cortexloop-workflow

A configurable workflow for reviewing code across areas such as security, error handling, cleanup, and other project checks. It supports presets for quick reviews, deep reviews, pull requests, and tracking an existing baseline of issues.

In plain words
What is it for?
Use it for project-wide or recent-change reviews, security-focused checks, pre-pull-request checks, benchmark-backed deep reviews, and recording or reflecting on technical debt.
Why use it?
It gives repeated code checks a defined scope and severity threshold, so teams can focus on important problems and re-check changes consistently.

Cursor rule

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 rules/whitequeen306/code-cortex-loop/cortexloop-workflow
Clone the repo
git clone --depth 1 https://github.com/whitequeen306/code-cortex-loop
Per session 39 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 4,584 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 $0.00039 $0.04584
Opus 5 $0.00019 $0.02292
Sonnet 5 $0.00008 $0.00917
Haiku 4.5 $0.00004 $0.00458

Measured 2d ago against content hash 4375f352ffbf, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

cortexloop-workflow 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 2d 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.

rules/cortexloop-workflow.mdc · 371 lines

How it starts

The opening of the file, as written. The whole thing — 371 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CodeCortexLoop Workflow (v2.2)

Read at the start of every /cortexloop invocation. Load project config from cortexloop.config.json if present (merge with preset defaults).

Presets

Preset Command Passes enabled Severity floor Default scope
lite /cortexloop-lite review, security, error-handling High+ only recent changes
default /cortexloop all 7 Medium ask user
quick /cortexloop-quick review, security, error-handling High+ only recent changes
deep /cortexloop-deep all 7 + benchmarks required Low+ whole project
security /cortexloop-security security, error-handling, cleanup(deps only) Medium+ recent changes
pre-pr /cortexloop-pre-pr all 7 High+ recent changes
baseline /cortexloop-baseline n/a (manage debt snapshot) n/a n/a
reflect /cortexloop-reflect n/a (record learnings) n/a n/a

Config file overrides preset defaults. See cortexloop.config.example.json.

Severity Taxonomy

Severity Meaning Direct mode action
Critical Exploit, data loss, broken functionality, silent failure Fix immediately
High Missing critical tests, N+1 on core path, poor error handling Fix before done
Medium Readability, minor perf, non-critical coverage gaps Fix if low-risk
Low Style, optional optimization Report unless confirmed
Info Observations Summary only

Categories

correctness | security | performance | simplicity | tests | error-handling | cleanup

Suppression (apply before analysis)

  1. Read project .cortexloopignore (gitignore-style patterns for paths)
  2. Read inline suppressions: // cortexloop-ignore CL-001 or # cortexloop-ignore CL-001
  3. Skip suppressed findings; list suppressed count in summary

Scope Detection

Recent changes: union of git diff --name-only HEAD, --cached, and branch vs main/master merge-base.

Read the full file on GitHub · 371 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. 2d ago First seen · 371 lines · 39 tokens per session scan A 4375f352ffbf

Subscribe to this mod's changes

cortexloop-workflow is a cursor rule published in the GitHub repository whitequeen306/code-cortex-loop (15 stars, last pushed 1mo ago), licensed MIT. It adds 39 tokens to every session and 4,584 once invoked, about $0.0002 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 2026-08-30.