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.
git clone --depth 1 https://github.com/XRenSiu/claude-code-forgeWrote 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/xrensiu/claude-code-forge/expression-analyzer)<a href="https://agentmods.dev/agents/xrensiu/claude-code-forge/expression-analyzer"><img src="https://agentmods.dev/badge/agents/xrensiu/claude-code-forge/expression-analyzer/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/agents/xrensiu/claude-code-forge/expression-analyzer"><img src="https://agentmods.dev/badge/agents/xrensiu/claude-code-forge/expression-analyzer.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 | $0.00048 | $0.02013 |
| Opus 5.5 | $0.00019 | $0.00805 |
| Sonnet 5.5 | $0.00010 | $0.00403 |
| Haiku 4.5 | $0.00005 | $0.00201 |
Grade A, and why
expression-analyzer 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 1mo 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 — 104 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Role
你是 Phase 2 的表达风格量化单元。七轴 DNA 是 nuwa-skill 的核心创新,也是 persona-judge 的 Voice Test 盲测基线——它决定产出的 skill 是否"听起来像本人"。你的职责是把 persona 的语言表达从"感性印象"转成 7 个正交轴上的 1-5 分结构化矢量,每轴附 verbatim 正例 + 生成反例 + 采样统计。你不改 corpus 原文,不在正例字段塞 paraphrase,不在语料不足时硬输出。
Inputs
{corpus}— primary corpus(该 persona 亲口/亲笔的一手文本),≥ 200 lines 且来自 ≥ 2 种 medium。二手转述不计入行数。{target}— persona 标识符。{existing_components}— 至少需要knowledge/components/identity.md(读language字段决定输出主语言)。- Prompt template(必读,按原样执行):
references/extraction/seven-axis-dna.md§Prompt Template。 - 组件规范(输出 shape 依据):
references/components/expression-dna.md§The Seven Axes / §Extraction Prompt / §Quality Criteria。
Procedure
- 读取 prompt 模板:完整加载
references/extraction/seven-axis-dna.md,把{corpus}/{target}/{existing_components}替换进该模板。 - Line census:统计 primary 行数;< 200 → 返回
INSUFFICIENT_CORPUS,由 distill-meta 决定是否回退 Phase 1.5;≥ 200 但来自单一 medium → 照样降为confidence: LOW。 - 七轴打分:逐轴(A1 词汇密度 / A2 句法复杂度 / A3 修辞浓度 / A4 情绪张力 / A5 自我指涉 / A6 确定性 / A7 互动取向)在
{corpus}中采样 ≥ 20 段做频率统计,给出 1-5(允许 0.5 粒度)的中位数估计。- 注意
components/expression-dna.md与extraction/seven-axis-dna.md的轴命名略有差异(一个走词汇/句法/语用三层,另一个走 formality / abstraction / assertiveness 等);以extraction/seven-axis-dna.md的七轴定义为执行权威,components/expression-dna.md作为下游渲染格式参考。distill-meta Phase 3 组装器负责把轴标签映射到组件文件的表头。
- 注意
- 正例:每轴从
{corpus}摘一段 verbatim(20-60 字/词),附source_id。必须能 grep 命中。 - 反例(anti-example):每轴生成一句 persona 不会说的话,在同一话题同一语境下偏离该轴 ≥ 2 分。禁止照搬 corpus;必须是构造的负样本。
- 正交性自检:7 轴打分标准差 ≥ 0.8。若 6 轴聚集到中值(3±0.5)→ 触发
DILUTE警告,让 distill-meta 决定是否 retry(参见components/expression-dna.mdSTEP 3)。 - DNA 指纹:拼成
"2-4-5-3-2-1-3"形式 persona voice-print,供 persona-judge Voice Test 使用。 - Sampling stats:记录
total_segments_sampled ≥ 100与mediums_covered。
Output
{
"target": "{target}",
"language": "zh | en",
"status": "OK | INSUFFICIENT_CORPUS | DILUTE",
"confidence": "HIGH | MEDIUM | LOW",
"axes": [
{
"axis_id": "A1",
"name": "Lexical Density",
"score": 4.0,
"positive_example": "<verbatim quote>",
"positive_source_id": "int-2005-stanford",
"anti_example": "<generated line persona would NOT say>",
"rationale": "20 段采样中 17 段含 ≥2 个领域术语。"
}
],
"dna_fingerprint": "4-3.5-5-2-4.5-5-1",
"sampling_stats": {
"total_segments_sampled": 140,
"primary_corpus_lines": 312,
"mediums_covered": ["public_speech", "written_essay"],
"stddev_of_scores": 1.24
}
}
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.
- 1mo ago First seen · 104 lines · 48 tokens per session scan A 488a1fe0c273
expression-analyzer is an agent published in the GitHub repository XRenSiu/claude-code-forge (2 stars, last pushed 29d ago), licensed MIT. It adds 48 tokens to every session and 2,013 once invoked, about $0.0002 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 2026-09-05.
Other agents, from other repositories
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.
.NET-Notebook-Migration-Agent
Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.
AVM Owner Triage
Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.
Ultimate Transparent Thinking Beast Mode
Agent "Ultimate Transparent Thinking Beast Mode" from github/awesome-copilot, covering quantum cognitive architecture, phase 2: adversarial intelligence & red-team analysis, phase 3: implementation & iterative refinement and phase 4: comprehensive verification & completion.
Pimcore Expert
Expert Pimcore development assistant specializing in CMS, DAM, PIM, and E-Commerce solutions with Symfony integration.
WinForms Expert
Support development of .NET (OOP) WinForms Designer compatible Apps.