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/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/publish)<a href="https://agentmods.dev/commands/frankxai/agentic-creator-os/publish"><img src="https://agentmods.dev/badge/commands/frankxai/agentic-creator-os/publish/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/commands/frankxai/agentic-creator-os/publish"><img src="https://agentmods.dev/badge/commands/frankxai/agentic-creator-os/publish.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 | $0.00016 | $0.00672 |
| Opus 5.5 | $0.00006 | $0.00269 |
| Sonnet 5.5 | $0.00003 | $0.00134 |
| Haiku 4.5 | $0.00002 | $0.00067 |
Grade A, and why
publish 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 — 69 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/publish — Evidence-Bound Publishing Orchestrator
Publish a reviewed content packet through the active repository/CMS and verify the actual production result.
Contract
Read docs/content-intelligence.md and the target repository's instructions/content schema before action. Use the working article packet based on templates/content/article-packet.json.
/publish [path-or-content-id]
/publish --dry-run [path-or-content-id]
/publish --authority=PREVIEW|PUBLISH|DISTRIBUTE [path-or-content-id]
There is no --force, --skip-review, direct-to-main, hard-coded copy path, or fabricated live URL path. Resolve the canonical publisher from repository evidence.
Preflight
Require:
- stable content ID, canonical creator/property, repository/CMS path, and explicit authority;
- frozen thesis and reader consequence;
- source and typed claim ledgers with no unresolved central claim;
- truth/rights, commissioning editor, SEO/GEO, and production-verifier passes;
- governed media identities, provenance, rights, alt text, placements, and approval;
- correct commercial relationship, affiliate disclosure/link qualification, and current destination;
- index/canonical/sitemap/structured-data/internal-link plan;
- rollback or supersession path.
Return the exact blocker when any requirement fails.
Preview
- Create or reuse a content branch; never overwrite unrelated work.
- Apply the smallest coherent change according to the target content model.
- Run repository-native format, lint, type, content/schema, link, and production-build checks.
- Create a pull request with brief, source/evidence receipt, media placements, test results, risk, and rollback.
- Resolve the actual preview deployment and inspect mobile/desktop output:
- HTTP and rendered main content;
- title, description, author/dates, canonical, robots/snippet controls;
- JSON-LD matching visible content;
- images, alt text, crop, links, responsive behavior;
- analytics events and runtime/build errors.
- Mark
PREVIEW_LIVEonly when the pull request and preview are confirmed.
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 · 69 lines · 16 tokens per session scan A 36efa7f65898
publish is a command published in the GitHub repository frankxai/agentic-creator-os (12 stars, last pushed today), licensed Apache-2.0. It adds 16 tokens to every session and 672 once invoked, about $0.0001 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 2026-09-03.
Other commands, from other repositories
business-model
Explore business models using Lean Canvas, Business Model Canvas, Startup Canvas, or Value Proposition frameworks.
brainstorm
Brainstorm product ideas or experiments from PM, Designer, and Engineer perspectives — for existing or new products.
discover
Run a full product discovery cycle — from ideation through assumption mapping to experiment design.
setup-metrics
Design a product metrics dashboard with North Star metric, input metrics, health metrics, and alert thresholds.
triage-requests
Analyze, categorize, and prioritize a batch of feature requests from customers or stakeholders.
pricing
Design a pricing strategy — models, competitive analysis, willingness-to-pay estimation, and pricing experiments.