session-handoff
Skill8 starsChanged 6 months agoMITView on GitHub
Cold-start advisory: surfaces commits on remote-tracking refs that landed in the last 24 hours and are NOT yet on any local branch. Catches the incident-2026-1507 pattern where a sibling machine pushed work between sessions and the next session edited blind. Read-only; never blocks.
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 repository129 other files it gives its agents.
- AGENTS.mdAGENTS.md
- guidance/AGENTS.mdAGENTS.md
- CLAUDE.mdCLAUDE.md
- guidance/CLAUDE.mdCLAUDE.md
- .github/copilot-instructions.mdCopilot instructions
- blast-radius-checkSkill
- brainstormingSkill
- branch-flow-gateSkill
- branch-sync-gateSkill
- codebase-reconSkill
- codeowners-drift-auditSkill
- code-review-batterySkill
- cognitive-complexity-refactoringSkill
- debateSkill
- debug-conductorSkill
- dispatching-parallel-agentsSkill
- domain-buildSkill
- evidence-adjudicatorSkill
- executing-plansSkill
- external-cli-auditSkill
- feature-developmentSkill
- field-rename-verificationSkill
- finishing-a-development-branchSkill
- git-branch-conventionsSkill
- gitlab-cliSkill
- hotfix-charterSkill
- implementation-trackerSkill
- incident-revert-reviewSkill
- infra-config-investigatorSkill
- investigation-stateSkill
- kernel-splitSkill
- llm-behavior-investigatorSkill
- llm-skill-reviewSkill
- merge-authorization-gateSkill
- micro-harsh-reviewSkill
- output-verificationSkill
- pre-commit-gateSkill
- progressive-code-review-gateSkill
- progressive-harsh-reviewSkill
- providing-code-reviewSkill
- pr-triage-gateSkill
- push-authorization-gateSkill
- receiving-code-reviewSkill
- reproduction-experiment-investigatorSkill
- requesting-code-reviewSkill
- requirements-validation-pmSkill
- requirements-validationSkill
- scope-tripwireSkill
- skills-hierarchy-tuningSkill
- sp-bughuntSkill
- state-consistency-investigatorSkill
- subagent-driven-developmentSkill
- systematic-debuggingSkill
- test-driven-developmentSkill
- timeline-trace-investigatorSkill
- token-estimationSkill
- unified-commit-gateSkill
- using-git-worktreesSkill
- using-superpowersSkill
- verification-before-completionSkill
- The first 60 shown.
The file
Files
Session Handoff
Wrong skill? Resuming an explicit prior context ->
branch-sync-gate(fetches + checks behind/diverged). Per-branch budget doc ->hotfix-charter. Per-commit LOC ceiling ->pre-push-loc-gate. Cumulative branch vs ticket estimate ->scope-tripwire.
A first-touch advisory that asks: what landed in this repo since I last looked? Lists commits on remote-tracking refs from the last 24 hours that are NOT yet reachable from any local branch -- the actionable handoff set. Run it BEFORE editing on a cold start.
When this fires (vs. branch-sync-gate)
| Verb / phrase | Skill | Why |
| "let me check this repo" / "starting work on..." / "what's new in..." | session-handoff | Cold start; engineer needs to see what landed |
| "continuing work on..." / "resuming where I left off..." | branch-sync-gate | Explicit resume; fetch + behind/diverged check |
/sp-session-handoff (explicit) | session-handoff | Manual invocation |
/sp-sync (explicit) | branch-sync-gate | Manual invocation |
Both should run when both verbs are present. Session-handoff runs first (order: -1), reports the sibling-activity summary, then branch-sync-gate handles the fetch + alignment workflow.
Quick start
# Manually, from the repo root
tools/session-handoff-check.sh
# With assurance line when no activity found
tools/session-handoff-check.sh --verbose
# Wider window (default: "24 hours ago")
SESSION_HANDOFF_WINDOW="7 days ago" tools/session-handoff-check.sh
# Skip the git fetch (offline or hostile network)
SESSION_HANDOFF_NO_FETCH=1 tools/session-handoff-check.shWhat it shows
Output (stderr; nothing on stdout):
session-handoff: sibling activity detected (window: 24 hours ago)
(Read these commits before editing -- they may overlap your planned work.)
origin/fix/incident-2026-1507-intro-protection
2026-06-09T14:32 user@example.com fix: greeting registration race
2026-06-09T15:14 user@example.com test: add ceiling-hit case
origin/main
2026-06-10T11:22 user@example.com Merge commit message
Tip: `git log <ref> --since="24 hours ago"` for full detail.Silent when no commits match (unless --verbose).
Configuration
| Env var | Default | Purpose |
SESSION_HANDOFF_WINDOW | 24 hours ago | Any git log --since= expression |
SESSION_HANDOFF_VERBOSE | 0 | 1: print assurance line when no activity |
SESSION_HANDOFF_NO_FETCH | 0 | 1: skip git fetch (uses stale local refs) |
SESSION_HANDOFF_FETCH_TIMEOUT | 10 | Wall-clock budget for fetch (seconds) |
Exit codes
| Exit | Meaning |
| 0 | Activity surfaced; OR no activity; OR fetch failed (advisory only -- never blocks) |
| 2 | Not in a git repo, OR invalid env var, OR git log error |
Composition with peer skills
session-handoff is the COLD-START half of the session-orientation pair:
+-- session-start group --------------------+
| |
| [order: -1] session-handoff | <-- "what landed since I left?"
| | |
| v produces: sibling-activity |
| |
| [order: 0] branch-sync-gate | <-- "now fetch + reconcile"
| |
+--------------------------------------------+Both skills running back-to-back is intended ergonomics. The incident-2026-1507 pattern would have been caught by this skill firing on cold-start verbs.
Why this exists
The 2026-06-10 incident-2026-1507 involved two machines doing parallel work on the same hotfix branch. Branch-sync-gate did not fire because the engineer never said "continuing" or "resuming" -- it was a cold start with edit verbs ("let me look at..."). The sibling commits sat invisible on the feature branch while the engineer started a second parallel implementation. Hours of fork-merge confusion followed.
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.

