references/tracker-schema.md — read it before any read or write.
Require CareerNavigator/profile.md and tracker.json. If missing, send user to /career-navigator:launch.
2. Opt-in and warning
- If
interview-capture-settings.jsondoes not exist oremployer_warning_acknowledgedis false: print the employer policy warning; on user acknowledgment, write the settings file. - If user has not opted in to capture for this session, confirm before processing audio.
3. Match application
Identify application_id (or company + role) for the interview being logged. Match it against tracker.json → applications[] on id, falling back to each row's previous_ids. Hold onto the matched row's detail_file, contacts_file, and application label — the writes in step 5 need all three. If unknown, ask before writing tracker updates.
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 · 108 lines · 97 tokens per session scan A 8e1cde197c7f
interview-capture is a skill published in the GitHub repository tmargolis/career-navigator (13 stars, last pushed 6d ago), licensed Apache-2.0. It adds 97 tokens to every session and 1,952 once invoked, about $0.0005 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.