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 contact-contextgit 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/contact-context)<a href="https://agentmods.dev/skills/tmargolis/career-navigator/contact-context"><img src="https://agentmods.dev/badge/skills/tmargolis/career-navigator/contact-context.svg" alt="Measured on agentmods" 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 | $0.00097 | $0.02782 |
| Opus 5 | $0.00048 | $0.01391 |
| Sonnet 5 | $0.00019 | $0.00556 |
| Haiku 4.5 | $0.00010 | $0.00278 |
Grade A, and why
contact-context 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 7d 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 — 113 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Gather evidence-backed context from Gmail / Microsoft 365 (and calendar when the host exposes it) so draft-outreach and writer do not guess about prior conversations.
Meeting history awareness (warm networking identification): When calendar tools are used, retrieve past and scheduled (upcoming) events involving this contact. An upcoming meeting on the calendar is a strong signal the relationship is warm (not cold)—outreach can reference the scheduled time or avoid redundant “first touch” framing. A past meeting without a future one still supports warm follow-up. Label uncertainty in caveats if attendee matching is fuzzy.
Gate (run first)
- Connectors: If no Gmail/M365 (inbox) tools and no host calendar tools (e.g. Google Calendar, Outlook/Teams calendar via Microsoft 365) appear in this session, stop and point to CONNECTORS.md and
/career-navigator:launchStep 6—do not invent inbox or calendar access. - Explicit approval: Ask once before calling tools—cover what is available, e.g.
“I can search your mail for threads involving {name or company} [and check your calendar for past and upcoming meetings with them / their email]—read-only. Approve for this request?”
(Include the bracketed calendar sentence only when calendar tools exist and the user wants meeting context.)
If the host exposes only mail or only calendar, ask only for that scope. If no, exit with a short note—no fabricated summaries.
Inputs (ask if missing)
- Contact: name, email, or LinkedIn-style identifier; company (optional but helps disambiguate).
- Scope: default = relevant threads in the last ~12 months; user may narrow or widen. For calendar: default = past ~12 months plus upcoming ~6 months (or tool default) so scheduled meetings with the contact are included.
User said they sent — trust them (default)
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.
- 7d ago First seen · 113 lines · 97 tokens per session scan A 719b1db72f40
contact-context is a skill published in the GitHub repository tmargolis/career-navigator (13 stars, last pushed 9d ago), licensed Apache-2.0. It adds 97 tokens to every session and 2,782 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
media-ingest
Ingest video, audio, PDF, book, screenshot, and GitHub repo content into the brain. Multi-format handling with entity extraction and backlink propagation. Covers video-ingest, youtube-ingest, and book-ingest subtypes.
mem0-oss-to-platform
Plan and then execute a migration of a project from the mem0 open-source / self-hosted SDK (the local Memory class) to the mem0 Platform / hosted / managed SDK (the MemoryClient class). Use this whenever a developer wants to move, switch, or migrate their mem0 usage off OSS/self-hosted to the hosted API — e.g.…
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…
memory
Use when the user asks to remember, recall, forget, update, search, or inspect durable OpenSquilla memory, including profile facts in USER.md and long-term notes in MEMORY.md or memory//.md.
ha-data-stores
Map of Hope Agent's local data stores and safe read-only query workflow. Use when the user asks where Hope Agent stores data, wants to inspect sessions/messages/memory/logs/background jobs/knowledge indexes/settings, asks the model to query local app data, or debugging requires checking persisted state. Trigger…
establishing-project-context
Use when the user asks to establish shared project language, or project work exposes a conflicting, renamed, or deprecated domain term that needs active semantic modeling. Routine small tasks stay on the fast path.