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 mardab96/b2b-lead-generation-claude-skills --skill cold-outbound-sequence-reviewgit clone --depth 1 https://github.com/mardab96/b2b-lead-generation-claude-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/mardab96/b2b-lead-generation-claude-skills/cold-outbound-sequence-review)<a href="https://agentmods.dev/skills/mardab96/b2b-lead-generation-claude-skills/cold-outbound-sequence-review"><img src="https://agentmods.dev/badge/skills/mardab96/b2b-lead-generation-claude-skills/cold-outbound-sequence-review/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/mardab96/b2b-lead-generation-claude-skills/cold-outbound-sequence-review"><img src="https://agentmods.dev/badge/skills/mardab96/b2b-lead-generation-claude-skills/cold-outbound-sequence-review.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 | $0.00054 | $0.01127 |
| Opus 5 | $0.00027 | $0.00563 |
| Sonnet 5 | $0.00011 | $0.00225 |
| Haiku 4.5 | $0.00005 | $0.00113 |
Grade A, and why
cold-outbound-sequence-review 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 12d 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 — 87 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Cold Outbound Sequence Review
Use this skill when
The sequence is written or running, and the replies are not coming.
Before this runs, confirm the emails are actually being delivered. A sequence with a deliverability problem produces the same symptom as a sequence with a copy problem, and rewriting copy fixes only one of them. That check is spam-folder-check.
Once delivery is not the issue, the cause is almost always one of four things, and they are not equally likely: who it went to, what the first line claims, how big the ask is, and how many times it lands.
Required input
- The full sequence, every step, in order, as it actually sends.
- Who it targets: role, company size, industry, and how the list was built.
- The cadence, in days between steps.
Better with:
- reply rate, positive reply rate and unsubscribe rate per step
- open rate, treated as a soft signal because Apple Mail Privacy Protection fires the pixel on delivery
- examples of the replies, especially negative ones
- what you are actually selling and the deal size
Analysis workflow
- Read the opener as the recipient, who does not know you and did not ask. The first two lines decide everything after them, and most sequences spend both on the sender.
- Check the claim in the opener. It usually falls into one of three shapes: a compliment, a statistic, or an observation about their business. Only the third earns a reply reliably, and only when it is specific.
- Measure the ask. "Fifteen minutes to discuss how we help companies like yours" asks a stranger for a meeting on the strength of nothing. The first ask should be answerable in one line without a calendar.
- Check whether personalisation is real or performed. A merge field with the company name is not personalisation, and recipients read it as the opposite: proof this went to a thousand people.
- Walk the cadence. Steps that arrive too close together read as pressure, steps too far apart lose the thread, and steps that only say "bumping this up" teach the recipient that ignoring you works.
- Look for the sequence's implicit theory of why they should care, and state it plainly. Many sequences do not have one, which is the finding.
- Identify the single highest-leverage change, not a list of eleven improvements. Rewriting everything at once means learning nothing from the result.
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.
- 12d ago First seen · 87 lines · 54 tokens per session scan A 7598e8b50449
cold-outbound-sequence-review is a skill published in the GitHub repository mardab96/b2b-lead-generation-claude-skills (5 stars, last pushed 1mo ago), licensed MIT. It adds 54 tokens to every session and 1,127 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
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…
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
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…