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 Xe/agent-plugins --skill sound-like-a-persongit clone --depth 1 https://github.com/Xe/agent-pluginsWrote 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/xe/agent-plugins/sound-like-a-person)<a href="https://agentmods.dev/skills/xe/agent-plugins/sound-like-a-person"><img src="https://agentmods.dev/badge/skills/xe/agent-plugins/sound-like-a-person.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 5.1 | $0.00066 | $0.01181 |
| Opus 5 | $0.00033 | $0.00590 |
| Sonnet 5 | $0.00013 | $0.00236 |
| Haiku 4.5 | $0.00007 | $0.00118 |
Grade A, and why
sound-like-a-person 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 7d 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 — 127 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Sound Like a Person
Make writing read like it came from someone who lived it, not someone performing competence. The target is prose a real person would say out loud without second-guessing every word.
This skill complements stop-slop (which removes specific AI tells) by
focusing on the felt quality of voice — pacing, conviction, the small
unevenness that signals a human was here.
When to Use
- A draft is grammatically clean but sounds like nobody.
- Sentences are all roughly the same length and shape.
- The piece reads as if it's trying not to offend anyone.
- Every paragraph lands on a tidy quotable line.
- You can't tell who wrote it from the writing itself.
The Six Passes
Run these in order. Each pass has one job. Don't try to do all six at once — you'll dilute every one.
1. Real Person Rewrite
Read it as someone who actually lived the thing being described. Cut anything that feels rehearsed, overbuilt, or written to sound impressive. A person recounting an experience is a little rougher and more direct than a person constructing an essay.
Ask: Would someone actually say this, or only write it?
2. Thought Flow Fix
This is not a grammar pass. It's a thinking pass. Real minds move unevenly — punchy in places, slower in others, occasionally circling back. If the prose moves at one steady tempo, break the pattern. Shorten a sentence that's pacing itself. Let one breathe longer than expected.
Ask: Does this read like a mind working, or like a metronome?
3. Pattern Disruptor
Spot the tells: tricolons, balanced contrasts, em-dash reveals, paragraphs that all open the same way, sentences that all resolve neatly. Strip them one by one. Vary structure. Soften phrasings that feel templated. Each word should feel chosen in the moment, not generated by a pattern.
Ask: Would removing this sentence's twin make the piece feel more honest?
4. Voice Shaper
A real person has a point of view. They prefer some things over others. They're allowed small contradictions. The piece should belong to one person, not read like a neutral observer trying to please everyone. Let opinions through. Let tone shift naturally when the subject does.
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.
- 7d ago First seen · 127 lines · 66 tokens per session scan A 9e9dc723acf6
sound-like-a-person is a skill published in the GitHub repository Xe/agent-plugins (2 stars, last pushed 2mo ago), licensed MIT. It adds 66 tokens to every session and 1,181 once invoked, about $0.0003 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.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…
chronicle
Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…
babysit-pr
Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…