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 ztemerbekov/a1-marketing-skills --skill a1-business-messagegit clone --depth 1 https://github.com/ztemerbekov/a1-marketing-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/ztemerbekov/a1-marketing-skills/a1-business-message)<a href="https://agentmods.dev/skills/ztemerbekov/a1-marketing-skills/a1-business-message"><img src="https://agentmods.dev/badge/skills/ztemerbekov/a1-marketing-skills/a1-business-message/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/ztemerbekov/a1-marketing-skills/a1-business-message"><img src="https://agentmods.dev/badge/skills/ztemerbekov/a1-marketing-skills/a1-business-message.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 | $0.00068 | $0.00726 |
| Opus 5 | $0.00034 | $0.00363 |
| Sonnet 5 | $0.00014 | $0.00145 |
| Haiku 4.5 | $0.00007 | $0.00073 |
Grade A, and why
a1-business-message 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 — 36 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Business Message
Create or rewrite one self-contained workplace message so its recipient set can understand, decide, act, or reply without avoidable follow-up.
Entry Contract
Accept one workplace message for one recipient set—a single existing business contact or a coherent group whose members share one communication job—awareness/status, decision, action, or reply—and need the same relevant facts and disclosure level—through either branch:
- assemble a new message from supplied facts, notes, correspondence, documents, tables, or transcript material;
- rewrite one selected workplace-message draft for the same source-supported communication job.
The accepted artifact is one compact send-ready messenger or ordinary business-email message for that recipient set. A completed specialist analysis, report, legal review, financial model, technical assessment, or project plan may be used as input; performing or rethinking that analysis is outside this skill.
Classify cold first-contact outreach, public marketing or editorial copy, a standalone layered reference-ready internal document, new specialist analysis, and multiple unrelated messages as outside scope. A coherent group is one recipient set when its members share one communication job—awareness/status, decision, action, or reply—plus the same relevant facts and disclosure level and any required wording; produce one message for it. Split only when audience sets materially diverge by facts, action or decision, confidentiality or disclosure, or wording. For materially divergent audiences, identify the separate message jobs, ask which eligible one to start, and produce no partial artifact.
A layered reference-ready document remains with Decision Memo even when it is delivered by email or addressed to an existing business contact. Retain Business Message for the lightest complete job that fits one compact send-ready message. The communication goal alone—inform, decide, approve, or respond—does not override this shape boundary. When the format is unnamed and both shapes remain materially plausible, ask one artifact-shape question only when choosing depth or structure would materially change the result. For any other mixed request, identify the incompatible job and stop before producing partial output.
What ships with it
18 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.
- agents/openai.yaml 427 B
- assets/icon-large.svg 2.3 KB
- assets/icon-small.svg 2.3 KB
- evals/cases/message-approval-001.md 2.3 KB
- evals/cases/message-boundaries-006.md 2.0 KB
- evals/cases/message-coherent-group-008.md 4.9 KB
- evals/cases/message-incompatible-audiences-009.md 2.6 KB
- evals/cases/message-marketing-context-007.md 4.1 KB
- evals/cases/message-missing-owner-deadline-005.md 1.7 KB
- evals/cases/message-no-solution-004.md 1.4 KB
- evals/cases/message-plain-text-formatting-010.md 2.3 KB
- evals/cases/message-raw-forward-003.md 2.2 KB
- evals/cases/message-selected-draft-002.md 1.9 KB
- evals/README.md 1.5 KB
- references/final-qa.md 4.2 KB
- references/message-spine.md 2.6 KB
- references/message-structure.md 3.5 KB
- references/source-policy.md 4.0 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 · 36 lines · 68 tokens per session scan A f85252e72f11
a1-business-message is a skill published in the GitHub repository ztemerbekov/a1-marketing-skills (8 stars, last pushed 13d ago), licensed MIT. It adds 68 tokens to every session and 726 once invoked, about $0.0003 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
deai_humanize
A Chinese-language writing helper that measures signs of machine-like writing and rewrites text to sound more natural and personal.
humanize-automation
Human-like mouse, keyboard and scroll behavior for behavioral bot bypass.
analytics-strategy
Design measurement frameworks including event taxonomy, KPI hierarchy, dashboard architecture, attribution models, and analytics implementation strategy. Use this skill whenever the user wants to plan analytics, design dashboards, build event taxonomies, define KPIs, set up tracking, or audit existing measurement.…
cro-optimization
Run conversion rate optimization through hypothesis-driven testing including audit, hypothesis generation, test design, statistical analysis, and rollout decisions. Use this skill whenever the user wants to optimize conversion, run A/B tests, audit a funnel, generate test hypotheses, design experiments, or analyze…
research-seo-demand
A Chinese-language process for researching SEO opportunities, where SEO means improving pages so they can appear in search results. It studies user needs, keyword demand, search-result pages, and competing pages using Bing data.
create-seo-page
A Chinese-language workflow for creating and implementing search-focused pages in an existing product repository. SEO means improving a page so it can be found and understood through search engines.