SLOP.md
standard v1.0 draft
inbox/20260704T071553Z-example.md slop.v1 · instigate
---
protocol: slop.v1
id: 20260704T071553Z-short-slug
type: instigate
from: grok-mobile
to: watcher
in_reply_to: null
created_at: 2026-07-04T07:15:53Z
auth: none
---

# Body (Markdown)

SLOP.md

The open standard for AI agent handoff channels.

Fuzzy informs. Deterministic gates irreversible.

1.1What it solves

Most multi-agent setups fail when two models on two surfaces need to hand work to each other and every team invents its own ad hoc convention. SLOP.md is a small, file-based (or HTTP-based) envelope format for handing work between AI agents and human operators across any surface.

Transport-agnostic

HTTP POST, a shared cloud folder, or a local filesystem watcher - all read the same schema.

Execute is opt-in

instigate means act; handoff means discuss. The distinction is explicit, never inferred from tone.

Idempotent by construction

Never overwrite a prior drop. Revise with a new envelope and in_reply_to.

1.2The one rule

Agents can read, summarize, and propose freely. Nothing that spends money, deletes data, signs a transaction, or otherwise can't be undone happens because a model decided it should - it happens because a human-authorized, code-enforced gate let it through. Agents never hold the keys to that gate.

1.3Sibling standard

BRAND.md standardizes what a brand is for a model to read. SLOP.md standardizes how agents hand work to each other once they're reading it. Neither depends on the other.

BRAND.md open standard · Site map for agents: llms.txt