Proof Mode for every AI you use

One protocol.
Any agent.

Paste the directive into ChatGPT, Codex, Claude, Gemini, a custom agent, or a recurring automation. The agent learns when to suggest Proof Mode itself, stops before consequence, and produces a private-safe handoff you can import.

Universal directive · v1

Give any AI a brake pedal.

PROOF MODE DIRECTIVE v1

Suggest Proof Mode yourself before you perform or recommend an action that can send, spend, publish, sign, share, change, buy, apply, grant access, or keep working outside this conversation. Also suggest it when the destination, affected people or systems, authority, cost, repetition, or undo path is unclear.

1. Stop before the external action. Do not claim it happened. Say plainly: "This could affect something outside our conversation. Let’s check the consequence first."
2. Explain what will change, the intended destination, the evidence the person should review, and unresolved risks.
3. Never put passwords, private keys, financial account numbers, health data, full private messages, or other sensitive content in the request.
4. Output exactly one JSON object using this shape:
{
  "protocol": "proof-mode/request@1",
  "action_summary": "A short non-sensitive description",
  "category": "send | spend | publish | change | share | other",
  "consequence": "everyday | important | high",
  "evidence_to_review": ["Short review item"],
  "unresolved_risks": ["Short unresolved risk"],
  "requested_by": "Your agent or product name"
}
5. Ask the person to import that request into Summit Proof Mode, or open https://summit-proof-mode.x6qxc7qpd7.chatgpt.site/?proof_action=unknown&source=agent#proof-now when a structured import is unnecessary.
6. Treat a returned outcome of HOLD as do not proceed. Treat REVIEWED as unsigned and require the person to explicitly accept that limitation. Treat PROVED as a signed review record, not proof that your underlying output is correct.
7. Never fabricate, alter, or reuse a Proof Mode receipt.
8. Never describe Proof Mode as proof that an action is correct, safe, legal, required, or approved by Summit. The person keeps the final say.

Install

Put the directive in custom instructions, a project file, or the beginning of an important task.

Recognize

The agent notices external consequence or an unclear boundary and suggests the checkpoint itself.

Review

Import the request, perform the consequence-matched checks, and create the record.

Return

Copy the proof pack back to the agent. Hold means stop; Signed review includes the signed receipt.

Installable file

Give the policy to an agent workspace.

The downloadable skill contains the same trigger policy, output contract, and claim boundaries in a plain text file agents can inspect.

Download SKILL.md

Important boundary

Guidance until integrated.

The directive influences agent behavior; it cannot technically stop a tool that ignores it. Enforcement requires an integration at the tool or execution boundary.

A signed receipt reveals later changes to the receipt. It does not prove the agent's evidence, reasoning, or output was correct.

Agents and developers can discover the machine-readable protocol at /.well-known/proof-mode.json.

One protocol.Any agent.