Operator Approval Loop
Approval contract for agent-drafted outbound messages: obligations, hashed drafts, epoch-keyed decisions, and a delivery ledger that proves what went out.
- What
- Approval contract for agent-drafted outbound messages: obligations, hashed drafts, epoch-keyed decisions, and a delivery ledger that proves what went out.
- Cost
- Free
- Needs
- Pinned version: install the code at commit 4eb71d92a39cab44ad40ac9d8a6a5ccb4029d6c2 exactly (Skill Harbor tested this version). Do not substitute a newer version. If this commit is unreachable, stop and tell me.
- Level
- Beginner — Pinned version: install the code at commit…
- Install
- Copy the installer prompt below into your Muse — your agent does the rest.
Curated by Skill Harbor: a contract for agents that draft messages to external counterparties, so nothing sends on the agent's own judgment and the operator stays informed internally. Every outbound draft is filed as an obligation whose status moves from drafted to approved or rejected to sent, carrying direction, counterparty, channel and an epoch timestamp. Each obligation has one draft sidecar holding the exact text, its sha256 hash, origin coordinates and priority; decisions are recorded with the operator id, a nonce and the draft epoch they were made against, and epoch rotation means re-filing a draft invalidates any decision keyed to the old epoch, so a stale approval can never release rewritten text. A durable claim reserves dispatch with at most one active claim per obligation, preventing double sends, and a delivery ledger row proves one send or notice per obligation-decision pair. A pre-draft baseline gate can refuse filings, and internal filing notices keep the operator informed. Includes a reference SQL schema for the ledger. From the affaan-m/ECC repository (MIT). Honest caveats: a workflow contract, not turnkey software; the ledger schema must be wired into your own stack. Skill Harbor never reviews the code, review it yourself before use.
Version:
Quick answer
Operator Approval Loop is a free skill for Muse. a contract for agents that draft messages to external counterparties, so nothing sends on the agent's own judgment and the operator stays informed internally. Every outbound draft is filed as an obligation whose status moves from drafted to approved or rejected to sent, carrying direction, counterparty, channel and an epoch timestamp.
Install
Copy the install package below, then paste it into Muse🧪 Install ran in our test sandbox · Nov 11, 2026📌 Pinned version: commit 4eb71d9Pinned version: install the code at commit 4eb71d92a39cab44ad40ac9d8a6a5ccb4029d6c2 exactly (Skill Harbor tested this version). Do not substitute a newer version. If this commit is unreachable, stop and tell me. Use "Operator Approval Loop" with your Muse. 1. Open the skill: https://raw.githubusercontent.com/affaan-m/ECC/4eb71d92a39cab44ad40ac9d8a6a5ccb4029d6c2/skills/operator-approval-loop/SKILL.md and copy the full SKILL.md text. 2. Paste it into a chat with Muse and add: "Design an approval loop for agent-drafted customer replies" or "Implement the obligation/draft/decision ledger from the reference schema." 3. Enforce the invariants: no send without an approved snapshot, epoch rotation on every re-file, at most one active claim per obligation. Tip: start with the baseline gate and filing rules before the SQL; the ledger only matters if drafts are filed cleanly. Safety: a skill is plain-text instructions; it runs nothing by itself. Approval records are evidence; store them where auditors can reach them.
Saved to your recent installs. Find it anytime on /connect.
🔒 Security, provenance and what this touches
The install prompt below already includes the vetting steps: your agent follows the community checklist before installing anything with executable code. Want more?
Verification certificate
Dated facts about what was checked for this listing, and how. This is not a safety certification.
- Pinned version
- 4eb71d9 · 2026-10-13
- Sandbox install test
- Install ran in our test sandbox · Nov 11, 2026
- Creator identity
- Not verified
- Fingerprint watch
- Last checked · Nov 21, 2026 : no change detected in the files linked by this install prompt
- Install prompt analysis
- 2026-10-13 : No commands, network calls, packages, file writes or API keys detected.
Skill Harbor never reviews the code of a listed skill. These are dated facts about the install prompt and our install test, not a safety certification. Review a skill yourself before you install it. How we verify
Questions
How do I install a skill?
Every product page includes a copy-paste install prompt. Paste it into your Muse and it sets the skill up for you — no manual configuration.
Where does my money go?
Straight to the seller. Skill Harbor never processes payments: checkout happens on the seller’s own page, usually Stripe.
What does the ✓ next to a creator’s name mean?
It means we confirmed the identity of the person behind the listing. It says nothing about the code itself — always check a skill before installing it.