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/indranilbanerjee/contentforgeWrote 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/indranilbanerjee/contentforge/publish)<a href="https://agentmods.dev/commands/indranilbanerjee/contentforge/publish"><img src="https://agentmods.dev/badge/commands/indranilbanerjee/contentforge/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/indranilbanerjee/contentforge/publish"><img src="https://agentmods.dev/badge/commands/indranilbanerjee/contentforge/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 | $0.00020 | $0.00506 |
| Opus 5.5 | $0.00008 | $0.00202 |
| Sonnet 5.5 | $0.00004 | $0.00101 |
| Haiku 4.5 | $0.00002 | $0.00051 |
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 21d 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.
What it actually says
Publish
This command is a thin wrapper. The complete publishing procedure lives in
skills/cf-publish/SKILL.md — read that file and execute it
end to end. Do not improvise a different flow from this wrapper.
Trigger
User runs /contentforge:publish or asks to publish, push, or deploy content to a CMS platform.
Gather inputs
If not provided in the arguments, ask before proceeding:
- Content source — Google Drive URL, local file path, or requirement ID (e.g.,
REQ-001) - Platform —
webfloworwordpress - Publish status —
draft,publish, orschedule(schedule requires an ISO date, e.g.2026-08-15T09:00:00) - Optional — collection/category, featured image, author override, tags, custom URL slug
Prerequisites (gate check)
- Content must have Phase 7 (Reviewer) approval — composite score >= 7.0 — AND Phase 8 (Output Manager) complete
- Content scoring below 5.0 is flagged for human review and cannot be auto-published
Execute
Follow skills/cf-publish/SKILL.md in full:
connector verification → load & validate → platform formatting → preview →
AI disclosure & provenance check (EU AI Act Article 50, applicable from 2 Aug 2026) →
publish/schedule/draft → post-publish verification → tracking update.
If no CMS connector is available, use the skill's HTML export fallback.
To set up a missing connector: /contentforge:cf-connect webflow or /contentforge:cf-connect wordpress.
After publishing
Ask: "Would you like me to:
- Create social media posts to promote this? (
/contentforge:social-adapt) - Publish to another platform?
- Add this piece to the next freshness/performance audit cycle? (
/contentforge:cf-audit) - Schedule the next content piece? (
/contentforge:cf-calendar)"
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.
- 21d ago Changed · +1 lines · +2 tokens per session 2aef70aaa6da
- 2mo ago First seen · 47 lines · 18 tokens per session scan A 59870d40768c
publish is a command published in the GitHub repository indranilbanerjee/contentforge (32 stars, last pushed yesterday), licensed MIT. It adds 20 tokens to every session and 506 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 2026-08-30.
Other commands, from other repositories
engagement
Drive the 12-Part engagement by subcommand: start, next, status, validate, loop. "advance to the next part".
status
Show production status for the active brand and month. "where are we on this month".
finalize
Finalize the month and package approved content for delivery. "close out the month".
verify-outcome
Recompute a recorded outcome from raw data and compare it against what was claimed.
content-brief
Generate a content brief for a keyword or topic: intent, competitors, outline. "brief this keyword".
edit-post
Edit an existing post's copy, visual direction or metadata. "tweak the copy on P07".