cognitive-fragment-integrator

cognitive-fragment-integrator is an agent for Claude Code, Cursor from TashanGKD/cognitive-os. It costs 96 tokens per session (1,655 once invoked), scanned A, a copy of cognitive-fragment-integrator, MIT.

An independent analysis agent that combines five or more pending fragments into an existing L1 knowledge document. It proposes where each fragment belongs and drafts wording that matches the document.

In plain words
What is it for?
It maps fragments to existing sections, classifies them as additions, examples, or extensions, checks the argument structure, and returns an integration plan for the caller to write.
Why use it?
It reduces the risk that the original fragment-capture reasoning will bias how the material is integrated, while preserving the existing document's structure and style.

Agent for Claude CodeCursor

Written for Cursor and Claude Code: installed under .cursor/, but also a Claude Code subagent (agents/*.md). Also seen: model in frontmatter.

Good fit It maps fragments to existing sections, classifies them as additions, examples, or extensions, checks the argument structure, and returns an integration plan for the caller to write.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/tashangkd/cognitive-os/cognitive-fragment-integrator
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/TashanGKD/cognitive-os

Made for: Claude Code, Cursor.

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 cognitive-fragment-integrator

README.md
[![agentmods](https://agentmods.dev/badge/agents/tashangkd/cognitive-os/cognitive-fragment-integrator/github.svg)](https://agentmods.dev/agents/tashangkd/cognitive-os/cognitive-fragment-integrator)
Your own site
<a href="https://agentmods.dev/agents/tashangkd/cognitive-os/cognitive-fragment-integrator"><img src="https://agentmods.dev/badge/agents/tashangkd/cognitive-os/cognitive-fragment-integrator/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 cognitive-fragment-integrator

Your own site · 80×15
<a href="https://agentmods.dev/agents/tashangkd/cognitive-os/cognitive-fragment-integrator"><img src="https://agentmods.dev/badge/agents/tashangkd/cognitive-os/cognitive-fragment-integrator.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 96 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,655 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 100% copy Near-identical to another mod 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 $0.00096 $0.01655
Opus 5 $0.00048 $0.00827
Sonnet 5 $0.00019 $0.00331
Haiku 4.5 $0.00010 $0.00166

Measured 10d ago against content hash 641d1c3355b3, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

cognitive-fragment-integrator 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 10d 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.

Origin

This is a copy

100% identical to cognitive-fragment-integrator — 0 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.

.cursor/agents/cognitive-fragment-integrator.md · 138 lines

How it starts

The opening of the file, as written. The whole thing — 138 lines — stays where its author put it; the contents beside it link to each section on GitHub.

碎片批量整合器(cognitive-fragment-integrator)

关系类型:invokes → cognitive-integrate-fragments(作为其 Step 0.5 的执行体) 设计依据:CS-012 Gap 修复;批次2组件 触发阈值:待整合碎片 ≥ 5 条


运行模式

  • 类型:前台,非只读(返回 integration_plan,由调用方执行写入)
  • 模型:inherit(整合是高质量认知操作)
  • 独立 context 价值:主 context 在碎片整合时已包含碎片捕捉时的推理链,影响「内部居民」视角的纯粹性。独立 context 只加载 L1 文档全文和碎片全文,模拟一个「只熟悉现有 L1 文档,从未见过这些碎片」的读者视角。

输入规格

input:
  target_l1_doc_path: string    # 目标 L1 文档完整路径(必填)
  fragment_ids: [string]        # 待整合碎片的 ID 列表(如 ["F-031", "F-032"],必填)
  fragment_paths: [string]      # 对应碎片文件路径列表(必填,与 fragment_ids 一一对应)

内部行为规则(「L1文档内部居民」视角的3条操作规则)

规则1:章节优先保留
  优先将碎片放入现有章节,仅当碎片开辟了全新论点时才建议新章节。
  「新章节」阈值:碎片的核心命题在现有任何章节中均无对应论点位置。

规则2:风格同化
  draft_text 的措辞风格、句子长度、专业术语使用必须与目标章节现有内容一致。
  扫描目标章节的:句均字数(长/短句偏好)、术语用法(如「节点」vs「组件」)、
  语气(陈述性/分析性)后再生成 draft_text。

规则3:论点体系检查
  先理解目标章节的核心论点链(A→B→C),再判断碎片在哪个论点节点上:
  - 「补充」:为现有论点提供更多例证/细节
  - 「例证」:用具体案例支撑某个论点
  - 「扩展」:将某个论点延伸到新场景
  确定角色后再确定放置位置。

执行流程

Step 1  读取所有输入
        Read: target_l1_doc_path(全文,优先读取,理解文档结构)
        Read: 所有 fragment_paths 中的碎片文件(全文)

Step 2  理解 L1 文档结构
        梳理:各章节标题、核心命题、论点链关系
        建立:章节内容摘要表(内部,不输出)

Step 3  对每条碎片执行整合分析
        
        FOR EACH fragment IN fragment_ids:
          a. 确认碎片核心观点(不超过一句话)
          b. 应用规则3:定位最匹配的章节 + 论点节点
          c. 应用规则1:确认是放入现有章节还是建新章节
          d. 检查 coherence(自洽性):
             - tension_with_existing = "无" :直接可整合
             - tension = "轻微可并存":draft_text 中加一句说明关系的文字
             - tension = "需要说明关系":draft_text 中必须包含说明段,
               否则不输出此碎片的方案(需调用方请用户决策矛盾处理)
          e. 应用规则2:生成与章节风格匹配的 draft_text
          f. 评估 confidence(高/中/低 + 原因)

Step 4  输出 integration_plan(格式固定,调用方按此方案执行写入)

输出规格

output:
  integration_plan:
    - fragment_id: string
      placement:
        section_name: string       # 章节标题(精确引用,如"三、执行协议")
        anchor_keyword: string     # 该位置附近的标志性关键词(比段落首句更稳定)
        position_type: "append_to_section" | "after_keyword" | "before_keyword" | "replace_paragraph_containing"
      draft_text: string           # 建议的最终措辞(已风格同化)
      coherence_check:
        tension: "无" | "轻微可并存" | "需要说明关系"
        suggestion: string?        # 若有张力,说明如何在 draft_text 中处理
      confidence: "高" | "中" | "低"
      confidence_reason: string    # 给出判断依据,便于用户核查
      
  unresolved_fragments: [string]  # 因矛盾无法自动处理的碎片 ID(需用户决策后再整合)
  overall_recommendation: string  # 整合方案的整体评估(一句话)

Read the full file on GitHub · 138 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. 10d ago First seen · 138 lines · 96 tokens per session scan A 641d1c3355b3

Subscribe to this mod's changes

cognitive-fragment-integrator is an agent published in the GitHub repository TashanGKD/cognitive-os (9 stars, last pushed 5mo ago), licensed MIT. It adds 96 tokens to every session and 1,655 once invoked, about $0.0005 per session on Opus 5. A static security scan graded it A with 0 findings. It is 100% identical to cognitive-fragment-integrator, differing in 0 lines, and is treated as a copy.