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 draft-outreachgit 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/draft-outreach)<a href="https://agentmods.dev/skills/tmargolis/career-navigator/draft-outreach"><img src="https://agentmods.dev/badge/skills/tmargolis/career-navigator/draft-outreach.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 | $0.00073 | $0.01405 |
| Opus 5 | $0.00036 | $0.00702 |
| Sonnet 5 | $0.00015 | $0.00281 |
| Haiku 4.5 | $0.00007 | $0.00140 |
Grade A, and why
draft-outreach 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 8d 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 — 54 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Invoke writer in draft-outreach mode.
Invocation
- Use the exact agent name
writer. Retry once with the same name if invocation fails.
Workflow
Application data uses the split layout defined in references/tracker-schema.md — read it before any read or write.
-
Prior communication history (enrichment — default for named recipients): Outreach to a specific person or known contact at a company should be grounded in real mail/calendar context when the host allows—not guesswork.
- If a ContactContextBrief is already in chat → use it as-is (full block to
writer). - Else if Gmail/M365 inbox and/or calendar tools appear in this session → run
contact-contextend-to-end before invokingwriter, unless the user explicitly says to skip history (“no prior thread,” “brand-new contact,” “template only”) or the ask is purely generic with no named recipient yet. Do not invent threads. - Else (no mail/calendar tools in session) → still invoke
writer, but pass a single line:Prior communication:not retrieved — inbox/calendar tools not available in this session; do not imply prior email or meetings.
If the user says they sent mail but the address was wrong or search is empty, follow
contact-context“User said they sent”;email_address_notescarries address candidates. Includecalendar_notes,upcoming_meetings, andwarm_networkingin the handoff when present—ifupcoming_meetingsis non-empty, outreach should not read as a cold first touch. - If a ContactContextBrief is already in chat → use it as-is (full block to
-
Read
{user_dir}/CareerNavigator/profile.mdand{user_dir}/CareerNavigator/voice-profile.md(create stub if missing). -
Voice preflight: If
voice-profile.mdhas no user-pasted block under## User writing samplesor## User writing samples (launch)(substantive excerpts), ask before invokingwriter: paste 2–5 LinkedIn posts or short professional writing; mention optional launch voice harvest (résumé/CV/cover text from disk); user may reply skip (low voice match). If they paste, append a dated## User writing samplessection. If samples already exist, skip this ask. -
From conversation, capture: channel, recipient archetype (title/company if known), objective (info chat, referral check-in, post-event ping), and any StrategistHandoff, ContactContextBrief, or facts the user pasted.
-
Pass a structured brief to
writerindraft-outreachmode. Required: include the full## ContactContextBriefmarkdown block when available, or thePrior communication:fallback from step 0.writermust thread summary, open_loops, hooks_for_writer, calendar_notes, upcoming_meetings, and warm_networking into the draft when present—seeagents/writer/AGENT.md. Do not draft final copy in this skill—delegate. -
Present
writeroutput (variants if offered). Remind: connectors support warm threading when available. -
Sent confirmation + auto-track: After presenting the copy, say:
"Let me know when you've sent this and I'll log it to your tracker."
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.
- 8d ago First seen · 54 lines · 73 tokens per session scan A 676cf34b8e09
draft-outreach is a skill published in the GitHub repository tmargolis/career-navigator (13 stars, last pushed 9d ago), licensed Apache-2.0. It adds 73 tokens to every session and 1,405 once invoked, about $0.0004 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
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…
chronicle
Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…