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 skills add build-with-dhiraj/ai-workflow-framework-portability-kit --skill humanizergit clone --depth 1 https://github.com/build-with-dhiraj/ai-workflow-framework-portability-kitWrote 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/build-with-dhiraj/ai-workflow-framework-portability-kit/humanizer)<a href="https://agentmods.dev/skills/build-with-dhiraj/ai-workflow-framework-portability-kit/humanizer"><img src="https://agentmods.dev/badge/skills/build-with-dhiraj/ai-workflow-framework-portability-kit/humanizer/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/skills/build-with-dhiraj/ai-workflow-framework-portability-kit/humanizer"><img src="https://agentmods.dev/badge/skills/build-with-dhiraj/ai-workflow-framework-portability-kit/humanizer.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 | $0.00000 | $0.07526 |
| Opus 5.5 | $0.00000 | $0.03010 |
| Sonnet 5.5 | $0.00000 | $0.01505 |
| Haiku 4.5 | $0.00000 | $0.00753 |
Grade A, and why
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 28d 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 humanizer — 232 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 — 630 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Humanizer: Remove AI Writing Patterns
You are a writing editor that identifies and removes signs of AI-generated text to make writing sound more natural and human. This guide is based on Wikipedia's "Signs of AI writing" page, maintained by WikiProject AI Cleanup.
STEP 0 — PICK THE MODE (before you touch a word)
Two modes. Choosing wrong is the number one failure of this skill.
- STAKEHOLDER / EXEC mode — anything a decision-maker reviews: docs, slides, sheets, exec Slack or email, anything to a manager, director, or founder. Do pattern-removal + structural discipline. Add ZERO voice.
- PEER mode — casual Slack/email/DM to a teammate, a personal note, blog-style writing. Do pattern-removal + measured voice (the PERSONALITY section, dialed low).
Default: if the destination is a formal artifact or a reader senior to the writer, use Stakeholder mode. When unsure, use Stakeholder mode. It never reads as "too AI"; over-voiced peer writing does.
THE TRAP, never repeat it: reading "make it human" and reaching for the add-soul half. Added personality, opinions, and writerly flourishes are precisely what an exec reads as "too AI-led." In Stakeholder mode you do not add soul. You remove tells and impose structure. Full stop.
STAKEHOLDER / EXEC MODE — the spec (The the Director Test + gstack)
Not stylistic polish. Structural. The reader asks one question of every line: "why are you telling me this?" No decision it drives, no question it answers, cut it.
Rules, most important first:
- Decision-first. First line answers "why am I reading this?" Lead with the call, the number, the ask. Kill every word of preamble ("I wanted to share", "As discussed", "Here is").
- Bullets by default. Anything listable becomes bullets or a table. Prose is the exception. ("Rule of thumb: short, bulleted points always help." — the Director)
- Cut stray data. Every number, caveat, and clause earns its place or it goes. ("I am reviewing a doc that has stray data." — the Director)
- Altitude-matched. A Director gets the calls, the timeline, one north-star metric. Engineering depth (file:line, SQL, ticket IDs) lives in a SEPARATE artifact, never mixed in.
- Absolute dates only. "Mon 14 Jul", never "Monday" or "next week". (His comment: "which Monday?")
- One idea per sentence. No self-restating heading (a heading that just repeats the line under it).
- Show the trade-off, don't bury it. A cost or risk is a line, not a footnote.
- To the Director on a product change: outcome, then Scenario 1 (3 Sep 2026 PPP/1:1). He stopped a four-case CURATE walkthrough: "Just speak about scenarios. Scenario one." Not a yes-no tree. Not a workflow chart unless he asks. The chart is for tech. If CS does not need to operate it yet, do not explain it to them.
What ships with it
3 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.
- 28d ago First seen · 630 lines · 0 tokens per session scan A 9d3de73dc000
humanizer is a skill published in the GitHub repository build-with-dhiraj/ai-workflow-framework-portability-kit (5 stars, last pushed 15d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 7,526 tokens. A static security scan graded it A with 0 findings. It is 94% identical to humanizer, differing in 232 lines, and is treated as a copy.
Other skills, from other repositories
codeql
Run CodeQL database creation and security queries, add data-extension models, or process CodeQL SARIF. Use when CodeQL is explicitly requested; use security-review for a broader manual security review.
huggingface-vision-trainer
Train object-detection, image-classification, or SAM segmentation models on Hugging Face Jobs. Use for vision fine-tuning and evaluation; use huggingface-llm-trainer for language models.
sharp-edges
Identify error-prone APIs, dangerous configuration, and footgun designs that enable security mistakes. Use for API ergonomics, misuse resistance, secure defaults, or pit-of-success reviews; use code-review for general defects.
code-quality
Agents should invoke this skill for code reviews, linting/formatting setup, maintainability checks, complexity concerns, warning cleanup, coding standards, or quality gates in Rust, TypeScript, Python, shell, and mixed repos.
code-reviewer
Review code for bugs, logic errors, security vulnerabilities, code quality issues, and adherence to project conventions, using confidence-based filtering to report only high-priority issues that truly matter. Use this skill when reviewing a small set of changes locally (such as unstaged diff), when dispatched as a…
differential-review
Performs security-focused differential review of code changes (PRs, commits, diffs). Adapts analysis depth to codebase size, uses git history for context, calculates blast radius, checks test coverage, and generates comprehensive markdown reports. Automatically detects and prevents security regressions.