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 agentmods add skills/crossoverjie/skills/session-exportnpx skills add crossoverJie/skills --skill session-exportgit clone --depth 1 https://github.com/crossoverJie/skillsWrote 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/crossoverjie/skills/session-export)<a href="https://agentmods.dev/skills/crossoverjie/skills/session-export"><img src="https://agentmods.dev/badge/skills/crossoverjie/skills/session-export.svg" alt="Measured on agentmods" 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 | $0.00045 | $0.00827 |
| Opus 5 | $0.00023 | $0.00413 |
| Sonnet 5 | $0.00009 | $0.00165 |
| Haiku 4.5 | $0.00005 | $0.00083 |
Grade A, and why
session-export 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 3d 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 — 99 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Session Export Skill
Exports AI chat session conversations to readable Markdown files. Supports two modes for cross-agent compatibility.
Prerequisites
- Python 3 (standard library only, no external dependencies)
Usage
Mode 1: Claude Code Log Export (Preferred)
When running inside Claude Code, the script reads the full JSONL session logs for complete, accurate export (including messages that may have been compressed from context).
python3 skills/session-export/session_export.py --output-dir <directory> [options]
Options
--output-dir: Directory to save the exported markdown (env:SESSION_EXPORT_OUTPUT_DIR, default: current directory)--cwd: Project working directory to locate session logs (default: current directory)--session-id: Export a specific session ID (default: most recent)--name: Custom filename for the exported markdown (without .md extension). AI should summarize the session topic as the name--summarize: Request a summary to be generated after export--no-subagents: Exclude subagent conversations--max-tool-output: Max characters per tool output in export (default: 5000)
Examples
Export current session:
python3 skills/session-export/session_export.py --output-dir /tmp/sessions
Export a specific session:
python3 skills/session-export/session_export.py --session-id abc12345-... --output-dir ~/exports
Export without subagent conversations:
python3 skills/session-export/session_export.py --output-dir ./exports --no-subagents
Export with summary:
python3 skills/session-export/session_export.py --output-dir ./exports --summarize
Mode 2: AI Fallback Export
When the script exits with code 2 (Claude Code logs not found), the AI should fall back to writing the conversation directly from its current context:
- Create a markdown file in the specified output directory using the same format:
- YAML frontmatter with
session_id,project,exported_at,message_count,export_mode: ai-context - Each message as
## User/## Assistantwith timestamps if available - File named
session-fallback-<YYYY-MM-DD-HHMMSS>.md
- YAML frontmatter with
- Write each message from the current conversation context verbatim
- Note: messages compressed from context earlier in the conversation may be lost in this mode
What ships with it
2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 3d ago First seen · 99 lines · 45 tokens per session scan A 557a23183caa
session-export is a skill published in the GitHub repository crossoverJie/skills (19 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 45 tokens to every session and 827 once invoked, about $0.0002 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
gog-cli
Use this skill whenever the user wants to operate Google Workspace from the command line with gog/gogcli, including Gmail, Calendar, Drive, Docs, Sheets, Slides, Forms, Apps Script, Chat, Classroom, Contacts, Tasks, People, Groups, Admin, Keep, auth, configuration, scripting, or agent-safe Google automation. Prefer…
chinese-pdf-document-workflows
Class-level workflow for extracting, converting, editing, and producing polished Chinese PDFs and document reports from PDFs, papers, webpages, markdown, and video transcripts. Use when asked to create Chinese PDF reports, fix Chinese font/glyph rendering, summarize academic papers into Chinese insight reports…
agent-qa-authoring
Create, edit, validate, and run Agent QA tests, suites, and hooks through MCP or CLI while preserving canonical IDs and schema contracts.
akf-trust-metadata
The AI native file format. EXIF for AI — stamps every file with trust scores, source provenance, and compliance metadata. Embeds into 20+ formats (DOCX, PDF, images, code). EU AI Act, SOX, HIPAA aud.
docx
Use this skill whenever the user wants to create, read, edit, or manipulate Word documents (.docx files). Triggers include: any mention of "Word doc", "word document", ".docx", or requests to produce professional documents with formatting like tables of contents, headings, page numbers, or letterheads. Also use when…
docx
当用户需要创建、读取、编辑或处理 Word 文档（.docx）时，使用此技能。触发场景包括提到“Word 文档”、“.docx”，或要求生成带目录、标题、页码、信头等格式的专业文档；也包括提取或重组 .docx 内容、插入或替换图片、在 Word 文件中查找替换、处理修订或批注，以及将内容整理为正式 Word 文档。如果用户要求生成“报告”“备忘录”“信函”“模板”等 Word / .docx 交付物，也应使用此技能。不要用于 PDF、电子表格、Google Docs，或与文档生成无关的一般编程任务。.