Handoff protocol

Skill IrfanSadiqRahat/constellation/methodology/handoff-protocol

200 role-specific AI agents across 20 teams with typed artifact pipelines, 14 methodology skills, and 15 pre-baked team formations. The virtual engineering org for Claude Code, Cursor, Codex CLI.

Install

npx -y skills add IrfanSadiqRahat/constellation --skill handoff-protocol

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

no licenseNo license file was found in the repository. Code published without one is not open source by default, so using it at work is a question for whoever answers licensing questions where you are.
1 stars1 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

Pass typed artifacts between roles with explicit contracts. The connective tissue of multi-agent pipelines.

SKILL.md

1.9 KB, 409 tokens by cl100k_base, as published. Nobody here has run it

handoff-protocol

When activated

A role has produced an artifact and the next role needs to pick it up. Don't paste the whole conversation. Don't summarize verbally. Use the protocol.

The deliverable: `HandoffPacket`

artifact_id: <unique>
artifact_type: <PRD | DesignBrief | BackendArchitecture | ...>
produced_by: <role>
produced_at: <iso ts>
upstream_chain: [<artifact_id>, ...]      # what this depends on
content: <link to artifact file>
schema_version: <semver>
status: ready | provisional | blocked
open_decisions: [<decision needed before downstream can start>]
constraints_carried_forward: [<from upstream>]
test_coverage: <link to tests/evals if applicable>
review_state: { spec_pass: bool, quality_pass: bool, by: <role> }
next_role: <consumer agent id>
next_step: <what the consumer should do first>

Operating principles

Artifacts have IDs, not just types. Same type can flow many times.
Upstream chain is captured. Traceability for "why was this decision made?"
Open decisions surfaced explicitly. Don't bury them in prose.
Constraints carry forward. If PRD said "must be GDPR-compliant", the BackendArchitecture handoff includes that.
Status is honest. provisional lets downstream start without committing.
next_step is explicit. Don't make the consumer guess.

Why this exists

Multi-agent systems fail when handoffs are conversational. Constellation's typed contracts only work if the handoff packet itself is typed. This skill enforces it.

Storage

Handoff packets live in .constellation/handoffs/<timestamp>-<artifact_id>.yaml. The team workspace is a chain of these. Auditable, replayable, forkable.

Gives 0 of the 12 instructions most agent orchestration skills give in 409 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

give each artifact an id
capture the upstream artifact chain
surface open decisions explicitly
carry forward upstream constraints
set an honest handoff status
make the next step explicit

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.