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 tahirraufkeeyu/software-development-agent-stack--sdas --skill email-outreachgit clone --depth 1 https://github.com/tahirraufkeeyu/software-development-agent-stack--sdasWrote 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/tahirraufkeeyu/software-development-agent-stack--sdas/email-outreach)<a href="https://agentmods.dev/skills/tahirraufkeeyu/software-development-agent-stack--sdas/email-outreach"><img src="https://agentmods.dev/badge/skills/tahirraufkeeyu/software-development-agent-stack--sdas/email-outreach/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/tahirraufkeeyu/software-development-agent-stack--sdas/email-outreach"><img src="https://agentmods.dev/badge/skills/tahirraufkeeyu/software-development-agent-stack--sdas/email-outreach.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00058 | $0.01890 |
| Opus 5 | $0.00029 | $0.00945 |
| Sonnet 5 | $0.00012 | $0.00378 |
| Haiku 4.5 | $0.00006 | $0.00189 |
Grade A, and why
email-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 10d 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 — 164 lines — stays where its author put it; the contents beside it link to each section on GitHub.
When to use
Trigger this skill when:
- A
lead-researchbrief has been produced and the rep is ready to initiate outbound. - A warm introduction has been made and the rep needs a multi-step follow-up plan.
- A prospect went cold after a meeting and needs a re-engagement sequence.
- A rep is drafting a LinkedIn connection + follow-up pattern tied to a specific angle.
Do not use this for newsletter-style nurture emails or for templated mass sends. This skill produces account-specific sequences.
Inputs
Required:
research_brief— output oflead-research. If missing, block on this and request it.sequence_type— one of:cold-3,warm-4,linkedin-follow,break-up.target_persona— role and name of the recipient.sender_identity— who the email is from (name, title, one-line credibility).
Optional:
preferred_angle— which of the three angles from the research brief to lead with. Default: angle 1.referral_context— required ifsequence_type=warm-4. Name of the referrer and context of the introduction.calendar_link— if available, used in the CTA of the demo-request email.avoid_topics— anything off-limits (e.g. competitor names, recent layoffs).
Outputs
A Markdown document containing the full sequence. Each email block has:
- Cadence day (Day 0, Day 3, Day 7, etc.).
- Subject line (under 45 characters).
- Body (under 120 words).
- A single, specific CTA.
- A one-line rationale for the sender to see why this email exists.
For linkedin-follow, the output includes the connection request message (under 300 characters, per LinkedIn's limit) plus a follow-up DM.
Tool dependencies
- None required to draft. The skill runs on the research brief plus sender context.
- Gmail / Outlook MCP — optional; used to save drafts directly into the rep's outbox.
- Salesforce / HubSpot MCP — optional; logs the sequence as activities on the contact/account.
Procedure
- Parse the research brief. Extract: chosen angle, the trigger it's tied to, the persona, and the hypothesis.
- Pick the sequence pattern.
cold-3: Day 0 opener → Day 3 value-add → Day 7 break-up.warm-4: Day 0 intro ack → Day 4 value-add → Day 9 specific ask → Day 14 break-up.linkedin-follow: connection request → DM 3 days after acceptance → email 7 days after DM.break-up: single email ending a dormant sequence.
- Draft subject lines. Under 45 characters, lowercase-friendly, no clickbait. Reference something specific — a trigger, a mutual connection, a metric.
- Draft bodies. Under 120 words. Structure:
- Line 1: Reference the trigger, by name. ("Saw the Insight Partners round.")
- Lines 2-3: Hypothesis about their situation. Specific, not generic.
- Lines 4-5: One concrete proof point — a customer name + outcome.
- Last line: one specific CTA.
- Choose one CTA per email. Valid CTAs:
- A specific meeting time ("Tuesday 10am PT or Wednesday 2pm PT?").
- A binary question ("Is this worth a 15-minute look, or not a priority this quarter?").
- A resource link tied to their situation.
- For break-up: permission to close the file.
- Write the LinkedIn connection message if applicable. Under 300 chars. No pitch. Reference a specific shared context.
- Write the break-up email with dignity. Name the topic, offer a resource, close the loop. No "just following up."
- Add a one-line rationale above each email so the rep understands the intent and can edit with context.
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.
- 10d ago First seen · 164 lines · 58 tokens per session scan A a457298c2a9e
email-outreach is a skill published in the GitHub repository tahirraufkeeyu/software-development-agent-stack--sdas (18 stars, last pushed 4mo ago), licensed MIT. It adds 58 tokens to every session and 1,890 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…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…
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…