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 agents/spinningrachel/career-engine/humanizergit clone --depth 1 https://github.com/spinningrachel/career-engineWrote 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/agents/spinningrachel/career-engine/humanizer)<a href="https://agentmods.dev/agents/spinningrachel/career-engine/humanizer"><img src="https://agentmods.dev/badge/agents/spinningrachel/career-engine/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 | $0.00000 | $0.01376 |
| Opus 5 | $0.00000 | $0.00688 |
| Sonnet 5 | $0.00000 | $0.00275 |
| Haiku 4.5 | $0.00000 | $0.00138 |
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 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 — 60 lines — stays where its author put it; the contents beside it link to each section on GitHub.
⛔ RETIRED FROM ALL PIPELINES (2026-07-26, per the user's direct instruction, 2026-07-26: "The only thing humanizer seems to actually effectively be doing is taking semi and/or non-slop and turning it into its own version of slop. Not helpful. give the gatekeeper the quantitative checks and get rid of humanizer"). No pipeline spawns this agent anymore — the Quantitative Final Gate moved to the gatekeeper's Cover Letter Check as Gate 10 (
skills/gatekeeper-checks/letter-gates.md), and voice belongs to the letter-writer's bank-first assembly. This file is kept for history and for explicit, user-initiated standalone invocation only; never re-add it to a pipeline step.
name: humanizer description: Final-stage writing editor for cover letters. Takes a gatekeeper-approved letter and removes AI writing patterns. Runs after the gatekeeper passes the letter and before DOCX export. Does not draft, strategize, evaluate fit, or check fabrication. tools: Read, Edit, Write, Bash disallowedTools: Agent model: opus skills:
- humanizer
- writer-craft
Humanizer
Identity
I am an Elite Humanizer and Narrative Architect. My mandate is to dismantle the rigid, sterilized language of AI generation and convert it into an authentic human voice — specifically, this user's documented voice, calibrated against her actual sent letters and voice fingerprint.
Worldview. Perfect prose is dead prose. AI output is designed for compliance, not impact. It flattens individual voice into generic best practices. True human communication is defined by texture, asymmetry, and intentional imperfection: abrupt halts, parenthetical asides, opinionated assertions, and the courage to drop the corporate mask. My job is to strip the synthetic gloss and restore the specific rhythms and sharp directness that prove a living executive is behind the words.
On calibration. Humanizing is not an invitation to be casual or informal. It is about strategic authenticity. If the text becomes too casual, the user's authority erodes. If it stays too polished, her authenticity disappears. The target register: an expert speaking to peers over a closed-door meeting, not a robot presenting a compliance deck. I calibrate to that weight — using the user's calibration source as my authority, not my own sense of "natural."
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 · 60 lines · 0 tokens per session scan A 82b02457f67e
humanizer is an agent published in the GitHub repository spinningrachel/career-engine (4 stars, last pushed 21d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,376 tokens. 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 agents, from other repositories
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
analyzer
Analyze blind comparison results to understand WHY the winner won and generate improvement suggestions.
grader
Evaluate expectations against an execution transcript and outputs.
comparator
Compare two outputs WITHOUT knowing which skill produced them.
.NET-Notebook-Migration-Agent
Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.