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 AlexisMarasigan/coldoutboundskills --skill positive-reply-scoringgit clone --depth 1 https://github.com/AlexisMarasigan/coldoutboundskillsWrote 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/alexismarasigan/coldoutboundskills/positive-reply-scoring)<a href="https://agentmods.dev/skills/alexismarasigan/coldoutboundskills/positive-reply-scoring"><img src="https://agentmods.dev/badge/skills/alexismarasigan/coldoutboundskills/positive-reply-scoring/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/alexismarasigan/coldoutboundskills/positive-reply-scoring"><img src="https://agentmods.dev/badge/skills/alexismarasigan/coldoutboundskills/positive-reply-scoring.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 | $0.00100 | $0.02027 |
| Opus 5 | $0.00050 | $0.01014 |
| Sonnet 5 | $0.00020 | $0.00405 |
| Haiku 4.5 | $0.00010 | $0.00203 |
Grade A, and why
positive-reply-scoring 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.
This is a copy
100% identical to positive-reply-scoring — 0 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 197 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Positive Reply Scoring
Reply rate tells you if people are paying attention. Positive reply rate tells you if they want what you're selling. This skill computes the second.
Why this exists
A campaign can get 5% reply rate and still be a disaster. If 90% of those replies are "unsubscribe" and "not a fit," you're burning your domains for nothing.
The metric that matters is:
positive_reply_rate = positive_replies / total_sent
Compared side-by-side:
- Campaign A: 1% reply rate, 70% positive → 0.7% positive reply rate
- Campaign B: 5% reply rate, 10% positive → 0.5% positive reply rate
- Campaign A wins.
Classification schema
Every reply is classified into exactly one bucket:
| Label | Meaning | Count as "positive"? |
|---|---|---|
positive_interested |
"Yes, tell me more" or booked a meeting | ✅ |
positive_soft |
"Send more info" / "reach out in Q3" / info request | ✅ |
positive_referral |
"Not me, but talk to X" | ✅ (referral is high-value) |
neutral_question |
Clarifying question, no commitment yet | ❌ (optional — some score as half) |
negative_notnow |
"Not right now, maybe later" | ❌ |
negative_notfit |
"Not a fit" / "we don't need this" | ❌ |
negative_hostile |
Angry reply, complaint, report | ❌ (and track separately as risk signal) |
unsubscribe |
Explicit opt-out | ❌ |
ooo |
Out-of-office auto-reply | ❌ (exclude from denominators) |
bounce |
Technical bounce | ❌ (exclude from denominators) |
other |
Can't tell | ❌ |
Positive reply rate = (positive_interested + positive_soft + positive_referral) / total_sent
Inputs
- Smartlead API key (env:
SMARTLEAD_API_KEY) - Campaign ID to score
- Optional: client_id (if using a sub-client setup)
- Optional: date range (defaults to full campaign)
Steps
1. Fetch all leads + replies from the campaign
Run the fetch script:
npx tsx scripts/fetch-campaign-replies.ts --campaign-id=12345 --out=/tmp/replies.json
This walks /campaigns/{id}/leads paginated, identifies leads with replies (has_reply = true), then fetches /campaigns/{id}/leads/{lead_id}/message-history for each, and writes them to a JSON file with one object per reply.
What ships with it
2 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.
- 11d ago First seen · 197 lines · 100 tokens per session scan A ea7d78d8d621
positive-reply-scoring is a skill published in the GitHub repository AlexisMarasigan/coldoutboundskills (4 stars, last pushed 4mo ago), licensed MIT. It adds 100 tokens to every session and 2,027 once invoked, about $0.0005 per session on Opus 5. A static security scan graded it A with 0 findings. It is 100% identical to positive-reply-scoring, differing in 0 lines, and is treated as a copy.
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…