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 add-sourcegit 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/add-source)<a href="https://agentmods.dev/skills/tmargolis/career-navigator/add-source"><img src="https://agentmods.dev/badge/skills/tmargolis/career-navigator/add-source/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/add-source"><img src="https://agentmods.dev/badge/skills/tmargolis/career-navigator/add-source.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 | $0.00058 | $0.00884 |
| Opus 5.5 | $0.00023 | $0.00354 |
| Sonnet 5.5 | $0.00012 | $0.00177 |
| Haiku 4.5 | $0.00006 | $0.00088 |
Grade A, and why
add-source 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 1mo 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 — 114 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Extract structured experience units from a source document and merge them into the user's ExperienceLibrary.
Workflow
1. Identify the source document
If the user has provided a file path or uploaded a document — use it directly.
If no document is in context, ask:
"Which file should I add? Provide the path or paste the content directly."
Supported formats: PDF, DOCX, TXT, MD, plain text paste.
2. Read the current ExperienceLibrary
Read {user_dir}/CareerNavigator/ExperienceLibrary.json. Note:
- Existing unit IDs (to avoid collisions)
- Existing companies and roles (to detect duplicates)
If the file does not exist, create it with an empty units array before proceeding.
3. Extract experience units
Read the source document in full. For each distinct role, education entry, publication, award, or recognition, extract a structured unit:
{
"id": "exp-{next_available_number}",
"type": "role",
"company": "...",
"title": "...",
"dates": "...",
"summary": "1–2 sentence description of scope and context",
"achievements": [
{
"id": "exp-{n}-a1",
"theme": "impact | leadership | technical | commercial | operational",
"text": "exact achievement text, preserved from source"
}
],
"skills": ["skill1", "skill2"],
"performance_weight": 0.5,
"source_document": "{filename of source}"
}
Extraction rules:
- Preserve achievement text as written — do not rephrase or improve at ingest time. Tailoring happens at resume assembly.
- Assign a
themeto each achievement based on what it primarily demonstrates. - Extract skills as they appear — normalize capitalization but do not rename or merge technologies.
- Set
performance_weightto 0.5 (neutral) for all new units. The analyst agent adjusts weights from outcomes.
4. Check for duplicates
Before appending, check each extracted unit against existing ExperienceLibrary entries:
- Same company + overlapping date range = likely duplicate
- If a likely duplicate is found, surface it:
"I see an existing entry for {Role} at {Company} ({dates}) in your ExperienceLibrary. Should I replace it, merge the achievements, or add this as a separate entry?"
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.
- 1mo ago First seen · 114 lines · 58 tokens per session scan A 42e9957d8c9d
add-source is a skill published in the GitHub repository tmargolis/career-navigator (16 stars, last pushed 27d ago), licensed Apache-2.0. It adds 58 tokens to every session and 884 once invoked, about $0.0002 per session on Opus 5.5. 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…
instrument-data-to-allotrope
Convert laboratory instrument output files (PDF, CSV, Excel, TXT) to Allotrope Simple Model (ASM) JSON format or flattened 2D CSV. Use this skill when scientists need to standardize instrument data for LIMS systems, data lakes, or downstream analysis. Supports auto-detection of instrument types. Outputs include full…
apify-youtube-transcript-scraper
Get YouTube captions, timestamped quotations, SRT/VTT and translated transcripts for videos, channels and playlists through the harshmaur/youtube-transcript-scraper Apify Actor.
legal-hold
Issue, refresh, release, or report on legal holds — drafts the hold notice as .docx, updates legalhold fields in log.yaml, and calendars the next refresh. Use when the user says "issue a hold", "refresh hold", "release hold", or asks for a portfolio-wide hold status report.
baoyu-youtube-transcript
A tool for downloading the written captions, subtitles, chapter information, speaker labels, and cover image from a YouTube video using its URL or ID.
feishu
Work with Feishu or Lark bots, docs, sheets, bitables, approval flows, and OpenAPI/MCP setup without hardcoding credentials.