What is code-cortex-loop AGENTS.md?

Instructions for CodeCortexLoop, a code-quality workflow that scores findings and includes security and refactoring checks. A quality finding must include evidence and a confidence level.

Use them when running cortexloop commands, reviewing findings, performing security checks, establishing a baseline, or making refactors.

They prevent speculative issues from being treated as real defects and set baseline checks for safer code changes.

code-cortex-loop AGENTS.md — Instructions file by whitequeen306

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 instructions/whitequeen306/code-cortex-loop/agents-md

Clone the repo

git clone --depth 1 https://github.com/whitequeen306/code-cortex-loop

Made for: Codex, OpenCode.

Per session 1,601 This file is loaded in full into every session.

When invoked 1,601 The same file — it is already loaded in full.

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.

Model	Per session	Once invoked
Fable 5	$0.01601	$0.01601
Opus 5	$0.00800	$0.00800
Sonnet 5	$0.00320	$0.00320
Haiku 4.5	$0.00160	$0.00160

Measured yesterday against content hash 1c2b4c2bbc5d, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

code-cortex-loop AGENTS.md 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 yesterday.

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.md · 153 lines

How it starts

The opening of the file, as written. The whole thing — 153 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CodeCortexLoop — Agent Rules

These rules apply when running any /cortexloop* command. Tool-specific installs copy this to the appropriate rules directory or merge into project AGENTS.md.

When CodeCortexLoop Runs

Load cortexloop.config.json from project root (optional)
Load .cortexloopignore (optional)
Follow cortexloop-workflow for severity, scoring, CI, re-verify, and post-processing
Follow refactor-safety for all code modifications
Follow baseline-policy when using /cortexloop-baseline or ci.baseline
Follow learning-loop when querying or recording playbook entries

Finding Quality Gate

Every scored finding must include:

Evidence: trigger path, measurement, test gap, static proof, or audit output
Confidence: high or medium

Low-confidence speculation must not become a scored finding. Put it in Open Questions or drop it.

Security Baseline (always during security pass)

Every code change must satisfy:

User input sanitized at boundaries
SQL parameterized (no string concatenation)
No secrets in code, logs, or git
Error messages must not leak internals
File uploads restricted (type, size, path)
External URLs validated (SSRF prevention)

Refactor Safety (Direct mode)

Preserve behavior exactly during simplify/perf passes
Chesterton's Fence: understand before removing
Ask before deleting dead code or dependencies
Separate refactors from bug fixes
Run tests after each logical change group; revert on failure

Suppression

Project: .cortexloopignore (gitignore syntax)
Inline: // cortexloop-ignore CL-001 or # cortexloop-ignore CL-001
Never suppress Critical without explicit user approval

CI Gate

After CI report generation:

node scripts/ci-gate.mjs docs/cortexloop/report.json
# Baseline ratchet (new findings only):
node scripts/baseline.mjs diff docs/cortexloop/report.json
node scripts/ci-gate.mjs docs/cortexloop/report.json --baseline

Exit codes: 0 pass, 1 Critical, 2 High over threshold, 3 report error.

Read the full file on GitHub · 153 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.

yesterday First seen · 153 lines · 1,601 tokens per session scan A 1c2b4c2bbc5d

Subscribe to this mod's changes

code-cortex-loop AGENTS.md is an instructions file published in the GitHub repository whitequeen306/code-cortex-loop (15 stars, last pushed 1mo ago), licensed MIT. It adds 1,601 tokens to every session, about $0.0080 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.

Productivity Security

codex AGENTS.md

AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.

openai/codex · 5,182 tokens

buildNext

Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).

microsoft/vscode · 6,785 tokens

code-cortex-loop AGENTS.md