handoff
Skill2 starsChanged 4 months agoMITView on GitHub
Use when the user runs /synergy-handoff or asks Claude to capture a knowledge-transfer handoff for the active Synergy session before quitting. Snapshots the live agent's working context into .state/handoff.md so a future agent can resume exactly where it left off, even mid-phase.
- Sends data out
191 other projects use a version of this.
Adopted by
Most recently taken up by
- xiaoxiaosrm/dsh-mattpocock-skillstheir own version, first seen Nov 8, 2026
- ethosagent/ethostheir own version, first seen Nov 8, 2026
- dsifry/metaswarmtheir own version, first seen Nov 8, 2026
- glebis/claude-skillstheir own version, first seen Nov 8, 2026
- domengabrovsek/agent-configtheir own version, first seen Nov 8, 2026
- domengabrovsek/claudetheir own version, first seen Nov 8, 2026
Used with
Projects with it also use decision-mapping, setup-ts-deep-modules 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.
FabienDehopreSkilldecision-mapping
Turn a loose idea into a sequenced map of investigation tickets, then drive them to resolution one at a time.
Also in 8 projects that use this
liufeng1976Skillsetup-ts-deep-modules
Wire dependency-cruiser into a TypeScript repo so each package is a deep module — implementation hidden in subfolders, reachable only through its entry-point files. User-invoked.
Also in 42 projects that use this
AWSSkillto-questionnaire
Turn a decision you can't fully answer into a questionnaire for someone else to fill in.
Also in 93 projects that use this
GoogleSkillask-matt
Ask which skill or flow fits your situation. A router over the skills in this repo.
Also in 87 projects that use this
RoentekSkillloop-me
Grill me about specs for the workflows I want to build, within this workspace.
Also in 51 projects that use this
LesaniSkillwriting-beats
Shape an article as a journey of beats, choose-your-own-adventure style. The user picks a starting beat from the raw material, you write only that beat, then offer options for where to pivot next, beat by beat, until the article reaches a natural end. Use when the user has raw material and wants to assemble it as a narrative rather than an argument.
Also in 54 projects that use this
Other versions191 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 191
- mattpocock/skills★ 309ksame name
- QuivrHQ/quivr★ 40ksame name
- The-Vibe-Company/quivr★ 40ksame name
- GreyDGL/PentestGPT★ 16ksame name
- ykdojo/claude-code-tips★ 10ksame name
- ArcReel/ArcReel★ 6.3ksame name
- vinvcn/mattpocock-skills-zh-CN★ 5.5ksame name
- withcoral/coral★ 4.9ksame name
- epicenter-md/epicenter★ 4.8ksame name
- EpicenterHQ/epicenter★ 4.8ksame name
181 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
- CLAUDE.mdCLAUDE.md
- address-feedbackSkill
- continueSkill
- create-specSkill
- executeSkill
- preview-controlSkill
- reviewSkill
- spec-authoringSkill
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 172 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
- Distinctive: line 24
If it prints a warning, surface that line to the user verbatim before continuing.
- Distinctive: line 57
3. Write it: Prefer the daemon; fall back to the CLI.
- Very specific: line 83
Don't hand-edit .state/handoff.md — always go through the CLI/daemon.
- Distinctive: line 84
Don't omit "Next concrete step" or "Current phase state" — those are what let a fresh agent resume mid-phase instead of restarting it.
- Very specific: line 86
Don't delete the prior handoff — writeHandoff overwrites it (latest-wins).
“Common” is measured: kept by at least 6 in 10 of the 172 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
<!-- synergy-version: 0.22.0 -->Step 0 — Freshness check (run before anything else)
This skill loads at session start, so it can be stale if the plugin was updated
mid-session. Before doing any work, confirm you are the newest installed version.
Set MINE to the version in the synergy-version marker just above, then run:
MINE="0.22.0" # ← the synergy-version marker above
CACHE="${CLAUDE_PLUGINS_DIR:-$HOME/.claude/plugins}/cache/synergy/synergy"
NEWEST="$(ls "$CACHE" 2>/dev/null | sort -V | tail -1)"
if [ -n "$NEWEST" ] && [ "$NEWEST" != "$MINE" ] && \
[ "$(printf '%s\n%s\n' "$MINE" "$NEWEST" | sort -V | tail -1)" = "$NEWEST" ]; then
printf '⚠ synergy: this session loaded v%s, but v%s is installed. Restart Claude Code to load the latest skills/templates.\n' "$MINE" "$NEWEST"
fiIf it prints a warning, surface that line to the user verbatim before continuing. Then proceed — staleness is a warning, not a block.
handoff
Capture the current session's knowledge into .state/handoff.md so a future agent
resumes exactly where you stopped — even mid-phase. You (the live agent) author the
snapshot from your own context.
CLI base: node "$CLAUDE_PLUGIN_ROOT/packages/cli/dist/cli.js".
Steps
1. Resolve the session — same as synergy:execute step 1 ($ARGUMENTS first token, else
.synergy/active-session within the 10-minute window, else ask).
2. Author the handoff snapshot from your own working context. Fill every section; "none" is a valid value:
## What I did this session
## In-flight / half-done (files touched but not complete; what's missing)
## Next concrete step (the single first action the next agent should take)
## Gotchas / dead-ends (what NOT to retry, surprising constraints)
## Open questions (decisions deferred to a human)
## Current phase state (phaseId + rough %; e.g. "storage ~60%")Reference the phase by its slug (e.g. storage), never a file path like
phases/01-storage/spec.mdx — numeric prefixes are sort-order, not identity, and rot
under renumbering. Carry knowledge + slug only; the resuming agent resolves the spec path
from the slug via the fixed layout convention. Do not embed spec:/orchestrator: links.
3. Write it. Prefer the daemon; fall back to the CLI. Write the body to a temp file to avoid shell-escaping a large multi-line dump:
BODY_FILE="$(mktemp)"
cat > "$BODY_FILE" <<'EOF'
## What I did this session
…
## Current phase state
storage ~60%
EOF
# Fast path (daemon running):
# Assign PREVIEW_ORIGIN from `preview status --json`; do not assume a port.
curl -sS -X POST "${PREVIEW_ORIGIN}/api/handoff" \
-H 'content-type: application/json' \
-d "$(python3 -c 'import json,sys;print(json.dumps({"session":sys.argv[1],"next":sys.argv[2],"body":open(sys.argv[3]).read()}))' "<session>" "<nextPhaseId>" "$BODY_FILE")"
# Fallback (preview not running):
node "$CLAUDE_PLUGIN_ROOT/packages/cli/dist/cli.js" handoff <session> --next <nextPhaseId> --body-file "$BODY_FILE"4. Confirm the path (.state/handoff.md) and resume pointer back to the user. It is now
safe to quit — a future /synergy-continue or /synergy-execute will read this first.
Don'ts
- Don't hand-edit
.state/handoff.md— always go through the CLI/daemon. - Don't omit "Next concrete step" or "Current phase state" — those are what let a fresh agent resume mid-phase instead of restarting it.
- Don't delete the prior handoff —
writeHandoffoverwrites it (latest-wins).
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.

