agentleFS
RidhuanDEVRidhuanDEV/claude-skills/handoff/SKILL.md

handoff

Skill1 starsChanged yesterdayMITView on GitHub

Save, load, or merge AI coding session context (\"handoff\", \"lanjut handoff\", \"load handoff\") via shadow_handoff MCP. Use when context memory is full or switching/merging agent sessions. Do NOT use for client BAST project delivery (/shadow-handover).

191 other projects use a version of this.

Adopted by

Most recently taken up by

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.
  • FabienDehopreSkill

    decision-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

  • liufeng1976Skill

    setup-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

  • AWSSkill

    to-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

  • GoogleSkill

    ask-matt

    Ask which skill or flow fits your situation. A router over the skills in this repo.

    Also in 87 projects that use this

  • RoentekSkill

    loop-me

    Grill me about specs for the workflows I want to build, within this workspace.

    Also in 51 projects that use this

  • LesaniSkill

    writing-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

The file

We split this skill into the rules it gives an agent

4 rules. 0 are common, 0 are distinctive, and 4 are very specific to this project.

  • 0

    Common

    Most of the 172 edited versions we read keep these.

  • 0

    Distinctive

    This author's own choices. Worth a look.

  • 4

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    Use this skill whenever the Monarch invokes /handoff (or says "handoff" / "lanjut handoff" / "gabung handoff").

    line 8
  2. Very specific:

    If the result contains unmergedSessions, the snapshot shows only one parallel session.

    line 33
  3. Very specific:

    Call list_handoffs with projectPath to see saved sessions, then merge_handoffs with sessionLabels in execution order (e.g.

    line 38
  4. Very specific:

    Call list_handoffs on the shadow_handoff MCP server and display the saved snapshots and any unmerged sessions.

    line 44

“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.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

/handoff — Cross-Agent Session Handoff (Shadow Army)

Use this skill whenever the Monarch invokes /handoff (or says "handoff" / "lanjut handoff" / "gabung handoff"). This skill connects directly to the shadow_handoff MCP server (save_handoff, load_handoff, list_handoffs, merge_handoffs).

How to Execute

  1. Default (/handoff with no arguments, or /handoff save) — Save & Compact Current Session:
    • Immediately call the save_handoff tool on the shadow_handoff MCP server (d:/Ridhuan Ngoding Moment/SKILL/mcp-servers/shadow-handoff-mcp/index.mjs if MCP is not yet reloaded in the current window) with:
      • projectPath: the active workspace directory path
      • sourceAgent: current agent name (Antigravity, Claude Code, Codex, or Gemini CLI)
      • title: short milestone title
      • currentGoal: the Monarch's active objective
      • completedWork: concise bullet list of verified completed tasks
      • nextSteps: ordered, actionable next steps for the next session
      • keyDecisionsAndContracts: verified contracts, strict types, and architectural decisions
      • blockersOrBugs: any open bugs or blockers
      • importantFiles: key file paths to inspect first
      • readinessLevel (required): PLANNED (plan only) | IMPLEMENTED | VERIFIED-LOCAL | REVIEWED | READY-TO-MERGE, per the Rigor Protocol in shadow-monarch. Pick the level the evidence supports, not the one hoped for.
      • untestedSurfaces (required): surfaces not yet tested (e.g. "real multi-turn conversation", "topic switch", "ALL-CAPS input", "UI during streaming"). Send [] only if every surface was actually tested.
      • claimEvidenceMap: for each readiness claim, { claim, evidence, notMeasured }.
      • sessionLabel: set when another session works on the same project in parallel (e.g. plan, review), so neither overwrites the other.
    • Report the saved handoff ID, readiness level, and file path concisely to the Monarch. If the result contains mergeHint, tell the Monarch that parallel sessions exist and offer /handoff merge.
  2. Resume (/handoff load, /handoff lanjut, or "lanjut handoff") — Load Latest Handoff:
    • Immediately call the load_handoff tool on the shadow_handoff MCP server for the current projectPath (or globally if no project is open).
    • Read untestedSurfaces and readinessLevel before writing any review conclusion or readiness claim. Treat listed surfaces as unverified; do not upgrade the readiness level without new evidence.
    • If the result contains unmergedSessions, the snapshot shows only one parallel session. Tell the Monarch and offer /handoff merge before continuing.
    • Present a brief 3-bullet summary of the loaded state to the Monarch and immediately proceed with Step 1 of nextSteps.
  3. Merge (/handoff merge or "gabung handoff") — Combine Parallel Sessions Into One Agent:
    • Typical case: session A saved with sessionLabel: "plan", session B with sessionLabel: "review"; the Monarch wants one agent to continue.
    • Call list_handoffs with projectPath to see saved sessions, then merge_handoffs with sessionLabels in execution order (e.g. ["plan", "review"]).
    • The merge keeps the lowest readiness level, unions untested surfaces, tags every item with its source session, and moves merged sessions to sessions/archive/ (nothing is deleted).
    • Decisions from different sessions are listed side by side, not reconciled. Report every entry in warnings (different branches/commits, sessions >24h apart, possible contradictions) to the Monarch before acting on the merged steps.
    • Then proceed as in Resume.
  4. History (/handoff list):
    • Call list_handoffs on the shadow_handoff MCP server and display the saved snapshots and any unmerged sessions.

Download now (ZIP)

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
What did you use it for? e.g. Reviewing pull requests in a Rails app

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.