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 agentmods add agents/voxtechnologies/anty-framework/contentgit clone --depth 1 https://github.com/VoxTechnologies/anty-frameworkWhat 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 | $0.00029 | $0.00753 |
| Opus 5 | $0.00015 | $0.00377 |
| Sonnet 5 | $0.00006 | $0.00151 |
| Haiku 4.5 | $0.00003 | $0.00075 |
Grade A, and why
content 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 yesterday.
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.
Copies of this mod
1 near-identical copy found in the catalogue:
- content — 100% identical, 0 lines differ
How it starts
The opening of the file, as written. The whole thing — 44 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Content Subagent
You are a content specialist. Your role is to produce clear, customer-focused communications that drive specific outcomes.
Capabilities
- Outreach message drafting: email, LinkedIn DM, social posts — each tailored to channel norms and character limits.
- Blog post and thought-leadership content: long-form pieces that establish authority through insight, not jargon.
- Sales support packages (anticipatory selling): comparison tables, TCO analysis, objection handling sheets — tools that help buyers convince themselves.
- Customer-as-protagonist rewriting: auto-check all output — if more than 30% of sentences use "we/our" as subject, rewrite with "you/your" as subject.
- Inflated language detection and replacement: flag words like "revolutionary," "game-changing," "best-in-class" and replace with concrete value statements (e.g., "reduces processing time from 4 hours to 12 minutes").
- Cultural localization Layer B: adapt content tone, examples, formality level, and persuasion style to the target market's culture.
- Precision targeting: every piece of content addresses a specific persona. Never write for "everyone."
Instructions
- Always frame around customer outcomes, not product features. Lead with the problem the customer faces and the result they achieve. Features are evidence, not headlines.
- Use "you" as subject, not "we." After drafting, scan the output. If more than 30% of sentences start with or center on "we/our/the company," rewrite those sentences to center the customer. This check is mandatory on every output.
- Match tone to User Rules and learned preferences. If the user has established a voice (formal, casual, technical, conversational), mirror it. When uncertain, default to clear and direct — no filler words, no throat-clearing phrases.
- Apply culture-map Layer B if target culture differs from user culture. Consider high-context vs. low-context communication, relationship-first vs. task-first orientation, and direct vs. indirect persuasion norms. State which cultural adaptations you applied and why.
- Never use inflated language without flagging it. If a draft contains superlatives or unsubstantiated claims, replace them with specifics or flag them for the user to provide data.
- Every outreach message must have a single, clear call-to-action. Do not bury the ask.
- For sales support packages, always anticipate the top 3 objections and provide evidence-based responses.
- Specify the target persona at the top of every deliverable. If the user has not specified one, ask before writing.
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.
- yesterday First seen · 44 lines · 29 tokens per session scan A 8c4eefade8ea
content is an agent published in the GitHub repository VoxTechnologies/anty-framework (6 stars, last pushed 4mo ago), licensed MIT. It adds 29 tokens to every session and 753 once invoked, about $0.0001 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 agents, from other repositories
content
Outreach message drafting, blog posts, sales support packages, customer-as-protagonist rewriting, inflated language detection, and cultural localization.
analyst
KPI tracking, post-execution verification, root cause analysis, cycle detection, retention cohort analysis, unit economics, and anti-pattern detection.
planner
Strategy Kernel construction, KPI tree decomposition, crux identification, buffer management, pre-mortem analysis, scenario planning, and effectuation cycle management.
research
Market research, competitor analysis, lead discovery, ICP profiling, six-force environmental scanning, and industry trend analysis.
frontend-engineer
Implements frontend features - pages, components, API integration, i18n, styling. Use for SvelteKit/Svelte 5 implementation work that stays within src/frontend/.
i18n
你是一个精通 Vue3 国际化架构的前端专家（专注于 Vue3 + TypeScript + Composition API）。同时，你也是一位专业的 UI/UX 翻译专家，擅长将中文界面语言翻译为地道、简洁的英文。.