self-review

self-review is a cursor rule for Cursor from Axcient/public-gateway-mcp. It costs 388 tokens per session, scanned A, original, Apache-2.0.

Rules requiring a final self-review against AGENTS.md, the repository’s instructions for coding agents, before declaring a change complete.

In plain words
What is it for?
Checking implementation, testing, naming, resource cleanup, database access, and other repository-specific requirements before reporting completion.
Why use it?
They catch violations that automated checks may miss, such as incorrect MCP setup, incomplete cleanup, mocking, or weak tests.

Cursor rule for Cursor

Written for Cursor: installed under .cursor/. Also seen: mentions AGENTS.md.

Good fit Checking implementation, testing, naming, resource cleanup, database access, and other repository-specific requirements before reporting completion.

Compare 6 cursor rules from other repositories ↓
Install with agentmods
npx agentmods add rules/axcient/public-gateway-mcp/self-review
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.

Clone the repo
git clone --depth 1 https://github.com/Axcient/public-gateway-mcp

Made for: Cursor.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for self-review

README.md
[![agentmods](https://agentmods.dev/badge/rules/axcient/public-gateway-mcp/self-review.svg)](https://agentmods.dev/rules/axcient/public-gateway-mcp/self-review)
Your own site
<a href="https://agentmods.dev/rules/axcient/public-gateway-mcp/self-review"><img src="https://agentmods.dev/badge/rules/axcient/public-gateway-mcp/self-review.svg" alt="Measured on agentmods" height="20"></a>
Per session 388 This file is loaded in full into every session.
When invoked 388 The same file — it is already loaded in full.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.00388 $0.00388
Opus 5 $0.00194 $0.00194
Sonnet 5 $0.00078 $0.00078
Haiku 4.5 $0.00039 $0.00039

Measured 6d ago against content hash 228bfce6e59d, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

self-review 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 6d ago.

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.

.cursor/rules/self-review.mdc · 26 lines

What it actually says

Mandatory self-review before completing work

Before declaring any code change complete, you MUST:

  1. Read AGENTS.md and review every rule against your changes
  2. Specifically verify (including current MCP / testing rules in AGENTS.md):
    • mcp is a module-level global — assigned at import time outside any function; FastMCP CLI-importable
    • OpenAPI docs unchanged — pass loaded specs into from_openapi as-is; no copy/deep-copy/path rewrite
    • One httpx.AsyncClient per OpenAPI mountbase_url from that spec’s servers[0].url; close all in lifespan/finally
    • No BaseException — use try/finally for cleanup
    • No mocking — no monkeypatch/MockTransport/fake clients; prefer DI + real local HTTP
    • Assert full objects — never assert partial responses (single fields, lengths, filtered projections)
    • No enumerated variables — use lists, not x1, x2
    • No time.sleep — never add sleep calls anywhere
    • No raw DB access in tests — all database operations go through PostgresInteractor when DB exists
  3. Only after confirming compliance with ALL rules, report the work as done

If any rule is violated, fix it before reporting completion. Do not rely on just check-all alone — it checks tooling (lint, types, coverage) but NOT AGENTS.md conventions.

When a code review runs, the reviewer must also read AGENTS.md first and enforce it (see .cursor/rules/code-review-agents.mdc).

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. 6d ago First seen · 26 lines · 388 tokens per session scan A 228bfce6e59d

Subscribe to this mod's changes

self-review is a cursor rule published in the GitHub repository Axcient/public-gateway-mcp (0 stars, last pushed 13d ago), licensed Apache-2.0. It adds 388 tokens to every session, about $0.0019 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.