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 anysiteio/agent-skills --skill anysite-outreachgit clone --depth 1 https://github.com/anysiteio/agent-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/anysiteio/agent-skills/anysite-outreach)<a href="https://agentmods.dev/skills/anysiteio/agent-skills/anysite-outreach"><img src="https://agentmods.dev/badge/skills/anysiteio/agent-skills/anysite-outreach/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/anysiteio/agent-skills/anysite-outreach"><img src="https://agentmods.dev/badge/skills/anysiteio/agent-skills/anysite-outreach.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Rogue Agent · line 3 Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.Fix: Remove any persistence mechanisms (cron jobs, startup scripts, state files). Skills should not maintain state across sessions without explicit user consent.
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 | $0.00161 | $0.02212 |
| Opus 5 | $0.00081 | $0.01106 |
| Sonnet 5 | $0.00032 | $0.00442 |
| Haiku 4.5 | $0.00016 | $0.00221 |
Grade A, and why
anysite-outreach 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 — 155 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Outreach
The other skills end at "found the contact, here's the email". This one writes the message — and its value is that the message rides a specific, dated fact you already collected, not a generic template every competitor also sends.
The rule behind everything: could this exact message be sent to another company? Yes → generic, rewrite or don't send. No → ready. This "mental test" is the skill's core; run it literally on every draft.
Step 0 — the offer (once per user, before any draft)
The message has three slots: [their detail] — [your offer, one line] — [question].
The middle slot is about the SENDER, and no other skill in the pack knows it.
Establish it once and reuse:
- what you sell, in one plain line;
- one number that matters (a price, a metric) — optional but strong;
- 1–2 proof points (a named customer, a hard figure) for touches 3–4;
- words to avoid (competitor names in touch 1, internal jargon).
Ask the user if it isn't already saved. Store it next to the CRM profile
(~/.claude/skills/anysite-crm-profile/) so future sessions skip the question.
(Do not import anysite's own pitch — "$1 per 1k", "don't mention LinkedIn" are
that internal playbook's rules, not yours; see the gold examples file only for
STYLE, not content.)
Where the detail comes from — and it must be fresh
You already have these from the sourcing/signal skills. A detail without a date is not a detail — stale facts are worse than none ("congrats on the round" about a 2021 raise reads as a bot). Freshness gates:
| Source skill | Detail | Fresh if |
|---|---|---|
anysite-crm-champions |
job change / were your champion at | ≤180 days |
anysite-crm-signals |
funding round, exec hire, hiring surge, layoff, news | ≤90 days, and DATED |
anysite-crm-competitor-intel |
uses + a pain from its reviews | pain quote is timeless; usage claim must be PROVEN |
anysite-crm-account-brief / anysite-people-sourcing |
a recent post/comment, a stated priority | post ≤30 days |
anysite-company-sourcing |
homepage quote, product name, a specific metric | timeless |
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 · 155 lines · 161 tokens per session scan A 2f0eef18a786
anysite-outreach is a skill published in the GitHub repository anysiteio/agent-skills (19 stars, last pushed 27d ago), licensed MIT. It adds 161 tokens to every session and 2,212 once invoked, about $0.0008 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 2026-08-30.
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…