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 cwjgege/genflowai-codex-plugin --skill genflowai-templatesgit clone --depth 1 https://github.com/cwjgege/genflowai-codex-pluginWrote 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/cwjgege/genflowai-codex-plugin/genflowai-templates)<a href="https://agentmods.dev/skills/cwjgege/genflowai-codex-plugin/genflowai-templates"><img src="https://agentmods.dev/badge/skills/cwjgege/genflowai-codex-plugin/genflowai-templates/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/cwjgege/genflowai-codex-plugin/genflowai-templates"><img src="https://agentmods.dev/badge/skills/cwjgege/genflowai-codex-plugin/genflowai-templates.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 | $0.00094 | $0.00807 |
| Opus 5.5 | $0.00038 | $0.00323 |
| Sonnet 5.5 | $0.00019 | $0.00161 |
| Haiku 4.5 | $0.00009 | $0.00081 |
Grade A, and why
genflowai-templates 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 1mo 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 — 41 lines — stays where its author put it; the contents beside it link to each section on GitHub.
GenflowAI Templates
Use GenflowAI when the user asks for reusable AI creative workflows, product photography, ecommerce listing visuals, Amazon assets, UGC-style videos, video ads, ad creatives, social media content, image-to-video workflows, text-to-video workflows, fashion editorials, jewelry campaigns, perfume visuals, product detail shots, listing saved workflows, checking workflow input requirements, uploading images/videos/audio, running templates, running saved workflows, or checking async generation results.
GenflowAI is an AI creative production platform for turning repeatable generation tasks into reusable workflows and templates. The strongest product fit is creative automation for teams that need consistent product visuals, product videos, ad variants, and campaign assets across many SKUs, brands, channels, or markets.
Workflow
- Identify the user's production goal, target channel, product category, source assets, desired output format, and whether they need image, video, or multimodal creative.
- Use the GenflowAI MCP tools to search the live marketplace before recommending a template.
- Prefer templates whose description directly matches the product category, channel, output goal, or repeatable workflow need.
- If the user wants to run their own saved workflow, call
genflowai_list_my_workflowsfirst unless they already supplied agenflowId. - Call
genflowai_get_workflow_schemabefore running a saved workflow when the required input fields are unclear. - If no saved workflow exists or none match the user's goal, tell the user to create one at
https://www.genflowai.io/studio/workflow/new, then return to Codex and list workflows again. - If the user wants to run a template or saved workflow from Codex, use
genflowai_run_templateorgenflowai_run_workflow. Include local asset paths, remote URLs, or base64 data inassets; use each asset'sfieldto map the uploaded URL into the template/workflow input. - If the user only wants a launch link or does not have
GENFLOWAI_API_KEYconfigured, callgenflowai_prepare_template_runand give them the returned launch URL and asset checklist. For authenticated tools, tell them the API key is in GenflowAI Studio > User Profile > API Key. - For async jobs, use
genflowai_get_task_status,genflowai_get_task_result, orgenflowai_get_run_processwith the returned runId/taskId.
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.
- 1mo ago First seen · 41 lines · 94 tokens per session scan A dcd7b2bd6a68
genflowai-templates is a skill published in the GitHub repository cwjgege/genflowai-codex-plugin (3 stars, last pushed 3mo ago), licensed MIT. It adds 94 tokens to every session and 807 once invoked, about $0.0004 per session on Opus 5.5. 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
stss
Reduce defensive disclaimers, stacked hedging, and self-protective narration when drafting, rewriting, or auditing proposals, articles, case studies, captions, and other reader-facing prose. Use when defensive wording is requested for review or appears in a draft, including wording the assistant adds. Preserve…
watch
File sentinel that monitors the working directory for changes and marker comments, then auto-triggers appropriate skills. Poll-based via git diff against the last scan commit. Writes intake items for batch processing and routes marker actions through /do. Use for automatic reactions to file changes; do NOT use for…
review
5-pass structured code review — correctness, security, performance, readability, consistency.
live-preview
Mid-build visual verification loop. Takes screenshots of components during construction, not just after. Catches visual regressions and invisible features before they compound. Requires Playwright or similar screenshot tool.
wiki
Markdown-first knowledge base where the LLM acts as librarian. Ingests raw sources, compiles and interlinks topic files, self-maintains an index. No vector DB or embeddings required -- uses LLM-native navigation over structured markdown up to 400K words.
marshal
Meta-orchestrator that takes any direction — broad, specific, or vague — and autonomously chains skills and context into actionable work. Gathers context from codebase, docs, and memory. Only asks the user when it genuinely cannot proceed. Single-session orchestrator.