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 xujingchen1996/research-app-toolkit --skill cold-emailgit clone --depth 1 https://github.com/xujingchen1996/research-app-toolkitWrote 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/xujingchen1996/research-app-toolkit/cold-email)<a href="https://agentmods.dev/skills/xujingchen1996/research-app-toolkit/cold-email"><img src="https://agentmods.dev/badge/skills/xujingchen1996/research-app-toolkit/cold-email.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 | $0.00062 | $0.00571 |
| Opus 5 | $0.00031 | $0.00285 |
| Sonnet 5 | $0.00012 | $0.00114 |
| Haiku 4.5 | $0.00006 | $0.00057 |
Grade A, and why
cold-email 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 — 68 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Outreach Email
Preconditions
- Read
../../memory.mdfirst. - If
cv_profile_analyzedis not complete, first suggest that the user runcv-analyze, unless the user has already directly provided sufficiently complete background materials.
Language Rules
- Support three output modes:
zh,en, andbilingual. - If the user explicitly specifies the email language, prioritize the current request.
- Otherwise read
preferred_languagefrommemory.md. - If it is still unclear, prioritize the language commonly used by the target professor or target program.
- If the user requests bilingual output, default to one main email body plus one concise counterpart version, rather than mixing Chinese and English in the same email.
Identify the Email Type
If the user does not specify it, default to first-contact. Supported types:
first-contactfollow-upinterview-thanksoffer-negotiationreference-remindrejection-follow
Fill In the Key Context First
If any of the following is missing, ask directly:
- professor name and school
- whether the user wants Chinese or English
- the 1 to 2 experiences they most want to emphasize
- whether there has already been prior communication
Writing Workflow
- Extract the most relevant background from
memory.md. - Verify the target professor through web search:
- homepage
- research direction
- recent papers or projects
- Identify the 1 to 2 most natural connection points between the user's experience and the professor's research.
- Output the email draft, and provide subject-line alternatives when necessary.
Writing Rules
- The first outreach email should be short and direct.
- It must include specific research connections, not just generic praise.
- Do not expose unnecessary weaknesses, such as grade anxiety or previous application failures.
- For English emails, aim to keep them within about 250 to 300 words.
- For Chinese emails, aim to keep them within one screen of readable length.
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 · 68 lines · 62 tokens per session scan A e313d0372122
cold-email is a skill published in the GitHub repository xujingchen1996/research-app-toolkit (114 stars, last pushed 1mo ago), licensed MIT. It adds 62 tokens to every session and 571 once invoked, about $0.0003 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-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…
babysit-pr
Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…