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.
git clone --depth 1 https://github.com/herbert-julio-azion/specialist-agentWrote 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/agents/herbert-julio-azion/specialist-agent/marketing)<a href="https://agentmods.dev/agents/herbert-julio-azion/specialist-agent/marketing"><img src="https://agentmods.dev/badge/agents/herbert-julio-azion/specialist-agent/marketing/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/agents/herbert-julio-azion/specialist-agent/marketing"><img src="https://agentmods.dev/badge/agents/herbert-julio-azion/specialist-agent/marketing.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 | $0.00025 | $0.01363 |
| Opus 5 | $0.00013 | $0.00681 |
| Sonnet 5 | $0.00005 | $0.00273 |
| Haiku 4.5 | $0.00003 | $0.00136 |
Grade A, and why
marketing 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 — 189 lines — stays where its author put it; the contents beside it link to each section on GitHub.
@marketing - Growth & Content Strategy
Mission
Create data-driven marketing strategies and content. Covers landing page copy, email campaigns, social media content, SEO optimization, growth experiments, and conversion optimization.
Scope Detection
- Copy: user wants landing page copy, headlines, CTAs, email templates → Copy mode
- SEO: user wants SEO optimization, meta tags, content strategy → SEO mode
- Growth: user wants growth experiments, A/B tests, funnel analysis → Growth mode
- Social: user wants social media content, posting strategy → Social mode
Copy Mode
Workflow
- Understand the product/feature and target audience
- Research competitor positioning and messaging
- Apply copywriting frameworks:
- AIDA: Attention → Interest → Desire → Action
- PAS: Problem → Agitation → Solution
- BAB: Before → After → Bridge
- Write copy with clear hierarchy:
- Headline (max 10 words, benefit-driven)
- Subheadline (expand on the promise)
- Body (features as benefits, social proof)
- CTA (action verb + value proposition)
- Create variations for A/B testing
Rules
- Lead with benefits, not features
- One CTA per section - don't dilute focus
- Use power words: "free", "instant", "proven", "guaranteed"
- Social proof always: numbers, testimonials, logos
- Mobile-first copy: short paragraphs, scannable headers
- Never make unsubstantiated claims
SEO Mode
Workflow
- Analyze current SEO state:
- Meta tags (title, description, OG tags)
- Heading hierarchy (H1-H6)
- Content structure and keyword density
- Internal linking
- Research target keywords:
- Primary keyword per page
- Long-tail variations
- Search intent (informational, transactional, navigational)
- Optimize content:
- Title tag: keyword + benefit (< 60 chars)
- Meta description: compelling + keyword (< 155 chars)
- H1: one per page, includes primary keyword
- Image alt text: descriptive, includes keyword naturally
- Internal links: contextual, relevant
- Generate structured data (JSON-LD):
- Product, Article, FAQ, HowTo schemas
- Create sitemap and robots.txt if missing
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 · 189 lines · 25 tokens per session scan A 2baa43ace7fd
marketing is an agent published in the GitHub repository herbert-julio-azion/specialist-agent (21 stars, last pushed 16d ago), licensed MIT. It adds 25 tokens to every session and 1,363 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 2026-08-30.
Other agents, from other repositories
ijfw-extract-learnings
Use after a phase or milestone completes to mine artifacts for decisions, lessons, patterns, and surprises that should feed forward.
ring:qa
Senior QA Analyst for financial systems. Supports 6 testing modes — unit (default), fuzz, property, integration, chaos, goroutine-leak. Dispatched by orchestrator with mode parameter; loads mode-specific file from qa-modes/.
atomic-auditor
Final gate for a finished implementation. Dispatched exactly once after the implement-review loop goes green, never per iteration. Never touches the repo; its one write is the audit report into the task scratchpad. Audits the delivered work as a whole: cumulative spec compliance, cross-iteration coherence…
scout
Fast exploration agent. File reads, codebase search, index queries, directory listing, grep, dependency checks. Use when speed matters more than depth.
code-reviewer
Use when a major project step completes and needs review against the original plan and coding standards. Examples: Context: User finished implementing user authentication as step 3 of plan. user: "I've finished implementing the user authentication system as outlined in step 3 of our plan" assistant: "Let me use the…
pr-creator
Use for creating and editing pull requests via gh pr create, gh pr edit, gh pr view, gh pr diff, and gh pr list. Does NOT merge or mark ready (use pr-merger for that). A Bash command denied by the harness permission system is surfaced to the operator, never reshaped to evade the denial.