ce-session-extract
Extract conversation skeleton or error signals from a single session file at a given path. Invoked by session-research agents after they have selected which sessions to deep-dive — not intended for direct user queries.
Best for Agent workflowsWorks with GitHubLow risk
⌘source
- author
@EveryInc- language
- TypeScript
★15kstars
1.2kforks
Apr 21, 2026
✦overview.md
Key Features
- ·Extracts conversation skeletons from session files
- ·Extracts error signals from session files
- ·Processes JSONL session files from Claude Code, Codex, or Cursor
- ·Supports head or tail output limiting
- ·Designed for agent use, not direct user invocation
Use Cases
- →Session-research agents extracting key content from selected session files
- →Agents analyzing conversation patterns without loading full session files
- →Debugging agents identifying error signals in session histories
Best for
- ✓Agent workflows
- ✓Session analysis pipelines
Not ideal for
- !Direct user queries
- !Real-time processing
FAQs
name
ce-session-extract
description
Extract conversation skeleton or error signals from a single session file at a given path. Invoked by session-research agents after they have selected which sessions to deep-dive — not intended for direct user queries.
user-invocable:false
context:fork
Session extract
Agent-facing primitive. Extract filtered content from a single Claude Code, Codex, or Cursor session file — either a conversation skeleton or error signals.
This skill exists so that agents do not read multi-megabyte session files into context. The scripts under scripts/ own the JSONL shape knowledge and emit a narrative-readable digest.
Arguments
Space-separated positional args:
<file>— absolute path to a session JSONL file (typically afilevalue returned byce-session-inventory).<mode>—skeletonorerrors.<limit>(optional) —head:Nortail:Nto cap output at N lines (e.g.,head:200). Omit to return full extraction.
Execution
Skeleton mode — narrative of user messages, assistant text, and collapsed tool-call summaries:
cat <file> | python3 scripts/extract-skeleton.py
Errors mode — just error signals:
cat <file> | python3 scripts/extract-errors.py
$install
1-click copynpx skills add EveryInc/compound-engineering-plugin --skill ce-session-extractSafety assessment
★
Clarity score
How clear and easy to understand the SKILL.md instructions are, rated from 1 to 5.
5/ 5
excellentVery clear and well structured, with almost no room for misunderstanding.
◎
Actionability score
How directly an agent can act on the SKILL.md instructions, rated from 1 to 5.
5/ 5
very highHighly actionable with clear, concrete steps that an agent can follow directly.