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/indranilbanerjee/contentforge/create-contentgit clone --depth 1 https://github.com/indranilbanerjee/contentforgeWhat 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 | $0.00022 | $0.00851 |
| Opus 5 | $0.00011 | $0.00426 |
| Sonnet 5 | $0.00004 | $0.00170 |
| Haiku 4.5 | $0.00002 | $0.00085 |
Grade A, and why
create-content 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 2d 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.
Copies of this mod
1 near-identical copy found in the catalogue:
- create-content — 100% identical, 0 lines differ
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.
Create Content
If you see unfamiliar placeholders or need to check which tools are connected, see CONNECTORS.md.
This command is a thin wrapper around the ContentForge pipeline skill. It parses the user's inputs, then invokes the contentforge skill (skills/contentforge/SKILL.md), which owns the full Execution Protocol: run initialization, Step 0.5 title curation, the Pipeline Contract (phases 1–8, 10 quality gates), per-phase checkpointing, loop management, and the final .docx delivery. Do not re-implement any pipeline logic here.
Trigger
User runs /contentforge:create-content or asks to write, draft, create, or produce content (articles, blog posts, whitepapers, FAQs, or research papers).
Step 1 — Parse and gather inputs
Collect the following. If a required input is missing, ask before proceeding:
Required:
- Topic — the subject the content is about (e.g., "AI in Healthcare"). This is NOT the final title.
- Content type — one of:
article,blog,whitepaper,faq,research_paper,video_script,case_study,newsletter. Word-count and readability standards per type are defined in the skill's Content Types & Specifications table. - Brand — which brand profile to use. If none exists, offer
/contentforge:brand-setupor the skill's No-Brand Mode (non-regulated topics only).
Optional flags (pass through to the skill unchanged):
--audience="..."— target audience (e.g., "Healthcare CIOs")--keyword="..."— primary SEO keyword--word-count=<n>— overrides the content-type default--tone=<authoritative|conversational|technical|witty>— overrides brand default--sources=<urls or file>— user-supplied references (required in No-Web Mode)--title="Exact Title"— non-interactive title bypass (skips Step 0.5 option generation)- Competitor URLs to differentiate from
Step 2 — Invoke the pipeline skill
Invoke the contentforge skill (skills/contentforge/SKILL.md) with the gathered inputs. The skill performs, in order:
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.
- 2d ago First seen · 59 lines · 22 tokens per session scan A cdce8f4cc20c
create-content is a command published in the GitHub repository indranilbanerjee/contentforge (26 stars, last pushed 16d ago), licensed MIT. It adds 22 tokens to every session and 851 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 2026-08-30.
Other commands, from other repositories
engagement
Run a marketing engagement using the 12-Part methodology. Subcommands: start, next, status, validate, re-run-decision, update-back, lif-show, file-tree, list-engagements, four-core, growth-plan, yearly-planner, loop.
resume
Resume a long-running DMP workflow (engagement / campaign-plan / content-engine / seo-audit / competitor-analysis / campaign-audit / launch-campaign) that was interrupted partway through.
execute-action
Actually fire a campaign-audit / launch-campaign action against its real API (vs returning a manifest). Reads credentials from env vars (no OAuth flow). Read ops auto-execute with --execute; write ops require --confirm. Logs every execution to the audit trail.
check
Run the unified pre-publish quality gate on marketing content (hallucination + brand voice + structure + claims). Use before publishing any marketing copy.
status
Unified status snapshot of the active brand: profile, engagements, recent insights, recent compliance violations, Python dependency mode.
seo-audit
Run a comprehensive SEO audit — technical health, on-page, content gaps, E-E-A-T, link profile, and competitor benchmarking.