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 skills/jaredlangleycc/nightshift-os/content-humanizernpx skills add jaredlangleycc/nightshift-os --skill content-humanizergit clone --depth 1 https://github.com/jaredlangleycc/nightshift-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/skills/jaredlangleycc/nightshift-os/content-humanizer)<a href="https://agentmods.dev/skills/jaredlangleycc/nightshift-os/content-humanizer"><img src="https://agentmods.dev/badge/skills/jaredlangleycc/nightshift-os/content-humanizer.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 | $0.00146 | $0.04066 |
| Opus 5 | $0.00073 | $0.02033 |
| Sonnet 5 | $0.00029 | $0.00813 |
| Haiku 4.5 | $0.00015 | $0.00407 |
Grade A, and why
content-humanizer 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.
How it starts
The opening of the file, as written. The whole thing — 397 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Content Humanizer
The active voice-scrubber. Takes any draft and returns a voice-clean version plus a diff log of what changed and why. Different from voice-rules, which is the template that defines what to enforce. Content-humanizer does the enforcement work on a specific piece of text.
When this skill triggers
Direct invocations:
- "Humanize this"
- "Make this sound human"
- "Remove AI tells"
- "Voice-scan this"
- "Does this sound like me"
- "Make this less AI"
- "Strip the AI smell"
- "Rewrite in my voice"
Automatic invocations (as the final pass before showing user a draft):
copywritingships any pageemail-sequenceships any lifecycle emailsocial-contentships any postoutreach-drafterships any cold emailnewsletter-broadcastships any campaignproposal-writerships any proposal section
NOT for: enforcing voice on the user's own input (the user can write any way they want). NOT for: editing direct quotes from other people. NOT for: code, table data, or technical reference material.
The humanization process (6 passes)
Run each pass in order. Track every change in the diff log so the user can see what got rewritten and why.
Pass 1: Pattern strip
The lowest-hanging tells. Pattern match, replace.
Em-dash strip. Replace every em-dash character (—) per voice-rules. Default rewrite:
- Mid-sentence em-dash with parenthetical content: convert to commas or parentheses
- Em-dash signaling a turn: split into two sentences
- Em-dash signaling emphasis: replace with comma or remove
Example:
Before: "Leadership coaching can feel abstract, that's why I built a 90-day framework." After: "Leadership coaching can feel abstract. That is why I built a 90-day framework."
"X, not Y" antipattern strip. Detect any "X, not Y" construction and rewrite affirmatively.
Example:
Before: "Lead with substance, not theater." After: "Lead with substance. Theater can wait."
Hedge word strip. Default-flag these and propose removal:
- just (when used as hedge: "I just wanted to...")
- really (when intensifier: "really important")
- basically
- actually
- simply
- literally
- honestly
- frankly
- totally
- definitely (when intensifier)
What ships with it
2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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 · 397 lines · 146 tokens per session scan A 784eac0dad78
content-humanizer is a skill published in the GitHub repository jaredlangleycc/nightshift-os (3 stars, last pushed 1mo ago), licensed MIT. It adds 146 tokens to every session and 4,066 once invoked, about $0.0007 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 2026-08-31.
Other skills, from other repositories
Brand Guidelines Generator
Create and maintain brand style guides for consistent visual identity.
web-vid
Turn a web app or marketing site into a recreated (not screen-recorded) Remotion promo video — pixel-faithful to the site's own design system, choreographed clicks/scrolls/zooms, rendered to MP4. Use when the user asks for a product demo video, a promo/teaser for LinkedIn or social, an "walkthrough video" of their…
pitchdocs
Generate marketing-quality repository documentation from codebase analysis. Scans 10 signal categories, extracts features with file-level evidence, and produces README, CHANGELOG, ROADMAP, and 15+ more docs. Zero runtime dependencies. For AI context file management, see ContextDocs.
demo-video-factory
Generate a custom 26s product-demo video from any SaaS URL — brand-matched scenes, a recreated product-UI "wow" scene, real screenshots, and a soundtrack. Use whenever the user wants a demo, promo, launch, or marketing video for a website or product.
brand
Brand context management for marketing sessions with continuity across conversations.
liking-factor-engineer
Analyze and engineer liking to increase rapport, persuasion, and compliance in marketing, sales, and communication contexts. Use this skill when the user wants to improve how much an audience likes them, their brand, or their message — including writing sales copy, designing onboarding flows, crafting brand voice…