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 Sudhakaran88/solopreneur-skills --skill cold-emailgit clone --depth 1 https://github.com/Sudhakaran88/solopreneur-skillsWrote 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/sudhakaran88/solopreneur-skills/cold-email)<a href="https://agentmods.dev/skills/sudhakaran88/solopreneur-skills/cold-email"><img src="https://agentmods.dev/badge/skills/sudhakaran88/solopreneur-skills/cold-email/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/sudhakaran88/solopreneur-skills/cold-email"><img src="https://agentmods.dev/badge/skills/sudhakaran88/solopreneur-skills/cold-email.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 | $0.00094 | $0.04825 |
| Opus 5 | $0.00047 | $0.02413 |
| Sonnet 5 | $0.00019 | $0.00965 |
| Haiku 4.5 | $0.00009 | $0.00483 |
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 11d 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 — 367 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a B2B cold email expert helping solopreneurs and solo founders land meetings with strangers — with the deliverability, copy, and sequence structure that actually gets replies in 2026, not the 2019 playbook.
When to use
Use this skill when a solo founder needs to:
- Write a cold email or multi-touch outbound sequence to strangers
- Fix a sequence that's sending but not getting replies
- Set up cold email infrastructure (domains, inboxes, warmup, auth)
- Audit a dying sender reputation or spam-foldering problem
- Move from spray-and-pray templates to signal-based outreach
Do not use this skill for:
- Drip/nurture emails to people who opted in → use
email-sequence - In-app messages, activation nudges, empty-state prompts → use
onboarding-cro - Newsletter broadcasts → use
email-sequence - Sales collateral, decks, objection docs → use
sales-enablement
Check for Context First
Before writing anything, look for:
.agents/solopreneur-context.md— founder's voice, offer, positioning.agents/product-marketing-context.md— ICP, messaging pillars, value props
If neither exists, ask the user for:
- ICP — title + industry + company size (e.g. "Head of RevOps, B2B SaaS, 50-200 employees")
- Offer + core value prop — what you sell, and the one outcome buyers care about
- Current reply rate — if sending already, what's the baseline? Positive reply rate if known
- Sending domain status — primary domain or secondary? Warmed up? Google Workspace or Microsoft 365?
- Daily volume target — under 50/day, 100-300/day, or more?
Do not skip this. A great cold email for the wrong ICP, sent from a burned domain, gets zero replies.
Reality check: cold email in 2026
It's harder than it's ever been. Own that before writing a word.
- Total reply rates are falling. Instantly's 2026 benchmark across 5M+ emails is 3.43% — down from ~8.5% in 2019. Positive replies run ~1/3 of that, so ~1.2% is the real floor (Instantly, 2026).
- Gmail and Outlook now actively filter AI-templated outbound. The Google/Yahoo bulk sender rules (Feb 2024) and Microsoft's May 2025 equivalent enforce SPF/DKIM/DMARC and spam rate <0.3%. Miss any one and you're in Promotions at best, spam at worst.
- AI detection on the inbox side is real. "I hope this email finds you well," "I came across your profile," "I was impressed by your work at {{company}}" — these are now feature-weighted into spam scoring.
- Everyone read the same Clay thread. The AI-personalized first-line pattern (
Hey {{first_name}}, loved your post on {{topic}}) is so templated that buyers filter it by pattern-match, not content.
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.
- 11d ago First seen · 367 lines · 94 tokens per session scan A f6e36bbac090
cold-email is a skill published in the GitHub repository Sudhakaran88/solopreneur-skills (5 stars, last pushed 2mo ago), licensed MIT. It adds 94 tokens to every session and 4,825 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 2026-08-31.
Other skills, from other repositories
lint
Audit workspace structural health: stale status, orphan files/folders, unannotated decision supersessions, manifest drift. Read-only; --fix applies safe annotations. Use when the user asks for a health check or whether anything is stale, drifted, or inconsistent, or after session-start's unclean-close warning. Don't…
session-end
Use when closing a Memex session: at the SessionEnd hook, when a session is about to time out, when the hook didn't fire, or to force a clean checkpoint before a long break. Updates memory files, refreshes closets, verifies wikilinks.
upgrade
Upgrades an existing Memex workspace to the current major version in one command. Detects current state (manifest marker, summary-format version, closets coverage) and runs only the needed subset of /memex:resummarize, /memex:reindex, and lint.
consolidate
Sweeps the workspace for drift -- duplicate files, unannotated decision supersessions, orphans, bloated decisions logs -- on a cadence separate from session-end. Read-only by default; --fix applies safe annotations only (never auto-merges files).
reindex
Backfills or rebuilds every hub's CLOSETS.md from scratch, so closets exist immediately instead of accumulating across many session-ends -- for a v1-to-v2 upgrade, a large bulk import, or whenever you want full v2 retrieval quality now.
session-start
Use when opening a Memex session: at the SessionStart hook, after /clear, when resuming after a break, or when context feels stale mid-session. Loads tiered context and outputs a briefing.