session-list
Skill0 starsChanged 9 months agoMITView on GitHub
Lists all sessions for a work stream or topic. Use when user asks "what have we done on X?", reviewing session history, or looking for specific session.
2 other projects use a version of this.
Adopted by
Most recently taken up by
- apappascs/claude-code-sessionstheir own version, first seen Nov 1, 2026
- manastalukdar/ai-devstudiotheir own version, first seen Oct 13, 2026
Other versions2 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 2
- apappascs/claude-code-sessions★ 2same name
- manastalukdar/ai-devstudio★ 1same name
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository18 other files it gives its agents.
- CLAUDE.mdCLAUDE.md
- adr-createSkill
- dev-log-rotateSkill
- discovery-startSkill
- gather-insightSkill
- git-commitSkill
- init-projectSkill
- insight-captureSkill
- jira-startSkill
- review-implementationSkill
- session-endSkill
- session-startSkill
- team-stream-startSkill
- work-stream-startSkill
- worktree-endSkill
- worktree-listSkill
- worktree-removeSkill
- worktree-startSkill
The file
We split this skill into the rules it gives an agent
10 rules. About 0 are common, 9 are distinctive, and 1 is very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈9
Distinctive · estimate
This author's own choices. Worth a look.
1
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 35
Read .claude/project-config.md if it exists
- Distinctive: line 40
Use default path listed above
- Distinctive: line 51
If ambiguous or not specified, ask user:
- Distinctive: line 58
Use Glob to find all session files:
- Distinctive: line 69
If no sessions found:
- Distinctive: line 78
Read first ~30 lines of each session file to get:
- Distinctive: line 90
Default: Oldest first (shows progression)
- Distinctive: line 284
Ask if user wants to create new topic
- Distinctive: line 287
Check if work stream document exists (but no sessions yet)
- Distinctive: line 297
Ask: "Which topic would you like to see sessions for?"
≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Session List Skill
Provides quick overview of all sessions for a given topic, showing chronological history of work.
When to Use
Activate this skill when:
- User asks "what have we done on X?"
- User says "list sessions for..."
- Reviewing session history for a topic
- Looking for specific session
- Understanding work cadence/velocity
- Preparing summary or report
Purpose
Provides visibility into session history:
- See all work done on a topic at a glance
- Understand chronological progression
- Identify patterns or gaps
- Find specific sessions quickly
- Estimate complexity of remaining work
Instructions
Step 0: Read Project Config
- Read
.claude/project-config.mdif it exists - Parse
## Documentation Pathssection to get:- Sessions path (default:
docs/sessions/)
- Sessions path (default:
If no config exists:
- Use default path listed above
- Continue with skill execution
Step 1: Identify Topic
Parse user request to extract topic:
- Extract topic name from user query
- Example: "list sessions for user-authentication" -> topic:
user-authentication - Example: "what did we do on the API?" -> topic:
api(fuzzy search)
If ambiguous or not specified, ask user:
Which topic would you like to see sessions for?Step 2: Find Session Files
Use Glob to find all session files:
Glob: [sessions-path]/[topic-name]/*.mdFor fuzzy search (user provided partial topic):
Glob: [sessions-path]/*[partial-topic]*/*.mdIf no sessions found:
- Inform user: "No sessions found for [topic]"
- Suggest: "Check if topic exists? Typo in name?"
- Offer to list all available topics
Step 3: Read Session Metadata
For each session file found, extract key information:
Read first ~30 lines of each session file to get:
- Title: From first heading (# Title)
- Date: From
**Date**: YYYY-MM-DDline - Status: From
**Status**: Complete|In Progressline - Goal: From
## Session Goalssection (first line)
Store this information for formatting.
