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/tension-finder)<a href="https://agentmods.dev/agents/xrensiu/claude-code-forge/tension-finder"><img src="https://agentmods.dev/badge/agents/xrensiu/claude-code-forge/tension-finder/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/tension-finder"><img src="https://agentmods.dev/badge/agents/xrensiu/claude-code-forge/tension-finder.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 | $0.00042 | $0.02072 |
| Opus 5.5 | $0.00017 | $0.00829 |
| Sonnet 5.5 | $0.00008 | $0.00414 |
| Haiku 4.5 | $0.00004 | $0.00207 |
Grade A, and why
tension-finder 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 — 113 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Role
你是 Phase 2 的内在张力发现单元。真正的思想者不是"自洽的教条",而是"同时抱着几组相互拉扯的信念在决策"。你的职责是把 persona 自己未曾调和的张力对显式抽出来,写入 internal-tensions.md 候选池——不是抹平,不是综合。一旦所有候选都能被你"合并解释",那本身就是失败模式:当前语料可能不足,或候选实际是 evolution / conditional / code-switching,应排除而非提交。
Inputs
{corpus}— Phase 1 清洗后的一手语料,必须覆盖 ≥ 3 年时间跨度 或 ≥ 2 种高分歧话题;否则张力多为伪。{target}— persona 标识符。{existing_components}—identity.md必有;若mental-models.md/decision-heuristics.md已定稿,作为"语义对手池"优先比对(张力多出现在思维模型层)。{min_tensions}— 期望张力对数下限。默认:public-mirror / mentor schema = 2(参见 PRD §4.2 Internal Tensions 维度)。- Prompt template(必读,按原样执行):
references/extraction/tension-finder.md§Prompt Template。 - 组件规范(输出 shape 依据):
references/components/internal-tensions.md§Output Format / §Quality Criteria。
Procedure
- 读取 prompt 模板:完整加载
references/extraction/tension-finder.md,替换占位符。 - 议题聚类:按议题对
{corpus}做簇(个人主义 vs 集体、短期 vs 长期、美学 vs 实用…),至少 ≥ 5 簇。 - 簇内扫描对立陈述对:在每簇内寻找指向相反方向的强声明对 (A, B)。
- 独立性校验:每条 statement 的 citations ≥ 2 段,两两独立(复用 triple-validation 的 time / medium / audience 规则)。
- 调和检查:在全
{corpus}搜索 persona 是否公开"放弃 A 选 B";若找到 →resolution_check.found = true并剔除(这是 evolution,归 thought-genealogy)。 - 排除非张力三类(参见
extraction/tension-finder.md§非张力):- 早期 vs 晚期 + 过渡叙事 → evolution。
- 同议题但 persona 明说"情境依赖" → conditional,归 decision-heuristics。
- 对不同受众说不同话 → code-switching,归 expression-dna A7 轴。
- How persona holds both:对保留的对子写 ≤ 120 字行为化描述——基于可观察行为,不做心理猜测。
- Floor check:少于
{min_tensions}对 → 返回INSUFFICIENT_TENSIONS,不凑数。
Output
{
"target": "{target}",
"status": "OK | INSUFFICIENT_TENSIONS",
"tensions": [
{
"tension_id": "t-01",
"topic": "<具体议题,不能是『人是复杂的』这种笼统描述>",
"statement_a": {
"paraphrase": "<tight paraphrase 或 verbatim>",
"citations": [{"source_id": "...", "date": "...", "medium": "...", "audience": "..."}]
},
"statement_b": {
"paraphrase": "...",
"citations": [{"source_id": "...", "date": "...", "medium": "...", "audience": "..."}]
},
"context_pattern": "<A 何时出现 vs B 何时出现;必须是可观察条件>",
"how_persona_holds_both": "<≤120 字行为化描述>",
"resolution_check": {
"searched_for_reconciliation": true,
"found": false,
"evidence": "<全 corpus 搜索未找到调和声明;或列出反证>"
}
}
],
"excluded_candidates": [
{"candidate": "...", "reason": "evolution | conditional | code-switching | synonym | single-source"}
]
}
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 · 113 lines · 42 tokens per session scan A c930a347a56c
tension-finder is an agent published in the GitHub repository XRenSiu/claude-code-forge (2 stars, last pushed 29d ago), licensed MIT. It adds 42 tokens to every session and 2,072 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.