agentsclimarketplace

Handoff receipts

Skill runsagents/handoff-receipts

Records agent handoffs as provenance records with task state, ownership, and verification evidence.

Install
npx -y skills add runsagents/handoff-receipts

Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.

2 things to look at

  • 26 days oldThe repository was created 26 days ago. New is not bad, but a brand new repository carrying a familiar-sounding name is the shape a typosquat arrives in, and there has been no time for anyone else to find a problem with it.
  • 0 stars0 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.

What its author says it does

Copied from the file, not written here

Write and validate structured receipts for agent-to-agent or agent-to-human work transfers. Use when the user says "handoff" or "hand this off", when delegating work to another agent, when ending a work session with unfinished or transferable context, or when receiving work that another agent expects you to accept.

SKILL.md

2.6 KB, 439 tokens by cl100k_base, as published. Nobody here has run it

Handoff receipts

Create evidence-bearing boundaries between work sessions and owners.

Sending work

  1. Copy templates/handoff-receipt.md into the relevant project or response workspace.
  2. Replace every example value with observed facts. Keep the receipt synthetic only when explicitly demonstrating the format.
  3. Record the complete task and scope, authorized paths or territory, decisions and reasons, unresolved risks, exact verification command and observed result, produced artifacts, receiver acceptance checklist, identities, and an RFC 3339 timestamp.
  4. Use empty arrays for decisions, unresolvedRisks, or artifacts only when there are genuinely none. Never omit the fields.
  5. Run node scripts/validate-receipt.mjs <receipt-path> from this skill directory. Correct every reported error before handoff.
  6. Send the receipt with the artifacts. Call out failed or not-run verification and unresolved risks in the handoff message.

Do not claim a command passed unless its recorded output came from that run. Do not broaden territory.allowedPaths after the work merely to make unauthorized changes look allowed.

Receiving work

Refuse acceptance when no receipt accompanies incoming work. Ask politely: “Please provide a handoff receipt with the scope, allowed territory, decisions, unresolved risks, verification evidence, artifacts, and acceptance checklist.”

When a receipt exists:

  1. Validate it with node scripts/validate-receipt.mjs <receipt-path>.
  2. Confirm sender and receiver identities and inspect every artifact against the stated scope and allowed territory.
  3. Re-run the verification command when safe and authorized. Reconcile any result that differs from the receipt.
  4. Read every decision and unresolved risk. Do not treat acceptance as resolution of a listed risk.
  5. Confirm each acceptance checklist item explicitly before accepting.
  6. Refuse acceptance politely if validation fails, evidence is missing, territory was exceeded, a checklist item cannot be confirmed, or a risk makes the next step unsafe. State the exact correction needed.

A valid receipt is necessary but not sufficient for acceptance. It proves structural completeness, not truth, authorization, code quality, or production safety.

What ships with it: 11 files

36.1 KB alongside SKILL.md, 2 of them executable

examples/

schemas/

scripts/

templates/

tests/

Gives 0 of the 12 instructions most agent orchestration skills give in 439 tokens

Counted across 742 of the 995 authors here whose files we hold, read 2026-08-07

  • Reference existing artifacts by path or URLin 53 of 742, across 25 files
  • Run the full test suite after integrating changesin 51 of 742, across 19 files
  • Dispatch one agent per independent problem domainin 50 of 742, across 17 files
  • Verify fixes do not conflictin 45 of 742, across 13 files
  • Include a suggested skills section in the documentin 45 of 742, across 17 files
  • Redact sensitive informationin 41 of 742, across 11 files
  • Save to the temporary directory of the operating systemin 39 of 742, across 10 files
  • Tailor the document to user-provided focus argumentsin 39 of 742, across 9 files
  • Spot check agent changes for systematic errorsin 34 of 742, across 7 files
  • Write a handoff document summarising the current conversationin 31 of 742, across 6 files
  • Assign each agent a specific scopein 23 of 742, across 8 files
  • Provide specific scope and clear goalin 23 of 742, across 5 files

Said here and by no other author read

  • copy the receipt template into the workspace
  • replace every example value with observed facts
  • record the complete task scope and authorized paths
  • record decisions, unresolved risks, and verification results
  • keep fields with no entries as empty arrays
  • run the receipt validator before handoff

Grouped from the skills themselves: near-identical wordings counted once, and counted by distinct author, so one author publishing three of these counts once. Length counted with cl100k_base; the agent that loads this file may tokenize it differently.

Keep looking

Skills are one crate of 326,984. Ordering is by how many stacks a row turns up in, so the top of any crate is what has actually been picked rather than what has the most stars.