Write a structured handoff document before a session ends, before a context-heavy interruption (SSH/tmux disconnect, context running low, a worktree being handed to another worker or agent), or when explicitly asked for a handoff — captures progress, what worked/failed, and the exact next step so a fresh session can resume without re-deriving context. Own version of the dx plugin's `/dx:handoff`.
Collected from public GitHub. Every version is saved exactly as it was and never changes. Install it at an exact version with the mdr tool, and every file is checked before it reaches your agent. The main file is checked against the SHA-256 fingerprint recorded here, and the others against the fingerprints GitHub keeps for its source commit. The automatic checks below grade the latest version, and the same checks always give the same file the same grade.
What the file says
# Handoff
A handoff doc exists to save the *next* reader (a fresh session, a different
agent, or you tomorrow) from re-deriving everything this session already
figured out. Write for someone with zero memory of this conversation, not a
recap for someone who was watching.
## What to include
- **Goal.** One sentence: what this session was actually trying to accomplish.
- **Done — verifiably.** What's complete, stated as a fact a reader can check
(a commit hash, a passing test name, a file path with the final content) —
not "implemented X" without a way to confirm it.
- **In-flight / blocked.** What's partially done, and specifically *why* it
stopped — a failing test with its actual output, a decision waiting on the
user, an external dependency not yet available. "Ran out of time" without a
concrete blocker is not useful to the next reader.
- **Explicitly not done.** Anything the goal implies but this session didn't
touch — cheap to state, expensive for the next reader to discover by
assuming it's covered.
- **Next concrete step.** Not "continue the work" — the literal next action:
which file, which command, which decision needs making first.
…
The line at the top of this page pins the label git:20260725.3f0d943, which is what most people want. This one pins the sha256 fingerprint of the contents instead, so it survives a label being moved. Either way the exact version is written to mdr.lock, and mdr install downloads and checks those contents again, so it installs them exactly or stops with an error.
GET https://markdownregistry.com/api/v1/artifacts/art_2bxosvlsomd55fin
GET https://markdownregistry.com/api/v1/resolve?ref=patrickserrano/lacquer/handoff
GET https://markdownregistry.com/api/v1/blob/16999213ce722460d9a539dbfc043ba4de972e02280bf9517a1553d79e5ebb5d
Your AI assistant does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.
patrickserrano/lacquer · core/skills/advisor-checkpoint/SKILL.md · Consult a stronger model mid-task for a second opinion before committing to an approach, when stuck, or before…
patrickserrano/lacquer · core/skills/antigravity-rescue/SKILL.md · Use when stuck, wanting a second implementation or diagnosis pass, or handing a substantial task to Google's…
patrickserrano/lacquer · core/skills/caveman/SKILL.md · Use when the user says "caveman mode", "talk like caveman", "use caveman", "less tokens", or "be brief", invokes…
patrickserrano/lacquer · core/skills/claude-rescue/SKILL.md · Use when running under Codex CLI and stuck, wanting a second implementation or diagnosis pass, or handing a substantial…
patrickserrano/lacquer · core/skills/claudemd-review/SKILL.md · Use right after being corrected on something a CLAUDE.md file should already have told you, when explicitly asked to…
patrickserrano/lacquer · core/skills/engineering-workflow/SKILL.md · Implement a feature, review a change, delegate work, or resume a session in a Lacquer-managed project.
patrickserrano/lacquer · core/skills/evaluator-optimizer/SKILL.md · Generate a solution, evaluate it against explicit pass/fail criteria, refine using the feedback, repeat until it passes…
patrickserrano/lacquer · core/skills/exploring-an-idea/SKILL.md · Use at the very start of a new product idea — before a PRD, PCD, repo, or name exists, and any time someone says "I…
patrickserrano/lacquer · core/skills/github-ci-fix/SKILL.md · Fix failing PR checks, debug GitHub Actions, or account for CI follow-up rounds and wait for verification.
patrickserrano/lacquer · core/skills/github-issue-fix-flow/SKILL.md · Use when asked to take a GitHub issue number, implement a fix, run builds/tests, commit with a closing message, and…
patrickserrano/lacquer · core/skills/manager-loop/SKILL.md · Run a large batch of independent work items (a fleet-wide harvest, a multi-repo sync-down, an overnight backlog) as a…
thedotmack/claude-mem · plugin/skills/handoff/SKILL.md · Generate a HANDOFF.md that captures goal, current state, files touched, failed attempts, and next steps — so a fresh…
jeremylongshore/tons-of-skills-marketplace · plugins/ai-agency/hyperflow/skills/handoff/SKILL.md · Use when managing a two-session handoff — inspecting, picking up, or reviewing a committed handoff package produced by…
openonion/connectonion · connectonion/useful_skills/handoff/SKILL.md · Hand the work discussed in this session (every message the user wrote, your replies quoted, where the code is) to…
suboss87/fdeops · skills/handoff/SKILL.md · Transfer operation of a customer deployment with ownership, evidence and a tested support path. Use for handoff or an…
sno-ai/sno-station-skills · skills/S-communication-and-handoff/handoff/skill/SKILL.md · Transfer full task ownership to a fresh agent with a verified brief and explicit release. Use for replacing the current…
