220-review_for_bugs

220-review_for_bugs is a cursor rule for Cursor from pblagoje/mcp-ollama-python. It costs 208 tokens per session, scanned A, original, MIT.

A coding rule that requires reviewing code changes for bugs before completing a task.

In plain words
What is it for?
It is for checking the final diff and nearby code, then fixing clear defects before returning the work.
Why use it?
It helps catch logic mistakes, missing error handling, broken interfaces, security problems, and resource leaks introduced by the changes.

Cursor rule for Cursor

Written for Cursor: installed under .cursor/.

Good fit It is for checking the final diff and nearby code, then fixing…

Compare 6 cursor rules from other repositories ↓
Install with agentmods
npx agentmods add rules/pblagoje/mcp-ollama-python/220-review_for_bugs
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/pblagoje/mcp-ollama-python

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 220-review_for_bugs

README.md
[![agentmods](https://agentmods.dev/badge/rules/pblagoje/mcp-ollama-python/220-review_for_bugs.svg)](https://agentmods.dev/rules/pblagoje/mcp-ollama-python/220-review_for_bugs)
Your own site
<a href="https://agentmods.dev/rules/pblagoje/mcp-ollama-python/220-review_for_bugs"><img src="https://agentmods.dev/badge/rules/pblagoje/mcp-ollama-python/220-review_for_bugs.svg" alt="Measured on agentmods" height="20"></a>
Per session 208 This file is loaded in full into every session.
When invoked 208 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 $0.00208 $0.00208
Opus 5 $0.00104 $0.00104
Sonnet 5 $0.00042 $0.00042
Haiku 4.5 $0.00021 $0.00021

Measured 6d ago against content hash fd7a1a0a296d, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

220-review_for_bugs 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/220-review_for_bugs.mdc · 21 lines

What it actually says

020 — Review for bugs before return

After any code change, and before the final reply to the user:

  1. Re-read the diff you introduced (and immediate call sites) for defects.
  2. Check especially for:
    • Logic / off-by-one / wrong defaults
    • Missing null/empty/error handling on new paths
    • Broken contracts (return types, kwargs, side effects)
    • Race / ordering / cache freshness issues
    • Security: path traversal, secret leakage, unsafe YAML/load
    • Resource leaks (files, connections) and incorrect cleanup
  3. Fix clear bugs in the changed code before finishing.
  4. If a suspected bug is outside the change scope or needs a product decision, call it out briefly in the reply — do not silently leave a known defect in code you just wrote.
  5. Prefer a targeted fix over a large refactor.
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 · 21 lines · 208 tokens per session scan A fd7a1a0a296d

Subscribe to this mod's changes

220-review_for_bugs is a cursor rule published in the GitHub repository pblagoje/mcp-ollama-python (5 stars, last pushed 15d ago), licensed MIT. It adds 208 tokens to every session, about $0.0010 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 2026-08-31.