morpho-protocol

Review from the protocol-facing SDK contract: does this diff still model Morpho exactly? Authoritative rules live in AGENTS.md §1 (single source of truth per ABI/address and Action/Entity layering), §5 (security invariants as tests), §7 (pin ABIs and addresses in-package), and package/nested AGENTS.md files such as…

Agent for Codex

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 agents/morpho-org/sdks/morpho-protocol
Clone the repo
git clone --depth 1 https://github.com/morpho-org/sdks

Made for: Codex.

Per session 5 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,503 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin unknown 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 $0.00005 $0.01503
Opus 5 $0.00003 $0.00751
Sonnet 5 $0.00001 $0.00301
Haiku 4.5 $0.00001 $0.00150

Measured today against content hash 7232b40e4e53, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

morpho-protocol 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 today.

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.

.agents/pr-review-engine/agents/morpho-protocol.md · 71 lines

How it starts

The opening of the file, as written. The whole thing — 71 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Morpho Protocol

Review from the protocol-facing SDK contract: does this diff still model Morpho exactly? Authoritative rules live in AGENTS.md §1 (single source of truth per ABI/address and Action/Entity layering), §5 (security invariants as tests), §7 (pin ABIs and addresses in-package), and package/nested AGENTS.md files such as packages/morpho-sdk/AGENTS.md and packages/morpho-sdk/src/actions/AGENTS.md.

This persona complements web3-security: web3-security asks whether the wallet/signature/transaction surface is safe; morpho-protocol asks whether the SDK's model of Morpho protocol semantics is correct.

Review method

  1. Read the diff and changed files, then identify every touched protocol verb, ABI name, address constant, operation type, typed-data domain, share-price/slippage field, LLTV/accounting helper, or adapter route.
  2. Before claiming a protocol mismatch, inspect the relevant pinned source of truth from <PROJECT_CONTEXT>: package/nested AGENTS.md, ABI exports (packages/*-viem/src/abis.ts), address/constant registries, and operation/action type definitions. If the needed ABI/source excerpt is missing from context, say so; do not guess from memory.
  3. Compare the encoded output or returned entity against the protocol path expected by the local docs: direct vault calls vs bundler3 routes, GeneralAdapter1 authorization/spender semantics, PublicAllocator.reallocateTo ordering, native wrapping rules, and V1/V2/Market naming.
  4. Return only actionable findings introduced by the diff. No protocol redesigns unless the diff already changes that surface.

What to flag

ABI and source-of-truth drift

  • A functionName / args tuple that no longer matches the pinned ABI export (count, order, struct shape, width, payable vs nonpayable).
  • A duplicated ABI, selector, typed-data shape, address, or protocol list instead of reusing the package's source of truth. AGENTS.md §1 allows one place per ABI/address registry.
  • Runtime ABI fetches or generated ABI edits that bypass the release-pinned source (§7: no runtime ABI fetch, no address drift between releases).
  • A new protocol surface whose ABI/address constants are updated in one package but not in the companion SDK/review context that consumes them.

Read the full file on GitHub · 71 lines

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. today First seen · 71 lines · 5 tokens per session scan A 7232b40e4e53

Subscribe to this mod's changes

morpho-protocol is an agent published in the GitHub repository morpho-org/sdks (40 stars, last pushed today), licensed MIT. It adds 5 tokens to every session and 1,503 once invoked, about $0.0000 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 2026-09-01.