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 richfrem/agent-plugins-skills --skill humanizegit clone --depth 1 https://github.com/richfrem/agent-plugins-skillsWrote 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/richfrem/agent-plugins-skills/humanize)<a href="https://agentmods.dev/skills/richfrem/agent-plugins-skills/humanize"><img src="https://agentmods.dev/badge/skills/richfrem/agent-plugins-skills/humanize/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/richfrem/agent-plugins-skills/humanize"><img src="https://agentmods.dev/badge/skills/richfrem/agent-plugins-skills/humanize.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 | $0.00026 | $0.00519 |
| Opus 5.5 | $0.00010 | $0.00208 |
| Sonnet 5.5 | $0.00005 | $0.00104 |
| Haiku 4.5 | $0.00003 | $0.00052 |
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 17d 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 — 55 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Humanize Writing (humanize)
Transforms synthetic, stiff, or over-polished writing into natural text with an authentic human voice and rhythm.
Contents
Critical Constraints
- Preserve Source Facts: Never invent claims, details, or statistics not present in the original text.
- Default Output: Return rewritten text directly without conversational preamble or throat-clearing.
- Voice First: Do not merely strip bad patterns; replace them with natural character, rhythm, and concrete specifics.
Quick start
Identify the target channel and review the patterns catalog:
cat plugins/dev-utils/skills/humanize/references/patterns.md
Workflow
- Diagnose Fingerprints: Internally identify AI markers (triads, em dashes, semicolons, hollow filler) and the core factual thesis.
- Rewrite with Specifics:
- Prefer concrete details over abstractions ("cut latency in half" vs "improved performance").
- Maintain one clear idea per sentence and vary cadence across paragraphs.
- Calibrate register to the destination medium (LinkedIn, technical email, blog post, Slack).
- Channel Formatting: If a claim is pruned for lacking source evidence, append a footnote:
*(Removed: "X" -- no supporting detail in source.)*.
Verification
Run self-evaluative quality checks against the rewritten output:
- Read-Aloud Test: Does the text sound natural when spoken aloud?
- Fingerprint Scan: Confirm that hollow transitions ("Moreover", "Delve", "Crucial") and inflated adjectives are removed.
- Channel Fit: Verify length and formatting meet constraints in
channel-rules.md.
References
- acceptance-criteria.md — Acceptance criteria for voice rewriting and quality gates.
- channel-rules.md — Channel-specific length, structure, and formatting constraints.
- patterns.md — Comprehensive catalogue of artificial and synthetic writing patterns.
What ships with it
7 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.
- 17d ago Changed · -101 lines · -125 tokens per session ca39ae329461
- 1mo ago First seen · 156 lines · 151 tokens per session scan A 9c309021b2e1
humanize is a skill published in the GitHub repository richfrem/agent-plugins-skills (7 stars, last pushed yesterday), licensed MIT. It adds 26 tokens to every session and 519 once invoked, about $0.0001 per session on Opus 5.5. 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 2026-09-03.
Other skills, from other repositories
autoprompt
Run explicitly requested Autoprompt v2 work through the private controller. Ordinary coding and review requests do not activate this skill.
autoprompt
Run explicitly requested Autoprompt v2 work through the private controller. Ordinary coding and review requests do not activate this skill.
ap-route-analyst
Inspect only enough read-only project information to recommend a route and list the facts behind that recommendation.
ap-roadmap-author
Write one dependency-ordered roadmap with owners, integration points, success items, and real checks.
ap-depth-prober
Report the compatibility redirect to ap-worker; this retired role cannot perform new work.
ap-fresh-verifier
Report the compatibility redirect to ap-independent-checker; this retired role cannot perform new work.