- Home
- Skills
- Agents & Orchestration
- Agent Delegation Scope Chain Verifier
More screenshots
Works with the AI Agents you already use
Agent Delegation Scope Chain Verifier
Offline evidence verifier for agent delegation chains, effective scope, action permissions and supplied spend facts, with no authority to issue or enforce grants.
$7
Agent Delegation Scope Chain Verifier
Example session with this skill installed
Root allows crm.read on customers, read permission, USD 100 and depth 2. Worker A receives the same read scope and USD 25. Worker A delegates payments.refund to Worker B, which records a USD 5 refund action. Verify the supplied chain and write a local evidence packet.
- Read your context and instructions
- Compiled the agent delegation scope
- Generated the data export
Agent Delegation Verification
Status: BLOCK
| Delegation | Child | Decision | Reason |
|---|---|---|---|
| A to B | Worker B | BLOCK | Tool payments.refund expands beyond the parent scope |
| Action | Amount | Decision | Reason |
|---|---|---|---|
| refund | USD 5 | BLOCK | No valid effective grant for Worker B |
Files created
The local run writes result.json, delegation-matrix.csv, action-matrix.csv, violations.jsonl, DELEGATION_VERIFICATION.md and evidence-receipt.json. The receipt binds every supplied input and generated output with SHA-256.
Owner action
Reject this supplied chain and issue a corrected, narrower delegation only if the action is intended. The verifier did not authenticate identities or signatures, issue or enforce a grant, invoke an agent, execute a payment or contact any network service.
delegation-matrix.csv
CSV · data export
Example file from a real run - the skill writes it into your workspace.
Connects securely to your tools. The creator never sees your data.
About this skill
This downloadable local package turns authorized buyer-supplied files into a fixed, reproducible review packet. It includes an installable Python CLI, a local stdio MCP adapter and a companion Agent Skill. One run creates:
- result.json
- delegation-matrix.csv
- action-matrix.csv
- violations.jsonl
- DELEGATION_VERIFICATION.md
- evidence-receipt.json
The deterministic core checks delegation lineage, effective tool/resource/permission scope, time windows, depth and supplied spend facts. It rejects unsafe paths and malformed inputs, never overwrites an existing packet, escapes formula-active CSV cells and binds each input and output with SHA-256. Processing stays local. No API key, login, upload, telemetry or live external action is included.
Best for agent platform builders and operators testing delegated tool, resource, permission and spend boundaries; teams needing reviewable evidence before risky actions; and agencies preparing reproducible client handoffs. Requires Windows 11, Python 3.11–3.14 and authorized local evidence files. Optional mcp==2.2.0 enables the local adapter.
Limitations: no identity attestation, signature verification, grant issuance, policy enforcement, agent invocation, payment, network access or prevention guarantee. This is a one-time local V1.
Find more skills like this on the Claude Skills Marketplace, the Codex Skills Marketplace and the Gemini Skills Marketplace, or browse Claude Skills for Agents & Orchestration.
Requires local evidence files in JSON format. Cannot access remote APIs or live accounts to verify identity; relies entirely on the provided cryptographic traces and policy files.
How to use
- 1
Connect your agent to the Agensi MCP
Copy the prompt and paste it into Claude, ChatGPT, Cursor or any agent that supports MCP. It sets up the connection for you. Manual setup
- 2
Sign in to Agensi
Your agent shows a sign-in link. Sign in and click Allow.
- 3
Ask for what you need
Your agent loads this skill and uses it on your task. It always asks before buying a skill.
Reviews
No reviews yet
Be one of the first to try it. Every listed skill goes through the trust checks below.
Security scanned
Checked by our 8-point scan before listing
Fresh listing
Recently published to Agensi
Money-back guarantee
Doesn't do what its page promises? You get your money back.
Trust & safety
Security scan
Security scan passed 2 months ago
- Software
Python