Step 4: Sort Sessions
Sort sessions chronologically:
- Sort by date (filename prefix or Date field)
- Default: Oldest first (shows progression)
Step 5: Format and Display
Create formatted list:
Sessions for '[Topic Name]':
2026-01-08: Initial setup
Goal: Set up project structure and dependencies
Status: Complete
File: [sessions-path]/topic-name/2026-01-08-initial-setup.md
2026-01-09: Core implementation
Goal: Implement core functionality
Status: Complete
File: [sessions-path]/topic-name/2026-01-09-core-implementation.md
2026-01-11: Testing and fixes
Goal: Add tests and fix issues
Status: In Progress
File: [sessions-path]/topic-name/2026-01-11-testing.md
Total: 3 sessions
Completed: 2 sessions
In Progress: 1 sessionStatus indicators:
- Complete = finished session
- In Progress = active session
- Unknown = couldn't parse status
Step 6: Provide Summary Statistics
Calculate and display:
- Total sessions: Count of all sessions
- Completed sessions: Sessions marked complete
- In-progress sessions: Sessions marked in-progress
- Date range: First session date -> Last session date
Example:
Summary:
- Total sessions: 3
- Completed: 2 (67%)
- In Progress: 1
- Date range: 2026-01-08 to 2026-01-11Step 7: Suggest Follow-up Actions
Based on the session list, suggest relevant actions:
If all sessions complete:
All sessions for this topic are complete!
Consider:
- Creating a summary document
- Marking work stream as complete
- Archiving this workIf sessions in-progress:
Found 1 in-progress session:
- 2026-01-11: Testing and fixes
Consider:
- Resuming work on in-progress session
- Completing session before starting new oneIf many sessions (8+):
This topic has 12 sessions (substantial work!).
Consider:
- Creating a summary of accomplishments
- Reviewing learnings for documentation
- Extracting patterns for future workExamples
Example 1: List Topic Sessions
User: "list sessions for user-authentication"
Skill Actions:
- Identifies topic:
user-authentication - Globs:
[sessions-path]/user-authentication/*.md - Finds 3 sessions
- Reads metadata from each
- Formats output:
Sessions for 'User Authentication': 2026-01-08: Initial setup Goal: Set up auth middleware structure Status: Complete 2026-01-09: JWT implementation Goal: Add JWT token validation Status: Complete 2026-01-11: Testing Goal: Add comprehensive tests Status: In Progress Summary: - Total: 3 sessions - Completed: 2 (67%) - In Progress: 1
Example 2: Find In-Progress Sessions
User: "what sessions are in progress?"
Skill Actions:
- User didn't specify topic - search all sessions
- Globs:
[sessions-path]/*/*.md - Reads all session files, filters for "Status: In Progress"
- Formats output:
In-Progress Sessions: user-authentication: Testing Date: 2026-01-11 Goal: Add comprehensive tests File: [sessions-path]/user-authentication/2026-01-11-testing.md api-refactor: Endpoint cleanup Date: 2026-01-10 Goal: Clean up deprecated endpoints File: [sessions-path]/api-refactor/2026-01-10-endpoint-cleanup.md Total: 2 in-progress sessions
Example 3: Fuzzy Topic Search
User: "list sessions for auth"
Skill Actions:
- Identifies partial topic:
auth - Globs:
[sessions-path]/*auth*/*.md - Finds multiple matches:
user-authentication/(3 sessions)oauth-integration/(2 sessions)
- Asks user:
Found multiple topics matching 'auth': - user-authentication (3 sessions) - oauth-integration (2 sessions) Which one would you like to see?
Example 4: Empty Results
User: "list sessions for database-migration"
Skill Actions:
- Identifies topic:
database-migration - Globs:
[sessions-path]/database-migration/*.md - No files found
- Informs user:
No sessions found for 'database-migration' Possible reasons: - Topic hasn't started yet - Typo in name - Work hasn't been documented Available topics: - user-authentication - api-refactor - oauth-integration
Error Handling
If topic not found:
- List available topics
- Suggest similar names (fuzzy matching)
- Ask if user wants to create new topic
If no sessions exist for topic:
- Check if work stream document exists (but no sessions yet)
- Inform: "Topic exists but no sessions started yet"
- Suggest: "Use /session-start to begin first session?"
If session files are malformed:
- Skip sessions with parsing errors
- Note: "Skipped N sessions with formatting issues"
- Continue processing valid sessions
If user provides no topic:
- Ask: "Which topic would you like to see sessions for?"
- Offer to list all available topics
Quality Checks
Before displaying results:
- At least try to find sessions
- Metadata extracted successfully (where possible)
- Sessions sorted chronologically
- Status indicators correct
- Summary statistics calculated
Notes
- Works with date-based filenames:
YYYY-MM-DD-title.md - Supports fuzzy search (partial topic names)
- Fast operation (just file listing + light parsing)
- Useful for quick status checks
- Can be called repeatedly without side effects
- Output can feed into summary for deeper analysis
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

