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/neels-pluginsWrote 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/neels-plugins/output-folder)<a href="https://agentmods.dev/commands/indranilbanerjee/neels-plugins/output-folder"><img src="https://agentmods.dev/badge/commands/indranilbanerjee/neels-plugins/output-folder/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/neels-plugins/output-folder"><img src="https://agentmods.dev/badge/commands/indranilbanerjee/neels-plugins/output-folder.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 | $0.01190 |
| Opus 5.5 | $0.00008 | $0.00476 |
| Sonnet 5.5 | $0.00004 | $0.00238 |
| Haiku 4.5 | $0.00002 | $0.00119 |
Grade A, and why
output-folder 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 4d 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.
This is a copy
94% identical to output-folder — 0 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 108 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Output Folder
Show the user where ContentForge actually saves the finished .docx files, and (when supported) open that folder in the OS file manager. This is the answer to "where did my file go?" — a real question from the v3.12.2 user-feedback cycle.
Trigger
User runs /contentforge:output-folder, or asks any variant of "where did my file save", "I can't find the output", "open output folder".
Background
ContentForge writes two copies of every finished .docx:
- Internal tracking copy at
~/.claude-marketing/{brand}/tracking/outputs/{year}/{month}/{slug}_v1.0.docx. This is the system-of-record for/contentforge:cf-analytics,/contentforge:cf-audit, etc. It lives inside a dotfolder that Windows hides by default — users rarely find it. - User-visible published copy at
~/Documents/ContentForge/{brand}/{content_type}/{YYYY-MM}/{slug}.docx. If$CONTENTFORGE_PUBLISH_DIRis set it replaces the whole~/Documents/ContentForge/{brand}prefix — see the warning in Configuration below. This is the copy to surface.
The published copy was added in v3.12.3 specifically because end users reported "the file isn't saving on local drive" — it was saving, just somewhere they couldn't see.
Process
Step 1: Resolve the path
The published-output directory resolves exactly as local-tracker.py get_publish_dir() does — first non-empty wins:
--publish-diroverride, if passed$CONTENTFORGE_PUBLISH_DIR/if the env var is set — note: no{brand}segment is appended in this branch~/Documents/ContentForge/{brand-slug}/otherwise
A {content_type-slug} segment is appended after that base in every branch.
So when the env var is set, the resolved folder is $CONTENTFORGE_PUBLISH_DIR/{content_type}/ — the same tree for every brand. Report the path that actually resolves; do not invent a {brand} segment that isn't there.
Default to the active brand if no argument was provided. If neither is available, prompt: "Which brand's output folder? Run /contentforge:output-folder <brand> or set up a brand with /contentforge:brand-setup."
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.
- 4d ago First seen · 108 lines · 20 tokens per session scan A a2c1f7adbd3c
output-folder is a command published in the GitHub repository indranilbanerjee/neels-plugins (6 stars, last pushed 4d ago), licensed MIT. It adds 20 tokens to every session and 1,190 once invoked, about $0.0001 per session on Opus 5.5. A static security scan graded it A with 0 findings. It is 94% identical to output-folder, differing in 0 lines, and is treated as a copy.
Other commands, from other repositories
output-folder
Print the path to the ContentForge output folder and open it. "where is my output folder".
export
Export the brain to CSV for Sheets, Looker Studio, or any BI tool.
meeting-brief
Turn scattered context into a concise meeting prep brief.
change-plan
Create a comprehensive change management plan for a transformation initiative.
install
Guided setup for a new Cowork workspace. Interviews you (about 5 minutes) and generates a full, pre-configured cowork-os workspace (folders, copy, project instructions, and recurring routines).
start
The guided front door - run this first.