session-handoff
Skill3 starsChanged 7 months agoMITView on GitHub
Create structured session notes for continuity across conversations. Produces fixed-template notes with immutable section headers, session titles, and token-budgeted content. Use when saving session state, creating handoff notes, preparing for context compaction, or when asked to summarize work for continuity.
139 other projects use a version of this.
Adopted by
Most recently taken up by
- aktsmm/Agent-Skillstheir own version, first seen Nov 8, 2026
- wanshuiyin/HERO-Anti-OverDefensetheir own version, first seen Nov 8, 2026
- alapha888/session-handoff-kittheir own version, first seen Nov 8, 2026
- zedarvates/frugal-skillstheir own version, first seen Nov 8, 2026
- Sirius-Ji/dsh-disciplinary-skills-for-greenhandstheir own version, first seen Nov 8, 2026
- maideps/ai-harness-frameworktheir own version, first seen Nov 8, 2026
Used with
Projects with it also use ascii-diagram, research-fleet and 10 more.
Other files people use alongside this one.
Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
SethGammonSkillascii-diagram
Generate perfectly aligned ASCII diagrams — architecture, flow, sequence, box-and-arrow. Uses a programmatic character-grid approach so alignment is guaranteed by math, not token prediction. Includes post-render verification.
Also in 4 projects that use this
SethGammonSkillresearch-fleet
Parallel research using Fleet wave mechanics. Spawns multiple scout agents, each investigating a different angle of the same question. Findings are compressed between waves. Produces a unified research brief from multiple independent perspectives.
Also in 3 projects that use this
vicoa-aiSkilllive-preview
Start a local app in the current user project, expose it through a tunnel, and return preview details in structured Markdown. Use when the user asks for a preview URL, public URL, shareable localhost, mobile/web preview, or tunnel setup.
Also in 4 projects that use this
botlearn-aiSkilldoc-gen
Also in 4 projects that use this
flyingobsidianSkillterminology
Read a codebase, find terminology, create/update definitions into a markdown document.
Also in 3 projects that use this
Dizzy-TenSkillbug-diagnosis
Diagnose bugs and product issues without modifying code. Use when the user explicitly invokes $bug-diagnosis or asks for diagnosis, root-cause analysis, issue classification, or fix strategy for code bugs, failing tests, configuration/dependency problems, deployment issues, performance regressions, data anomalies, or frontend/user-experience problems described through screenshots, annotations, logs, errors, or natural-language reports. Prioritize analysis and recommendations only; do not edit files.
Also in 3 projects that use this
- +1 more from SethGammon
Other versions139 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 139
- rohitg00/pro-workflow★ 2.9ksame name
- SethGammon/Citadel★ 927same name
- wanshuiyin/HERO-Anti-OverDefense★ 805same name
- OneWave-AI/claude-skills★ 378same name
- ai-analyst-lab/ai-analyst★ 304same name
- entireio/skills★ 239same name
- Innei/SKILL★ 92same name
- yuzushi-dev/session-handoff★ 67same name
- Hive-Academy/ptah-extension★ 34same name
- Hive-Academy/PtahCode★ 34same name
129 more not listed
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 repository14 other files it gives its agents.
- architectural-planningSkill
- browser-testingSkill
- codebase-explorationSkill
- code-reviewSkill
- code-verificationSkill
- context-summarizationSkill
- disciplined-codingSkill
- effective-tool-useSkill
- knowledge-managementSkill
- prompt-engineeringSkill
- safe-autonomous-modeSkill
- security-reviewSkill
- systematic-debuggingSkill
- task-orchestrationSkill
The file
We split this skill into the rules it gives an agent
10 rules. 0 are common, 9 are distinctive, and 1 is very specific to this project.
0
Common
Most of the 117 edited versions we read keep these.
9
Distinctive
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
- Distinctive: line 51
Write DETAILED, INFO-DENSE content.
- Distinctive: line 54
Don't include information already in CLAUDE.md files — session notes capture session-specific knowledge, not project documentation.
- Distinctive: line 56
Always update "Current State" to reflect the most recent work — this is critical for continuity after compaction.
- Distinctive: line 60
Keep each section under ~2000 tokens.
