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 danielpaulai/Purely-Personal-Run-a-business-by-itself --skill outreach-prospectorgit clone --depth 1 https://github.com/danielpaulai/Purely-Personal-Run-a-business-by-itselfWrote 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/danielpaulai/purely-personal-run-a-business-by-itself/outreach-prospector)<a href="https://agentmods.dev/skills/danielpaulai/purely-personal-run-a-business-by-itself/outreach-prospector"><img src="https://agentmods.dev/badge/skills/danielpaulai/purely-personal-run-a-business-by-itself/outreach-prospector/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/danielpaulai/purely-personal-run-a-business-by-itself/outreach-prospector"><img src="https://agentmods.dev/badge/skills/danielpaulai/purely-personal-run-a-business-by-itself/outreach-prospector.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 | $0.00097 | $0.03735 |
| Opus 5 | $0.00048 | $0.01868 |
| Sonnet 5 | $0.00019 | $0.00747 |
| Haiku 4.5 | $0.00010 | $0.00374 |
Grade A, and why
outreach-prospector 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 — 347 lines — stays where its author put it; the contents beside it link to each section on GitHub.
◈ THE PROSPECTOR
Your job is not to find contacts. Your job is to make the wrong approach impossible.
Before a single word is written, this skill produces a complete intelligence brief on the human behind the profile, so the outreach that follows feels less like a DM and more like a conversation that was always going to happen.
━━ STEP 0, CONTEXT CHECK (always first, never skipped) ━━
Look for the participant's context, in this priority order:
- BUSINESS-BRAIN.md — project root, Project Knowledge, or attached to the chat. The single source of truth. If present, its Voice DNA, ICP, offer, proof, and sign-off OVERRIDE every default in this skill's references folder.
- If no brain: the individual foundation documents —
icp-[name].md,voice-dna-[name].md,positioning-[name].md,messaging-[name].md,rule1-[name].md,personal-story-[name].md,business-inbox-[name].md— in the workspace repo root,/docs, or/foundation(the matchmaker's convention). Use them the same way. - If neither: use the bundled references (Daniel Paul's defaults) and label the output header:
DEFAULT VOICE — personalize by adding your BUSINESS-BRAIN.md to this project.
Never re-ask for anything the brain already answers. The "About the sender" questions below are answered by the brain's Offer and ICP sections when a brain exists — pull them, state what you pulled, and move on.
━━ BEFORE YOU BEGIN ━━
If the user hasn't provided all of the following, AND Step 0 found no source for it, ask before proceeding:
About the prospect:
- Their name, LinkedIn URL, or a profile description
- Their role, company, and niche
- Any recent posts, comments, or content they've shared
About the sender (brain-first — only ask what the brain doesn't answer):
- What do you offer? What specific problem do you solve?
- Who is your ideal client? (role, industry, company size, pain point)
- What disqualifies a lead for you?
Do not proceed with partial information. A half-built profile produces half-built outreach.
What ships with it
10 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.
- references/ai-pattern-blacklist.md 7.0 KB
- references/client-intelligence.md 12 KB
- references/copywriting-frameworks.md 12 KB
- references/design-system.md 3.8 KB
- references/discovery-call-framework.md 8.6 KB
- references/html-output-templates.md 65 KB
- references/human-writing-standards.md 3.6 KB
- references/sales-output-examples.md 5.6 KB
- references/sell-by-chat-framework.md 8.0 KB
- references/voice-dna.md 4.8 KB
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 · 347 lines · 97 tokens per session scan A 1ee6c57bb300
outreach-prospector is a skill published in the GitHub repository danielpaulai/Purely-Personal-Run-a-business-by-itself (2 stars, last pushed 29d ago), licensed MIT. It adds 97 tokens to every session and 3,735 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
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…