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 makoMakoGo/fish-claude --skill gpt-isms-stamp-outgit clone --depth 1 https://github.com/makoMakoGo/fish-claudeWrote 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/makomakogo/fish-claude/gpt-isms-stamp-out)<a href="https://agentmods.dev/skills/makomakogo/fish-claude/gpt-isms-stamp-out"><img src="https://agentmods.dev/badge/skills/makomakogo/fish-claude/gpt-isms-stamp-out/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/makomakogo/fish-claude/gpt-isms-stamp-out"><img src="https://agentmods.dev/badge/skills/makomakogo/fish-claude/gpt-isms-stamp-out.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00077 | $0.01946 |
| Opus 5 | $0.00039 | $0.00973 |
| Sonnet 5 | $0.00015 | $0.00389 |
| Haiku 4.5 | $0.00008 | $0.00195 |
Grade A, and why
gpt-isms-stamp-out 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 13d 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 — 199 lines — stays where its author put it; the contents beside it link to each section on GitHub.
GPT-Isms Stamp Out
Remove GPT-5.4 verbal tics from text. Apply these rules when editing or creating documents.
When to Apply
- User explicitly asks: "去 GPT 味", "去掉 AI 口癖", "de-GPT this", "stamp out GPT-isms", "clean up the AI voice"
- User asks to create a document — apply rules proactively to avoid tics in output
- User provides AI-generated text for cleanup
Detection Rules — Chinese (ZH)
Level 1: Must Remove — Structural Tics
「不是……而是……」句式 GPT-5.4 abuses this to manufacture faux cognitive contrast. Rewrite as direct statement.
❌ "能把她拉出来的不是道理，而是一个能让情绪重新对上的节拍"
✅ "节拍和旋律——而非道理——才能把她拉出来" (or just state B directly)
Rule: When the "negated A" is not a real viewpoint anyone holds, delete the negation and state B directly.
「把」字句泛滥 GPT-5.4 overuses 把-construction far beyond natural Chinese frequency.
❌ "GPT 把把字句使用得很多"
✅ "GPT 高频使用把字句"
结尾主动推销 Never end with unsolicited offers for follow-up.
❌ "如果你需要，我可以……" / "需要我……吗？" / "下一步，我可以……" / "只要你回复我"
✅ [Just stop. No trailing offer.]
Level 2: Must Remove — Filler Phrases
| Tic | Fix |
|---|---|
| "简单的说" / "简单来说" | Delete or use "简言之" sparingly |
| "总结一下" / "一句话总结" | Delete; just state the conclusion |
| "结论先说清楚" | Delete |
| "我逐步说清楚" | Delete |
| "我来解释" | Delete |
| "换句话说" | Delete or use "即" |
| "从某种角度来说" | Delete |
| "值得注意的是" / "值得一提的是" | Delete; if truly notable, let content speak |
| "综上所述" / "总而言之" | Delete |
| "首先……其次……最后……" | Restructure to avoid numbered-transition chain |
Level 3: Must Remove — Sycophancy
❌ "你问到问题的核心" / "你太清醒了" / "你说的太对了"
❌ "我会稳稳地接住你" / "我就在这里，不躲不藏，随时接住你"
❌ "你只是太久没被人接住了"
✅ [Delete entirely. No flattery, no pseudo-empathy.]
Level 4: Must Remove — Internet Corporate Jargon
| Tic | Fix |
|---|---|
| 兜底 | "保底" or rephrase |
| 落盘 | "确认" / "定下来" |
| 闭环 | "完整流程" or rephrase |
| 说穿 | Delete |
| 口径 | "说法" / "表述" |
| 拆开 / 抽层 / 收口 / 压实 | Rephrase in plain language |
| 顺一下 / 补一个 / 拉起 | Rephrase |
| 砍一刀 / 补一刀 / 切 / 狠狠干 | Delete violent metaphor |
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.
- 13d ago First seen · 199 lines · 77 tokens per session scan A 87ffcbb1b6bc
gpt-isms-stamp-out is a skill published in the GitHub repository makoMakoGo/fish-claude (169 stars, last pushed 1mo ago), licensed MIT. It adds 77 tokens to every session and 1,946 once invoked, about $0.0004 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 2026-08-30.
Other skills, from other repositories
reverse-engineering-tools
Investigate supplied game binaries, protection components, drivers, dumps, and traces through reproducible binary analysis. Use for repository resource selection, PE/symbol inspection, disassembly and decompilation, control/data-flow reconstruction, build comparison, obfuscation classification, and interface evidence…
frontend-patterns
Frontend development patterns for React, Next.js, state management, performance optimization, and UI best practices.
codex-skin-pack-installer
Install Codex themes and Codex skin packs with npx skills. Use this skill when a user wants Codex to find, download, validate, apply, switch, remix, or restore Codex desktop themes such as caishen-readable, caishen-lite, mythic-guardian-noir, global-founder-bright, export-night, or caishen-max. It stages verified…
eval-harness
An evaluation framework for AI-assisted development that defines pass/fail criteria, measures pass@k reliability, and runs regression checks. Eval-driven development means testing an agent's expected behavior before and after changes, much like tests for software.
gitnexus
A code-graph analysis add-on for examining an existing codebase, including symbols, call paths, execution flows, and effects across repositories. It can query GitNexus through its command-line or MCP interfaces.
launchfast-product-research
Codex-native multi-keyword Amazon opportunity scan using LaunchFast MCP. Use when the user wants to research 1-10 keywords, compare niches, or decide whether a product idea is a GO, INVESTIGATE, or PASS. Requires the LaunchFast MCP tool researchproducts.