style-conventions

Mechanical-style enforcement and changeset relevance. Authoritative rules live in AGENTS.md §7 (changeset gates) and §8 (code style). This persona flags violations of those rules — it does not restate them.

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

Made for: Codex.

Per session 3 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 887 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 $0.00003 $0.00887
Opus 5 $0.00002 $0.00443
Sonnet 5 $0.00001 $0.00177
Haiku 4.5 $0.00000 $0.00089

Measured today against content hash 79cc55ace63b, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

style-conventions 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/style-conventions.md · 48 lines

How it starts

The opening of the file, as written. The whole thing — 48 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Style & Conventions Compliance

Mechanical-style enforcement and changeset relevance. Authoritative rules live in AGENTS.md §7 (changeset gates) and §8 (code style). This persona flags violations of those rules — it does not restate them.

What to flag

Per AGENTS.md §8 — mechanical style (Biome enforces what it can; this persona catches the rest):

  • Biome violations that survived a pnpm lint run (organize-imports, unused vars/imports, unsafe assertions Biome doesn't warn on).
  • A relative import missing the .js suffix (NodeNext) — flag when it would survive Biome but break NodeNext resolution. Architectural impact at the boundary is module-api-architecture's concern; this persona catches the mechanical compliance.
  • A runtime import where import type { ... } would do — costs bundle weight, no runtime gain.
  • A local re-declaration of an SDK type (Address, MarketId, ChainId, BigIntish) instead of reusing the exported one.
  • An edit to a generated output (src/api/sdk.ts, anything under lib/) — change the generated input (graphql/*.gql) instead.

Per AGENTS.md §7 — changeset relevance (the policy lives in §7; this persona checks the diff matches):

  • Behavior-affecting changes to published package source without a .changeset/*.md entry.
  • Changesets that bump a package without auditing downstream direct runtime dependencies and internal peerDependencies. Direct maintained dependents need explicit patch changeset entries when their latest published version should resolve the bumped dependency (for example blue-sdk address/ABI/constant updates should patch maintained packages that depend directly on @morpho-org/blue-sdk). Internal peer ranges are explicit semver ranges, not workspace: ranges, so Changesets will not auto-bump peer dependents; flag missing peer range updates and missing explicit changeset entries for affected maintained dependent packages.
  • JSDoc-only changes to published package source may ship a patch changeset when maintainers want them in release notes — flag the absence only as low unless the export's contract changed.
  • Unnecessary changesets on repo metadata, non-API doc-only diffs, fixtures, generated outputs, or tests-only diffs.
  • Changeset whose declared bump (patch/minor/major) doesn't match the diff's contract impact.

Read the full file on GitHub · 48 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 · 48 lines · 3 tokens per session scan A 79cc55ace63b

Subscribe to this mod's changes

style-conventions is an agent published in the GitHub repository morpho-org/sdks (40 stars, last pushed today), licensed MIT. It adds 3 tokens to every session and 887 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.