agoragentic-prove

agoragentic-prove is a cursor rule for Cursor from rhein1/agoragentic-integrations. It costs 36 tokens per session (246 once invoked), scanned A, original, MIT.

Rules for producing or checking local proof and receipt records for an Agoragentic agent run. These records describe what happened, which policies applied, and where supporting evidence is stored.

In plain words
What is it for?
Use them to document inputs and outputs, hashes, approvals, policy decisions, execution status, artifacts, blockers, and next actions.
Why use it?
They make run evidence precise and auditable while preventing unsupported claims or exposure of secrets and private data.

Cursor rule for Cursor

Written for Cursor: installed under .cursor/.

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add rules/rhein1/agoragentic-integrations/agoragentic-prove
Clone the repo
git clone --depth 1 https://github.com/rhein1/agoragentic-integrations

Made for: Cursor.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for agoragentic-prove

README.md
[![agentmods](https://agentmods.dev/badge/rules/rhein1/agoragentic-integrations/agoragentic-prove.svg)](https://agentmods.dev/rules/rhein1/agoragentic-integrations/agoragentic-prove)
Your own site
<a href="https://agentmods.dev/rules/rhein1/agoragentic-integrations/agoragentic-prove"><img src="https://agentmods.dev/badge/rules/rhein1/agoragentic-integrations/agoragentic-prove.svg" alt="Measured on agentmods" height="20"></a>
Per session 36 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 246 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00036 $0.00246
Opus 5 $0.00018 $0.00123
Sonnet 5 $0.00007 $0.00049
Haiku 4.5 $0.00004 $0.00025

Measured 6d ago against content hash 21d0e6b374cd, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

agoragentic-prove scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 6d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

.cursor/rules/agoragentic-prove.mdc · 31 lines

What it actually says

Agoragentic Prove

Use existing Harness Core / ECF evidence models. Do not create a competing receipt family.

A local proof or receipt should identify, where available:

  • producer/adapter and version
  • task or intent
  • input and output hashes
  • policy decision
  • authority/spend class
  • approval reference
  • execution status and duration
  • evidence/artifact references
  • blockers or next safe action

Keep claims precise. A local receipt is not a settlement receipt, certification, trust endorsement, marketplace verification, or owner approval unless an authoritative external artifact explicitly proves that separate state.

Never include credentials, raw secrets, private prompts, unrestricted tool output, or private ECF payloads.

Advanced Context

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 6d ago First seen · 31 lines · 36 tokens per session scan A 21d0e6b374cd

Subscribe to this mod's changes

agoragentic-prove is a cursor rule published in the GitHub repository rhein1/agoragentic-integrations (35 stars, last pushed today), licensed MIT. It adds 36 tokens to every session and 246 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.