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/tqnonline/agent-forge/humanizenpx skills add tqnonline/agent-forge --skill humanizegit clone --depth 1 https://github.com/tqnonline/agent-forgeWrote 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/tqnonline/agent-forge/humanize)<a href="https://agentmods.dev/skills/tqnonline/agent-forge/humanize"><img src="https://agentmods.dev/badge/skills/tqnonline/agent-forge/humanize.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 | $0.00120 | $0.02225 |
| Opus 5 | $0.00060 | $0.01112 |
| Sonnet 5 | $0.00024 | $0.00445 |
| Haiku 4.5 | $0.00012 | $0.00222 |
Grade A, and why
humanize 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 3d 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 — 161 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Humanize: Writing Transformation System
Transform AI-generated or AI-sounding text into genuinely human prose — or generate new content that reads as unmistakably human from the first word. This is not a pattern-removal checklist. It is a four-phase transformation system that detects, calibrates, transforms, and verifies.
The test: if someone reads the output and thinks "an AI wrote this," the skill has failed.
Voice Shortcodes
Four regional English voices, each grounded in its origin and proud of it. Default is OX unless another is specified.
| Code | Voice | One-line |
|---|---|---|
OX |
Oxford English | Senior diplomat at Chatham House — quiet authority, educated warmth |
SF |
American English | Foggy Bottom meets Sand Hill Road — strategic gravitas, builder velocity |
AB |
Canadian English | Albertan prairie directness — no-nonsense warmth, global polish |
ST |
Indian English | Tharoorian eloquence calibrated for boardroom clarity — erudite yet precise |
When the user specifies a shortcode, load references/voice-profiles.md for the full voice specification. When no shortcode is given, apply OX as default.
The Four Phases
Phase 1: Detect
Scan the input for AI patterns across three levels. Consult references/pattern-library.md for the full taxonomy.
Document level — structural predictability, paragraph symmetry, formulaic section ordering, absence of genuine digressions or callbacks.
Paragraph level — cadence uniformity (sentences clustering around 18-22 words), semantic front-loading, the zoom-out reflex, transitional scaffolding.
Sentence level — the original tells: significance inflation, promotional language, -ing analyses, vague attributions, em dash overuse, rule of three, AI vocabulary words, negative parallelisms, sycophantic tone, filler phrases, excessive hedging, copula avoidance.
Quick-reference — the 10 highest-signal patterns:
- Significance inflation — "pivotal moment," "enduring testament," "evolving landscape"
- AI vocabulary cluster — additionally, crucial, delve, enhance, foster, garner, intricate, landscape, pivotal, showcase, tapestry, testament, underscore, vibrant
- Cadence uniformity — every sentence roughly the same length and structure
- Copula avoidance — "serves as," "stands as," "functions as" instead of "is"
- Superficial -ing phrases — "highlighting," "underscoring," "reflecting," "symbolizing"
- Promotional language — "groundbreaking," "nestled," "vibrant," "breathtaking," "renowned"
- Transitional scaffolding — mechanical "That said," "To be sure," "What's more"
- Epistemic cowardice — "some argue," "others contend" without taking a position
- Emotional flattening — everything is "interesting" or "notable" but never genuinely felt
- Communication artefacts — "Great question!", "I hope this helps!", "Let me know if..."
What ships with it
5 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.
- 3d ago First seen · 161 lines · 120 tokens per session scan A 4c2f67ee2697
humanize is a skill published in the GitHub repository tqnonline/agent-forge (2 stars, last pushed 3mo ago), licensed BSD-3-Clause. It adds 120 tokens to every session and 2,225 once invoked, about $0.0006 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
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
brainstorming
You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.
auto-perf-optimize
Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.
chat-perf
Run chat perf benchmarks and memory leak checks against the local dev build or any published VS Code version. Use when investigating chat rendering regressions, validating perf-sensitive changes to chat UI, or checking for memory leaks in the chat response pipeline.
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…