tension-finder

tension-finder is an agent for Claude Code from XRenSiu/claude-code-forge. It costs 42 tokens per session (2,072 once invoked), scanned A, original, MIT.

A tension-finding agent searches a person's source material for pairs of beliefs or decisions that pull in opposite directions. It preserves genuine contradictions instead of forcing them into one consistent story.

In plain words
What is it for?
It compares statements across topics and time, verifies them with source passages, and records unresolved internal tensions for a persona skill.
Why use it?
It helps a persona reflect real changes, trade-offs, or unresolved conflicts rather than presenting a simplified set of rules. It requires enough varied material to distinguish real tension from missing context.

Agent for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: model in frontmatter.

Part of the persona-distill plugin — 5 skills, 16 agents shipped together

Good fit It compares statements across topics and time, verifies them with source passages, and records unresolved internal tensions for a persona skill.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/xrensiu/claude-code-forge/tension-finder
Install

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.

Clone the repo
git clone --depth 1 https://github.com/XRenSiu/claude-code-forge

Made for: Claude Code.

Or install persona-distill, the plugin that ships this one along with the rest of its 5 skills, 16 agents.

Wrote 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.

agentmods badge for tension-finder

README.md
[![agentmods](https://agentmods.dev/badge/agents/xrensiu/claude-code-forge/tension-finder/github.svg)](https://agentmods.dev/agents/xrensiu/claude-code-forge/tension-finder)
Your own site
<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.

agentmods 80×15 button for tension-finder

Your own site · 80×15
<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>
Per session 42 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 2,072 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce 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

Measured 1mo ago against content hash c930a347a56c, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

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.

plugins/persona-distill/skills/distill-meta/agents/tension-finder.md · 113 lines

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

  1. 读取 prompt 模板:完整加载 references/extraction/tension-finder.md,替换占位符。
  2. 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。
  3. 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)。
  4. 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)。
  5. 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)。
  6. 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。
  7. 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。
  8. 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"}
  ]
}

Read the full file on GitHub · 113 lines

Changes

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.

  1. 1mo ago First seen · 113 lines · 42 tokens per session scan A c930a347a56c

Subscribe to this mod's changes

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.