- Distinctive: line 62
When condensing, prioritize keeping "Current State" and "Errors & Corrections" accurate and detailed.
- Distinctive: line 63
Use terse, information-dense writing.
- Distinctive: line 67
When updating session notes:
- Distinctive: line 69
Update every section that has new information — make all edits in parallel.
- Distinctive: line 72
Don't reference the note-taking process itself in the notes content.
- Very specific: line 84
If user-config.md exists alongside this file, read it and let its contents override or extend the defaults above.
“Common” is measured: kept by at least 6 in 10 of the 117 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
Session Handoff
CRITICAL: Preserve the template structure exactly. Never modify, delete, or add section headers. Never modify the italic section descriptions. Only update the content below each section's description line.
Session Title Rules
Generate a concise, sentence-case title (3-7 words) that captures the main topic or goal.
Good titles:
- "Fix login button on mobile"
- "Add OAuth authentication"
- "Debug failing CI tests"
- "Refactor API client error handling"
Bad titles:
- "Code changes" — too vague, doesn't identify the session
- "Investigate and fix the issue where the login button does not respond on mobile devices" — too long
- "Fix Login Button On Mobile" — wrong case (use sentence case, not Title Case)
Session Notes Template
The notes file uses a fixed template. Each section has two parts that must be preserved exactly:
- The section header (line starting with
#) - The italic description line (the
_italicized text_immediately after the header)
You ONLY update the content that comes AFTER these two preserved lines.
Required Sections
| Section | What to Write |
| Session Title | 5-10 word descriptive title, info-dense, no filler |
| Current State | What's being worked on RIGHT NOW. Pending tasks. Immediate next steps. This is the most critical section for continuity. |
| Task specification | What the user asked to build. Design decisions and explanatory context. |
| Files and Functions | Important files, what they contain, why they're relevant. |
| Workflow | Bash commands usually run and in what order. How to interpret output if not obvious. |
| Errors & Corrections | Errors encountered, how fixed. What the user corrected. What approaches failed. |
| Codebase and System Documentation | Important system components. How they work/fit together. |
| Learnings | What worked, what didn't, what to avoid. Don't duplicate items from other sections. |
| Key results | If the user asked for specific output (answer, table, document), repeat the exact result. |
| Worklog | Step-by-step, what was attempted and done. Very terse summary per step. |
Content Rules
- Write DETAILED, INFO-DENSE content. Include specifics: file paths, function names, error messages, exact commands, technical details.
- For "Files and Functions," prefer structural outlines (file purpose, key exports, function signatures) over copying large code blocks. This maximizes context recovery per token within the 2000-token budget.
- For "Key results," include the complete, exact output the user requested.
- Don't include information already in CLAUDE.md files — session notes capture session-specific knowledge, not project documentation.
- Skip sections with no substantial new insights. Don't add filler content like "No info yet" — leave blank sections unedited.
- Always update "Current State" to reflect the most recent work — this is critical for continuity after compaction.
Token Budget
- Keep each section under ~2000 tokens. If a section approaches this limit, condense by cycling out less important details while preserving the most critical information.
- Total session notes should stay under ~12000 tokens.
- When condensing, prioritize keeping "Current State" and "Errors & Corrections" accurate and detailed.
- Use terse, information-dense writing. Every line should carry information that would be lost without these notes.
Update Process
When updating session notes:
- Review what's new since the last update.
- Update every section that has new information — make all edits in parallel.
- Preserve all headers and italic descriptions exactly as they are.
- Focus on actionable, specific information that helps someone continue the work.
- Don't reference the note-taking process itself in the notes content.
CRITICAL REMINDER: Never modify section headers or italic descriptions. Always update "Current State." Stay under 2000 tokens per section. Info-dense, no filler.
Related Skills
context-summarizationprovides the structured analysis that feeds into session notes.knowledge-managementclassifies what should become durable memory vs. session-specific notes.- Session notes draw on
codebase-explorationfindings for the Files and Functions section.
Project Customization
If user-config.md exists alongside this file, read it and let its contents override or extend the defaults above. Common customizations:
- Custom session note template with additional sections
- Modified token budgets per section
- Team-specific handoff requirements
- Custom title format or naming conventions
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.

