resume-session
Skill1 starsChanged 7 months agoMITView on GitHub
Resume from the last session -- restores context, progress, and next actions with zero wasted time.
9 other projects use a version of this.
Adopted by
Most recently taken up by
- Yesterday-AI/ytstacktheir own version, first seen Oct 13, 2026
- isac7722/skillstheir own version, first seen Oct 13, 2026
- kody-w/rappterbooktheir own version, first seen Oct 8, 2026
- ingpoc/SKILLStheir own version, first seen Aug 10, 2026
- Q00/ouroborostheir own version, first seen Jul 31, 2026
- amkfbant/claude-codex-orchestrationtheir own version, first seen May 15, 2026
Other versions9 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 9
- Q00/ouroboros★ 6.3ksame name
- kody-w/rappterbook★ 18same name
- jiten-singh-shahi/salesforce-claude-code★ 15same name
- ingpoc/SKILLS★ 9same name
- Yesterday-AI/ytstack★ 2same name
- amkfbant/claude-codex-orchestration★ 1same name
- isac7722/skills★ 1same name
- TheKREATORS/my-claude-skills★ 1same name
- ojagao/ClaudeCode_SKILLS★ 0same 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 repository3 other files it gives its agents.
- morning-briefingSkill
- save-sessionSkill
- statusSkill
The file
We split this skill into the rules it gives an agent
5 rules. 0 are common, 3 are distinctive, and 2 are very specific to this project.
0
Common
Most of the 8 edited versions we read keep these.
3
Distinctive
This author's own choices. Worth a look.
2
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 30
Read the most recent .md file
- Distinctive: line 32
If no session files exist, output:
- Very specific: line 40
Read .max/state/CURRENT.md if it exists -- this provides broader system context beyond the last session.
- Distinctive: line 72
After delivering the briefing, ask:
- Distinctive: line 78
Do NOT auto-start work: Wait for G to confirm direction.
“Common” is measured: kept by at least 6 in 10 of the 8 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Resume Session
Pick up exactly where the last session left off. No lost context. No wasted time.
Trigger
Activate when: /resume-session, "resume session", "what were we doing", "where did we leave off", "continue", "pick up where we left off".
Purpose
Reads the most recent session snapshot and delivers a structured briefing so G knows exactly what was happening, what worked, what broke, and what to do next. This is the read half of MAX's session memory system.
Procedure
Step 1: Find the Latest Session
- List all files in
.max/sessions/(excludingREADME.md) - Sort by filename (they're timestamped, so alphabetical = chronological)
- Read the most recent
.mdfile
If no session files exist, output:
No saved sessions found. This appears to be a fresh start.
Check .max/state/CURRENT.md for system state, or tell me what you'd like to work on.Step 2: Also Read Current State
Read .max/state/CURRENT.md if it exists -- this provides broader system context beyond the last session.
Step 3: Deliver the Briefing
Output in this exact format:
## Session Resume: [date from filename]
**Last session was [X hours/days] ago.**
### Where We Left Off
[2-3 sentence summary of what was being worked on]
### What Was Built
[Bullet list from the session file]
### What Failed (Do Not Retry)
[Bullet list of failed approaches -- highlight these so we don't waste time]
### Blockers
[Any unresolved issues]
### Next Step
> [The exact next step from the session file -- make it prominent]
### Active Files
[List of file paths that were being worked on]Step 4: Wait for Confirmation
After delivering the briefing, ask:
Ready to continue from here? Or would you like to work on something else?Do NOT auto-start work. Wait for G to confirm direction.
Rules
- Never auto-execute -- this skill is read-only. It presents information and waits.
- Highlight failures prominently -- the "What Failed" section should be impossible to miss so we don't repeat mistakes.
- Be concise -- G wants to know where things stand, not read an essay. Keep the briefing under 300 words.
- If multiple sessions exist, only read the most recent one. G can ask for older ones explicitly.
- Time context matters -- always calculate and show how long ago the last session was. "3 hours ago" vs "2 days ago" changes urgency.
Integration Points
- Save Session (
/save-session) creates the files this skill reads - Morning Briefing (
/morning) also reads session files but adds mentor voice and system status - SessionStart hook automatically triggers a lightweight version of this on every new session
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.