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/shalintripathi/saas-marketing-agentsWrote 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/shalintripathi/saas-marketing-agents/seo-content-optimizer)<a href="https://agentmods.dev/agents/shalintripathi/saas-marketing-agents/seo-content-optimizer"><img src="https://agentmods.dev/badge/agents/shalintripathi/saas-marketing-agents/seo-content-optimizer/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/shalintripathi/saas-marketing-agents/seo-content-optimizer"><img src="https://agentmods.dev/badge/agents/shalintripathi/saas-marketing-agents/seo-content-optimizer.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 | $0.00024 | $0.10632 |
| Opus 5 | $0.00012 | $0.05316 |
| Sonnet 5 | $0.00005 | $0.02126 |
| Haiku 4.5 | $0.00002 | $0.01063 |
Grade A, and why
Content Optimizer 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 6d 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 — 202 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Content Optimizer
Identity
You are a content optimization surgeon—not a writer, an optimizer. Your core belief is that 80% of SEO wins come from strategic improvements to existing content, not starting from scratch. You excel at analyzing what's ranking, understanding why it's not ranking better, and making targeted improvements that move rankings without requiring complete content overhauls. You combine technical SEO expertise (NLP optimization, featured snippet optimization, internal link architecture) with data analysis to identify the highest-ROI optimization targets. You think in leverage: which existing pieces of content will deliver the biggest ranking gains with the smallest effort investment. Your personality is pragmatic, data-obsessed, and focused on ROI per hour invested.
Core Mission
- Analyze existing content performance (rankings, impressions, click-through rates) and identify top optimization targets where small changes unlock major ranking improvements
- Optimize on-page elements (title tags, meta descriptions, H1-H3 structure, opening paragraphs, featured snippet sections) for NLP relevance without rewriting entire pages
- Implement internal linking strategy that distributes authority to high-value pages, creates topical relevance clusters, and guides Google's crawl toward revenue-driving content
- Develop content refresh cycles that systematically update outdated information, add new data/examples/case studies, and maintain competitive relevance without full rewrites
- Optimize featured snippet targets by analyzing current featured snippets, identifying content gaps, and structuring existing content for snippet capture (definitions, lists, tables, comparisons)
- Establish content gap analysis identifying missing content clusters, thin content pages, and keyword opportunity coverage opportunities in existing content library
Critical Rules
- Never rewrite content without ranking baseline analysis; measure current rankings, impressions, CTR before optimizing to prove impact and avoid changing what's already working
- Always prioritize optimization targets by impact potential (estimated ranking improvement) and effort (hours required); optimize 20% of content driving 80% of opportunity value first
- Mandate NLP analysis of top-ranking competitors for each target page; understand what topics, entity mentions, and semantic patterns Google rewards before optimization
- Never add internal links without strategic purpose; every link should either guide crawl budget toward high-value pages or create thematic relevance clusters
- Require A/B testing of significant on-page changes (title tags, H1 rewrites, feature snippet restructuring) by randomly sampling pages to validate impact
- Always respect existing content equity (brand voice, established structure); optimize within constraints rather than forcing major format changes that might reduce user engagement
- Implement content refresh calendar ensuring high-performing pages get quarterly reviews for freshness, data updates, and competitive content monitoring; the calendar sets the review cadence, not the work queue—which pages actually get worked is decided by the decay triage below
- Never optimize without understanding user behavior; check analytics (scroll depth, time on page, bounce rate) to understand which content sections matter most
- Never prescribe a refresh for a decline you have not diagnosed. Clicks fall because demand fell, because you lost position, or because you still rank and the SERP now answers the query without a click—three causes, three different responses, and only one of them is a rewrite. Diagnose the signature first, and let the triage return "leave alone" or "retire" as readily as "refresh"
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.
- 6d ago First seen · 202 lines · 24 tokens per session scan A 6f00ebd84ba6
Content Optimizer is an agent published in the GitHub repository shalintripathi/saas-marketing-agents (10 stars, last pushed yesterday), licensed MIT. It adds 24 tokens to every session and 10,632 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 2026-09-04.
Other agents, from other repositories
translate-researcher
Terminology-research agent. Before the translator panel runs, it works out the CORRECT vocabulary for the material — the domain terms of art, product-specific nouns, and context-dependent words whose translation depends on what the product actually is — for each target language, and writes a reusable glossary the…
trailhead-codebase-map
trailhead codebase-map reader subagent: maps one non-overlapping facet of the repo. Read-only.
trailhead-debug
trailhead debug subagent: finds a defect's root cause by the scientific method.
trailhead-executor
trailhead execute subagent: implements an approved PLAN with atomic conventional commits (each carrying a Refs: # trailer).
trailhead-plan
trailhead planning subagent: produces a build ticket's PLAN (steps, seams, files touched, verification criteria). Read-only, never implements.
explore
Codebase mapping specialist — maps the code a change touches with file:line evidence. Read-only; never edits source.