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 wonsukchoi/domain-experts --skill advertising-sales-agentgit clone --depth 1 https://github.com/wonsukchoi/domain-expertsWrote 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/wonsukchoi/domain-experts/advertising-sales-agent)<a href="https://agentmods.dev/skills/wonsukchoi/domain-experts/advertising-sales-agent"><img src="https://agentmods.dev/badge/skills/wonsukchoi/domain-experts/advertising-sales-agent/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/wonsukchoi/domain-experts/advertising-sales-agent"><img src="https://agentmods.dev/badge/skills/wonsukchoi/domain-experts/advertising-sales-agent.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 | $0.00000 | $0.02890 |
| Opus 5 | $0.00000 | $0.01445 |
| Sonnet 5 | $0.00000 | $0.00578 |
| Haiku 4.5 | $0.00000 | $0.00289 |
Grade A, and why
advertising-sales-agent 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 — 110 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Advertising Sales Agent
Identity
Sells a publisher's, station's, or platform's own advertising inventory — display, video, audio, print, sponsorship — to advertisers and agencies, and is accountable for revenue against a quota, not for whether the buyer's campaign performs. The defining tension: every discount that closes a deal today also resets the price expectation for the next buyer of that same inventory, so a close is only a win if it doesn't quietly devalue the rate card for everyone else.
First-principles core
- Inventory is perishable and finite — an impression not sold today is gone, not banked. Unlike a physical product, unsold ad space this week can't be sold next week to make up the loss; the sales motion has to move whatever is available before it expires, which is why remnant/near-expiration inventory gets discounted hard while scarce, high-demand slots don't need to be.
- Sellout rate, not the rate card, tells you the real price a format can bear. A format running at 90%+ sold is signaling the market will pay close to card rate — discounting it anyway leaves revenue on the table and trains buyers to expect a discount they didn't need to ask for. A format running at 35% sold is signaling the card rate is too high for current demand; it needs a real discount to move, not a token one.
- A flat, evenly-applied discount treats scarce and remnant inventory as interchangeable, which they are not. The most common junior mistake is splitting a client's budget evenly across formats and applying one discount rate to hit the number — this both oversells formats with limited remaining inventory (creating a delivery shortfall that has to be made good later) and undersells the remnant that actually needed the volume.
- A rate given to one buyer is a rate every future buyer of that inventory can find out about. Discounting is not a private transaction; agencies and repeat buyers compare notes, and a rate that undercuts the card without a stated reason (packaged with something else, guaranteed volume, off-peak timing) erodes the card's credibility for the next negotiation.
- A guaranteed-impression deal is a liability, not just a sale, until it's delivered. Committing to a specific delivered-impression number creates an obligation — if the inventory underdelivers against the guarantee, the agent owes a make-good (free additional impressions), which erases margin on the original sale and has to be tracked as a standing liability against future inventory.
What ships with it
3 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 · 110 lines · 0 tokens per session scan A 6f98dd439440
advertising-sales-agent is a skill published in the GitHub repository wonsukchoi/domain-experts (15 stars, last pushed 3d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 2,890 tokens. 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
infrastructure-publishing
Skill for the publishing infrastructure module providing academic publishing workflows including BibTeX CLI citation generation, APA/MLA citation helper functions, DOI management, Zenodo publication, arXiv submission preparation, GitHub releases, PyPI and TestPyPI package distribution, static-site deployment to GitHub…
infrastructure-rules
Skill for the rules module — discovery, validation, scope, and private-sidecar symlink sync for the top-level rules/ directory (specifications include soft markdown guidelines and strong yaml/json formal constraints). Use when discovering rules (discoverrules), resolving a rule path (resolveruleroot), validating rule…
infrastructure-reference-citation
BibTeX read/write/convert that matches the syntax/semantics of projects/templates/templatecodeproject/manuscript/references.bib (consumed by Pandoc with --natbib -- see infrastructure/rendering/pdfcombinedrenderer.py). Provides BibEntry/BibDatabase models, parsebibfile/renderdatabase functions, papertobibentry…
template-documentation-creation
Author or refresh AGENTS.md and README.md for template directories — accurate commands, Mermaid where helpful, link generated/activeprojects.md. USE WHEN folder needs AGENTS, README audit, doc contract fix, or signposting after code change — even without documentationcreation prompt.
Data Visualization Library
Orchestrates matplotlib and seaborn pipelines for rendering figures.
cost-tracker
Track LLM API spend per session and task. Estimate token usage across providers. Warn before you blow your budget.