Skip to content
Agentmart
Submit a tool

session-forensics

给 agent 会话配「观察者」：读完整会话历史（Codex rollout JSONL、Claude Code transcript、 Kimi wire、DeepSeek Harness / dsh 的 zstd 会话，含 subagent/team 日志）， 用「物证流 vs 叙事流」对质，找出执行…

Skill by cyl19970726

IndexedLicense unknown★ 1
Write a review

Chalk Labs

Need help deploying session-forensics?

Chalk Labs sets up agents like this inside real teams: connected to your tools, tested on your data, with a human in the loop where it matters.

Book a call

Install

Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.

npx agentmarket install skill/cyl19970726-session-forensics

Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.

Get the weekly diff

The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.

We use your email only for this newsletter. Privacy

About

给 agent 会话配「观察者」：读完整会话历史（Codex rollout JSONL、Claude Code transcript、 Kimi wire、DeepSeek Harness / dsh 的 zstd 会话，含 subagent/team 日志）， 用「物证流 vs 叙事流」对质，找出执行 agent 自己 原理上看不见的问题。四种能力：① audit——审计求解过程是否病态（空转、卡住、目标漂移、 gate 膨胀、修工具循环、假通过）；② handoff——交接包（压缩/中断/换人/跨 CLI 时， --check 闸保证完成度）；③ progress probe——运行中探针（silent worker / subagent 现在 在干什么，秒级判定，防空等）；④ harvest——沉淀（从历史挖出该固化成 skill/gate/harness 的东西）。当出现：读 session 历史、复盘会话、审计另一个 agent、为什么进度这么慢、 为什么一直失败、agent 卡住了、subagent 在干嘛、compaction 之后丢了什么、 要交接给下一个 agent、~/.codex/sessions、~/.dsh/sessions、rollout jsonl、session.jsonl.zstd、 dsh 会话、deepseek harness 历史、agent 复盘 —— 时使用本 skill。 ⚠️ 不要用向量检索/RAG/agent-memory 读 session（实证判死，见 §禁止事项）。

Use cases: ml, security, agent-building

Reviews

Write a review

No reviews yet. Installed it? Reviews come from verified installers only. How reviews work

Permissions

What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.

Tools
No tools found
Secrets
None asked for
Install scripts
None found
Runs as
Python package

Network hosts it talks to 1

  • codeload.github.com · found in install command

Files it touches

  • ~/.claude/skills/session-forensics

What's inside

Skill name
session-forensics
Description
给 agent 会话配「观察者」：读完整会话历史（Codex rollout JSONL、Claude Code transcript、 Kimi wire、DeepSeek Harness / dsh 的 zstd 会话，含 subagent/team 日志）， 用「物证流 vs 叙事流」对质，找出执行 agent 自己 原理上看不见的问题。四种能力：① audit——审计求解过程是否病态（空转、卡住、目标漂移、 gate 膨胀、修工具循环、假通过）；② handoff——交接包（压缩/中断/换人/跨 CLI 时， --check 闸保证完成度）；③ progress probe——运行中探针（silent worker / subagent 现在 在干什么，秒级判定，防空等）；④ harvest——沉淀（从历史挖出该固化成 skill/gate/harness 的东西）。当出现：读 session 历史、复盘会话、审计另一个 agent、为什么进度这么慢、 为什么一直失败、agent 卡住了、subagent 在干嘛、compaction 之后丢了什么、 要交接给下一个 agent、~/.codex/sessions、~/.dsh/sessions、rollout jsonl、session.jsonl.zstd、 dsh 会话、deepseek harness 历史、agent 复盘 —— 时使用本 skill。 ⚠️ 不要用向量检索/RAG/agent-memory 读 session（实证判死，见 §禁止事项）。
License
unknown
Instructions
268 lines in SKILL.md · view on GitHub

Before installing

  • Ships executable scripts

Files (21)

  • SKILL.md
  • openai.yaml · agents/
  • codex-jsonl.md · references/
  • dsh-jsonl.md · references/
  • handoff-packet.md · references/
  • mental-model.md · references/
  • platforms.md · references/
  • self-upgrade.md · references/
  • signatures.md · references/
  • batch_scan.py · scripts/
  • calibrate.py · scripts/
  • confirm_patterns.py · scripts/
  • drill.py · scripts/
  • handoff_packet.py · scripts/
  • harvest_report.py · scripts/
  • progress_probe.py · scripts/
  • selftest_dsh.py · scripts/
  • session_events.py · scripts/
  • session_locate.py · scripts/
  • session_metrics.py · scripts/
  • sync_skill.sh · scripts/

The license isn't open source, so the instructions aren't shown here. Read SKILL.md on GitHub

More from cyl19970726/reuse-agent-infra

Signals

Stars
1
Forks
0
Open issues
0
Last commit (this folder)
Sep 15, 2026 (1 month ago)

From GitHub (fetched Oct 24, 2026).

Details

License
License unknown
Repository
github.com/cyl19970726/reuse-agent-infra
First seen
Oct 24, 2026
Last checked
Oct 24, 2026
Source
GitHubgithub-graphql

More from cyl19970726

Done for you

Rather not set it up yourself?

Chalk Labs scopes, builds and runs agents for your team: the task audit, the eval harness, the integrations and the weekly ops report. Fixed scope, priced before we start.

See how we build AI agents →Read the case studies

Chalk Labs is a two-founder AI and growth studio. We build AI agents, CRMs and MVPs for Web3 and AI companies, and have shipped 50+ product and token launches.

launches shipped
50+
launches shipped
media placements
500+
media placements
founders on every account
2
founders on every account

Press we've placed: Forbes · CoinDesk · Decrypt · Cointelegraph · The Block

Rahil Jain, Co-founder, Chalk Labs. Ex-Goldman Sachs engineer. You talk to the person who builds it.

Get session-forensics running in your business

Tell us what you want to automate. A founder replies within one working day with a plan, not a pitch deck.

Goes to the Chalk Labs founders, not the newsletter. Privacy

Need help deploying session-forensics?

CallGet help
Cite this page

session-forensics skill. Agent Mart. https://agentmart.dev/skills/cyl19970726-session-forensics (last updated 2026-10-24)