session-handoff
Skill0 starsChanged 36 days agoMITView on GitHub
Preserve verified progress so a new session can resume with no memory of this one. Use when asked to write a handoff, log progress, leave pickup notes, or resume a previous task. Records completed work, the exact next action, decisions, blockers and the files to read first.
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 repository9 other files it gives its agents.
- AGENTS.mdAGENTS.md
- define-doneSkill
- interrogateSkill
- jevifySkill
- loop-builderSkill
- opascopeSkill
- openrouterSkill
- optimizeSkill
- planningSkill
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 117 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 13
Read shared.md first. Publish with kind handoff.
- Distinctive: line 28
Write a compact handoff using references/handoff.md.
- Distinctive: line 34
Check that existing pointers resolve.
- Very specific: line 41
Run kit.py resume to list task identities.
- Distinctive: line 48
Do not restart completed work, reopen settled choices without new evidence, or claim automatic startup pickup.
“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
Hand off context between Claude Code or Codex sessions
Read shared.md first. Publish with kind handoff. This single
artifact is the pickup contract; no runtime-specific state capture is needed.
Write a handoff
- Establish the task ID from the conversation or
kit.py resume. Read its previous handoff and artifacts. Cross-check conversation claims against the current files, command results, and git status/diff when this is a git project. In a non-git folder, inspect the relevant files and their actual contents. A directory listing proves existence, not unchanged content. Use content or hash comparison for preservation claims; state when no baseline is available. - Distinguish verified work, unverified recollections and unrelated existing changes. Never claim every dirty file belongs to this session. If compaction erased the rationale, say which facts were recovered from disk and what the next session must verify.
- Write a compact handoff using references/handoff.md. Its core is the exact next action, including the current partial state. Record completed output with proof, in-flight work, files touched, locked decisions, open questions and each blocker's explicit unblock condition.
- Supply a short read-first list sufficient for a cold reader. Use project-root relative paths and identify the root; use absolute paths for external files. Check that existing pointers resolve. Mark planned files as future outputs.
- Publish through
kit.py save TASK_ID handoff, which creates a unique file and preserves prior handoffs. Read it back and runkit.py resume TASK_IDto prove the pickup command returns this handoff. Report its path and the next action.
Resume a task
Run kit.py resume to list task identities. Use the task the user named; ask
only if multiple matches make the intended task ambiguous. Run
kit.py resume TASK_ID, read the read-first artifacts, then verify the
checkpoint against current disk state. A handoff is evidence to check, not
permission to execute every listed idea. State what is complete, what is next
and what remains blocked. Continue the originally authorized task when asked.
Do not restart completed work, reopen settled choices without new evidence, or claim automatic startup pickup. A new session must invoke the router/handoff skill or be told to read the returned handoff path.
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.

