cursor-rule

A repository rule describing how Contextur should run code reviews and personalize reviewer instructions. Contextur is the project’s command-line review workflow, with specialist reviews, a challenger check, and final synthesis.

In plain words
What is it for?
Use it when reviewing a pull request, initializing or updating Contextur, or deciding which project-specific review command and follow-up stages to run.
Why use it?
It gives contributors a consistent process for reviewing pull requests and updating reviewer guidance for the repository.

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/leenspace/contextur/cursor-rule
Clone the repo
git clone --depth 1 https://github.com/leenspace/contextur
Per session 9 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 386 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 $0.00009 $0.00386
Opus 5 $0.00005 $0.00193
Sonnet 5 $0.00002 $0.00077
Haiku 4.5 $0.00001 $0.00039

Measured yesterday against content hash 4aa24f50c0c9, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

cursor-rule 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.

cli/templates/base/integrations/cursor-rule.mdc · 28 lines

What it actually says

This repo uses Contextur for AI code review. The reviewer prompts live in .contextur/reviewers/.

When asked to "review this PR" / "review the code" / "run a code review"

Run contextur review --base {{base_branch}} in the terminal, then follow the 3-stage pipeline in the output:

  1. Stage 1 — Specialists: run each triggered reviewer against the context bundle.
  2. Stage 2 — Challenger: validate findings (CONFIRMED / DOWNGRADED / REJECTED).
  3. Stage 3 — Synthesizer: produce the final developer-facing report.

Present only the synthesized report to the user.

When asked to "initialize contextur" / "set up contextur for this repo" / "personalize the reviewers"

Prefer .agents/skills/contextur-init/SKILL.md when it exists and follow it exactly. It contains the full protocol for ingesting existing AI-friendly docs, launching reviewer-focused research subagents, and appending ## Repo-specific rules sections to each reviewer.

If the shared skill is missing, read .claude/commands/contextur-init.md and follow that protocol instead. If both files are missing, ask the user to re-run contextur init in the terminal first.

When asked to "update contextur" / "refresh the reviewers" / "sync contextur with recent changes"

Read .claude/commands/contextur-update.md and follow its instructions. The update flow is idempotent — it looks for <!-- contextur:repo-specific-start --> / <!-- contextur:repo-specific-end --> markers and replaces only what's between them.

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. yesterday First seen · 28 lines · 9 tokens per session scan A 4aa24f50c0c9

Subscribe to this mod's changes

cursor-rule is a cursor rule published in the GitHub repository leenspace/contextur (7 stars, last pushed 2mo ago), licensed MIT. It adds 9 tokens to every session and 386 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 2026-08-31.