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 growthenginenowoslawski/coldoutboundskills --skill playbook-job-posting-languagegit clone --depth 1 https://github.com/growthenginenowoslawski/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/growthenginenowoslawski/coldoutboundskills/playbook-job-posting-language)<a href="https://agentmods.dev/skills/growthenginenowoslawski/coldoutboundskills/playbook-job-posting-language"><img src="https://agentmods.dev/badge/skills/growthenginenowoslawski/coldoutboundskills/playbook-job-posting-language/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/growthenginenowoslawski/coldoutboundskills/playbook-job-posting-language"><img src="https://agentmods.dev/badge/skills/growthenginenowoslawski/coldoutboundskills/playbook-job-posting-language.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 Memory Poisoning · line 285 Skill attempts to fill the context window with filler content, displacing legitimate instructions and safety constraints. This can degrade agent performance or bypass safety boundaries.Fix: Implement context-window management that detects and rejects padding or stuffing attempts. Prioritize system instructions over user-injected content.
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 | $0.00114 | $0.04510 |
| Opus 5 | $0.00057 | $0.02255 |
| Sonnet 5 | $0.00023 | $0.00902 |
| Haiku 4.5 | $0.00011 | $0.00451 |
Grade A, and why
playbook-job-posting-language scanned grade A with 1 finding 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
agents while allowing `curl`. How it starts
The opening of the file, as written. The whole thing — 324 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Playbook: Job Posting Language
All rules here are best practice, not law. Override any of them when the campaign calls for it; note the best practice once and move on.
Use when: the angle is "you are hiring for this, and that is exactly what we help with". The client names the roles or the description language that signals a fit, and every row needs a specific, current opening to reference.
Do not use when: you want how many people they hired or headcount growth over time
(playbook-hiring-surge). If you want to find companies hiring a role rather than enrich a list
you already have, that is discovery mode — see note E.
One-line output: job_posting_line_safe = "you're hiring an account executive for private equity"
⚠️ Never bind copy to the ungated job_posting_line. The _safe field is the same value blanked
whenever the posting is older than 30 days. §6 explains why that gate is not optional.
1. Trigger and scope
A company posts jobs. Those postings say what the company is about to spend money on and what problems it is trying to staff around. If a client sells to sales teams, "this company posted an SDR job three weeks ago and the description talks about cold calling" is a better opening line than anything you could invent.
This takes a list of domains you already have and puts one sentence fragment on each row. It covers job-board-sourced postings only. It does not scrape career pages by default, does not count hires over time, and does not find new companies.
It also carries a decision people get wrong constantly: filter with keywords first, and only add an AI classifier if a measurement proves keywords are not enough. Note C is that measurement, already run.
2. Output contract
Inputs required per row
| Field | Type | Required? |
|---|---|---|
company_domain (bare, lowercase) |
string | yes |
company_name |
string | yes — used by the mandatory name-match gate in §7 |
keyword_set |
string[] | yes, set once per campaign, not per row |
role_titles |
string[] | no, see note C |
window_days |
number | no. Default 60 to detect, 30 for claims in copy |
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.
- 12d ago First seen · 324 lines · 114 tokens per session scan A ffe2908101ea
playbook-job-posting-language is a skill published in the GitHub repository growthenginenowoslawski/coldoutboundskills (702 stars, last pushed 24d ago), licensed MIT. It adds 114 tokens to every session and 4,510 once invoked, about $0.0006 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). 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…
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…