the-agency-ai/the-agency/handoff

Claude Code and agent skill by the-agency-ai/the-agency

Trust tier 3
  • community
Source check pending

Checking that the SKILL.md file is still in the repository.

Write a session handoff using the handoff tool — archive, write, verify

Install

npx vskill@latest install the-agency-ai/the-agency/handoff

SKILL.md

Session Handoff

Write a handoff file for session continuity. Always use the handoff tool — never write handoff files manually.

Arguments

  • $ARGUMENTS: Optional trigger name (e.g., pre-restart, phase-complete, discussion-milestone). Defaults to manual.

Instructions

Step 1: Archive and signal

Run the handoff tool to archive the current handoff and prepare for a new one:

bash ./agency/tools/handoff write --trigger $ARGUMENTS

If $ARGUMENTS is empty, use --trigger manual.

Step 2: Write the handoff

Write the handoff file at the path the tool reported. Include:

  1. Date and context — date, branch, session/agent name
  2. What was done — completed work this session, key changes
  3. What's next — immediate next steps for a fresh session
  4. Key decisions — anything a new session needs to know
  5. Open items/blockers — unresolved issues, pending discussions
  6. Discussion queue — carried-forward discussion items

Integrity rule: before writing, check git status. If any implementation files (.ts, .py, .bats, .sh, agency/tools/, hooks/, etc.) are uncommitted, either commit them first OR clearly mark them as "in progress — uncommitted" in the Current State section. Never write 'complete' for uncommitted work.

The handoff tool will automatically detect uncommitted impl files and emit a WARNING that you should include verbatim in the handoff Current State section. This is the audit trail — the next session reading the handoff sees exactly what was left dirty.

Step 3: Verify

Run bash ./agency/tools/handoff read to verify the handoff was written correctly.

Security

  • Security scanPassed, 95 of 100Pattern checks on the skill's files.
  • Model reviewPassed

Quality evaluation

  • Task evaluationNot runNo evaluation yet. Run one in Skill Studio.

Source

Popularity

7-day trend score
5

Not refreshed yet.

Works with

Any agent vskill installs to: 56 targets in all. These 39 have a page on this site.

  • Claude Code
  • Cursor
  • GitHub Copilot
  • Windsurf
  • Codex
  • Gemini CLI
  • Cline
  • Amp
  • Roo Code
  • Goose
  • Continue
  • Kilo Code
  • Junie
  • Trae
  • OpenHands
  • Qwen Code
  • AI Agent
  • Tabnine Chat
  • Sourcegraph Cody
  • Amazon Q
  • Firebase Genkit
  • Sweep
  • Devin
  • Phind
  • Mentat
  • Claude Desktop
  • Aider
  • GPT Pilot
  • Plandex
  • bolt.new
  • v0
  • Replit Agent
  • Anse
  • TypingMind
  • BetterChatGPT
  • LibreChat
  • Warp AI
  • Pieces
  • Fig AI
Embed badge
vskill VERIFIED badge
[![vskill VERIFIED](https://verified-skill.com/api/v1/skills/the-agency-ai/the-agency/handoff/badge)](https://verified-skill.com/skills/the-agency-ai/the-agency/handoff)

Something wrong with this skill or its page? Tell us.