agentleFS
Sign inStart free
mhlagharimhlaghari/stuntman/skills/handoff/SKILL.md

handoff

Skill16 starsChanged 2 months agoMITView on GitHub

Resume a Stuntman project from HANDOFF.md, STATUS.md, and the host's AGENTS.md or CLAUDE.md memory contract. Read back the current state and continue the documented next step. Use when asked to execute a handoff or resume from project memory.

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, 1 is distinctive, and 3 are very specific to this project.

  • 0

    Common

    Most of the 172 edited versions we read keep these.

  • 1

    Distinctive

    This author's own choices. Worth a look.

  • 3

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Read host setup. Follow AGENTS.md in Codex and CLAUDE.md in Claude Code, including any additional read-first documents listed there.

    line 14
  2. Very specific:

    Read what the next step needs, not the whole repo.

    line 25
  3. Very specific:

    If HANDOFF.md / STATUS.md don't exist, the project isn't scaffolded yet — tell the user to run /scaffold first, and stop.

    line 28
  4. Very specific:

    Check vault freshness: If $STUNTMAN_VAULT (default ~/Documents/Documents/MyProjects/laghari-vault) contains wiki/projects/<project …

    line 31

“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

stuntman: handoff — resume from the project's memory

/scaffold sets up the project-memory docs; /handoff is how you resume from them. It reads the project's running state, orients, and continues — so a brand- new session (or one after /clear) picks up with zero re-explaining.

What to do

Read host setup. Follow AGENTS.md in Codex and CLAUDE.md in Claude Code, including any additional read-first documents listed there.

  1. Read the memory docs, in order:

    • HANDOFF.md — the session baton: what the last session changed, the next step, gotchas. The primary "where we are."
    • STATUS.md — the board: built / in progress / planned.
    • SPEC.md — the contract: what this is and where it's going. Build to it.
    • STRATEGY.md — the honest why / direction. Read before any big call.
    • README.md — what the project is and how to run it.

    Read what the next step needs, not the whole repo. (A lightly-scaffolded project may not have SPEC.md / STRATEGY.md — skip what's absent.)

    If HANDOFF.md / STATUS.md don't exist, the project isn't scaffolded yet — tell the user to run /scaffold first, and stop.

  2. Check vault freshness. If $STUNTMAN_VAULT (default ~/Documents/Documents/MyProjects/laghari-vault) contains wiki/projects/<project dirname>.md, compare its updated: frontmatter to git log -1 --format=%cs. If it is more than 7 days behind, mention that in the read-back. If a vault-maintenance skill is available, suggest it; otherwise offer to refresh the page directly. /vault is not bundled.
  3. Orient and confirm. Give a short read-back: where the project stands and the next step you picked up from HANDOFF.md. Surface anything stale or contradictory between the docs and the actual code/tree.
  4. Continue the work from that next step — unless the user redirects you.
  5. Before you stop, honor the host's memory contract: update HANDOFF.md (what changed, next step, gotchas), STATUS.md (refresh the board), and README.md (if the project's surface changed) — written for a reader with zero memory of this session. Never commit without explicit authorization.

Notes

  • This is the runtime half of the pair: /scaffold writes the system, /handoff runs it. The read-first / update-before-stopping instructions also live in the host's instruction file (which auto-loads), so the loop holds even if a session never explicitly runs /handoff — this command just makes the resume deliberate.
  • Trust the working tree over the docs when they disagree — then fix the docs.

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.

Check your setup, free