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 commands/frankxai/agentic-creator-os/article-creatorgit clone --depth 1 https://github.com/frankxai/agentic-creator-osWrote 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/commands/frankxai/agentic-creator-os/article-creator)<a href="https://agentmods.dev/commands/frankxai/agentic-creator-os/article-creator"><img src="https://agentmods.dev/badge/commands/frankxai/agentic-creator-os/article-creator.svg" alt="Measured on agentmods" 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 | $0.00019 | $0.00648 |
| Opus 5 | $0.00010 | $0.00324 |
| Sonnet 5 | $0.00004 | $0.00130 |
| Haiku 4.5 | $0.00002 | $0.00065 |
Grade A, and why
article-creator 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.
How it starts
The opening of the file, as written. The whole thing — 59 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/article-creator — Content Intelligence Article Pipeline
Create a source-grounded article and take it only as far as the operator's authority permits.
Contract
Read:
docs/content-intelligence.mdskills/blog-writing/SKILL.mdskills/seo-optimization/SKILL.mdworkflows/content/research-to-article.yaml
Create working state from templates/content/article-packet.json.
Default authority is DRAFT. A request to write does not silently authorize repository, deployment, CMS, scheduler, or social writes.
Invocation
/article-creator [topic or source]
/article-creator --authority=DRAFT|PREVIEW|PUBLISH|DISTRIBUTE [topic or source]
Infer routine context from the active repository and connected evidence. Ask only when a missing choice changes public identity, rights, secrecy, destructive scope, or publication authority. Do not force the user through a generic backlog/angle/length questionnaire.
Execution
- Resolve the task envelope: creator/property, canonical repository/CMS, audience, authority, rights, timing, and success condition.
- Inspect active instructions, current content model, existing related URLs, editorial state, live route, and performance evidence.
- Build the source and claim ledgers; capture current primary sources and a dated search/competitor snapshot when discovery matters.
- Pass the commission gate. Return one precise reporting assignment,
HOLD, orKILLwhen origin, evidence, or information gain is missing. - Freeze the thesis, reader consequence, strongest objection, canonical/internal-link role, offer/affiliate relationship, and media necessity.
- Draft in the active creator voice. Do not impose word count, keyword density, TL;DR, question headings, FAQ, link count, image count, or CTA unless the subject/repository requires it.
- Run independent truth/rights, commissioning/ICP, SEO/GEO, visual, and production lanes. Allow one substantive editorial rewrite.
- For
PREVIEW+, create a content branch and pull request, run repository-native checks, and inspect the rendered preview on mobile and desktop. - For
PUBLISH+, release only after every gate passes and verify the canonical production URL. - For
DISTRIBUTE, create channel-native objects with content ID, UTMs, disclosure, asset renditions, approval, remote result, and final URL. - Record T+0/T+7/T+28/T+90 measurement and freshness triggers.
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 · 59 lines · 19 tokens per session scan A 54bbadb934b4
article-creator is a command published in the GitHub repository frankxai/agentic-creator-os (10 stars, last pushed yesterday), licensed Apache-2.0. It adds 19 tokens to every session and 648 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 2026-09-03.
Other commands, from other repositories
security-audit-static
Static security audit of AI-built code — map trust boundaries, cross-reference documented intent, self-refute every finding, and report only evidence-backed risks.
performance-audit-static
Static performance audit of AI-built code — find N+1 queries and request waterfalls, over-fetching, missing indexes, and caching opportunities, ranked by effort and impact.
sprint
Sprint lifecycle — plan a sprint, run a retrospective, or generate release notes.
document-app
Reverse-engineer an AI-built codebase into the system documents reviewers and auditors need — a core set (architecture, flows, permissions, variables) plus conditional docs (emails, cron, SEO, automation) when they apply.
analyze-test
Analyze A/B test results — statistical significance, sample size validation, and ship/extend/stop recommendations.
meeting-notes
Summarize a meeting transcript into structured notes with decisions, action items, and follow-ups.