agentleFS
Sign inStart free
AgoragenticAgoragentic/agoragentic-integrations/.agents/skills/agoragentic-assure/SKILL.md

agoragentic-assure

Skill41 starsChanged 44 days agoMITView on GitHub

Prepare and evaluate an autonomous agent transaction without self-granting authority or moving money. Use for bounded authority requests, pre-execution checks, payment and delivery evidence, safe retry decisions, outcome verification, and reconciliation.

We split this skill into the rules it gives an agent

3 rules. About 0 are common, 2 are distinctive, and 1 is very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈2

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 1

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    Use the source-only @agoragentic/transaction-assurance package when an agent must bind principal authority, seller terms, payment evidence, …

    line 8
  2. Distinctive:

    After approval to add local source files and dependencies:

    line 24
  3. Distinctive:

    Stop when authority, identity, terms, amount, rail, expiry, revocation, or replay evidence is missing.

    line 42

≈ “Common” is an estimate: at least 1 in 5 of the 308,232 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Agoragentic Transaction Assurance

Use the source-only @agoragentic/transaction-assurance package when an agent must bind principal authority, seller terms, payment evidence, execution, delivered outcome, and reconciliation.

Contract Pin

  • package: @agoragentic/transaction-assurance
  • version: 0.2.0-alpha.0
  • source: transaction-assurance
  • authority schema: transaction-assurance/schema/normalized-authority.v1.json
  • evaluation schema: transaction-assurance/schema/transaction-assurance-evaluation.v1.json
  • network calls: none
  • authority granted by installation or evaluation: false

The package is unpublished source-only alpha software. Do not substitute an npm registry package or claim registry availability.

Install And Prove Locally

After approval to add local source files and dependencies:

git clone --depth 1 https://github.com/rhein1/agoragentic-integrations.git
cd agoragentic-integrations/transaction-assurance
npm ci
npm run self-test

The self-test is local and no-spend. It requires no wallet, API key, payment method, provider call, or hosted authority.

Workflow

  1. Inspect the authority artifact and current rail/platform availability.
  2. Detect the protocol family without treating recognition as verification.
  3. Normalize the artifact conservatively; missing verifier evidence remains unverified.
  4. Prepare a proposal-only authority request for the principal.
  5. Build and evaluate a pre-execution envelope.
  6. Stop when authority, identity, terms, amount, rail, expiry, revocation, or replay evidence is missing.
  7. Execute only through a separately authorized host or rail; this skill never executes or pays.
  8. Bind returned payment, execution, outcome, and reconciliation evidence, then evaluate post-execution.

Owner Handoff

The approval packet must state the purpose, exact actions, seller/category/rail/currency scope, per-action/daily/total limits, expiry, revocation behavior, data shared, expected evidence, reconciliation path, wallet requirement, risks, blocked actions, and approve/edit/reject choices. It must not contain secrets or raw private payloads.

An agent may prepare this packet. It may not approve itself, broaden scope, raise a budget, invent verifier evidence, retry an ambiguous paid action blindly, or claim a complete chain while evidence is missing.

Required Result

Report protocol verification, authority, terms, payment, execution, outcome, outcome verification, reconciliation, blockers, unknowns, and the next safe action. Always state:

Authority granted by this report: false

Advanced Context

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

Reviews can't be read right now.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

Check your setup, free