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 emSoumik/cold-mail-agent-mcp --skill contentgit clone --depth 1 https://github.com/emSoumik/cold-mail-agent-mcpWrote 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/emsoumik/cold-mail-agent-mcp/content)<a href="https://agentmods.dev/skills/emsoumik/cold-mail-agent-mcp/content"><img src="https://agentmods.dev/badge/skills/emsoumik/cold-mail-agent-mcp/content.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 | $0.00057 | $0.00824 |
| Opus 5 | $0.00028 | $0.00412 |
| Sonnet 5 | $0.00011 | $0.00165 |
| Haiku 4.5 | $0.00006 | $0.00082 |
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 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 — 81 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Cold Email
Write the shortest truthful message that gives one specific person a reason to care and an easy way to reply. Preserve the voice established by the WhatsApp-derived Hall of Fame corpus. Do not replace it with generic sales-copy advice.
Source hierarchy
Use these sources in order:
- User-supplied preferences and verified recipient and sender facts for this message.
references/style-corpus.mdfor voice and proven patterns.- The matching workflow references below.
This public MCP does not include private memory or lead records. Apply those only when the connected client supplies them.
Never invent familiarity, attribution, numbers, results, or personalization. If a reference is unavailable, do not pretend to have read it.
References
references/style-corpus.md: read first to calibrate voice and ambition.references/channels-and-followups.md: read for email, LinkedIn, X, Instagram, WhatsApp, follow-up, or re-engagement behavior.references/use-cases.md: read only the matching use case.references/voices.md: choose the recipient-appropriate register.references/writing-engine.md: draft the subject and message.references/humanizer.md: required final anti-slop and readability pass.
Workflow
1. Ground the message
Apply any preferences the connected client provides. This public MCP cannot access private lead records.
Identify internally:
- recipient, channel, and relationship stage;
- one verified detail that explains why this person;
- why Soumik is writing now;
- the minimum proof needed to trust him;
- one desired response;
- any work, sample, idea, or useful artifact Soumik can show first.
Ask only for information that materially blocks a truthful draft. If enough context exists, proceed without an intake questionnaire. Research links when tools are available. Distinguish observed facts from inferences.
2. Choose the interaction
Read channels-and-followups.md, then choose the use case and voice. A DM starts a conversation; an email usually carries more context. The first contact should normally earn the next reply, not force the final decision.
What ships with it
6 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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 · 81 lines · 57 tokens per session scan A 158414c8fc08
cold-email is a skill published in the GitHub repository emSoumik/cold-mail-agent-mcp (0 stars, last pushed 1mo ago), licensed MIT. It adds 57 tokens to every session and 824 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 2026-08-31.
Other skills, from other repositories
add-provider
Add a new storage or service provider to the core package. Use when implementing a new backend for StorageService (e.g., a new database) or a new service provider (e.g., a new LLM backend).
add-export
Add a new subpath export to the @cyanheads/mcp-ts-core package. Use when creating a new public API surface that consumers import from a dedicated subpath (e.g., @cyanheads/mcp-ts-core/newutil).
owd-albatross
Connect, initialize, resume, or coordinate MDevolved Projects from Albatross using its agent.config.json stdio MCP surface, a pinned OAuth bridge, qualified tool names, workspace prompt continuity, path forks, resets, and independently attributable participant identities. Use when a repository runs Albatross, contains…
owd-eve
Connect, initialize, resume, or coordinate MDevolved Projects from an Eve agent using Eve's standard remote MCP connection, user-scoped Vercel Connect OAuth, qualified tool names, durable Project continuity, and independently attributable agent identities. Use when an Eve repository has agent/connections, when adding…
owd-obsidian-mind
Connect, initialize, resume, or coordinate an Obsidian Mind vault with MDevolved while preserving its local qmd/om MCP runtime, native note layout, scoped memories, private-note rules, and multi-agent writer safety. Use when a vault-manifest.json identifies template obsidian-mind, when adding MDevolved beside Obsidian…
mdevolved-eve
Connect or resume an Eve agent with MDevolved through a user-scoped remote MCP connection while preserving Eve runtime identity and MDevolved Project continuity.