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.
git clone --depth 1 https://github.com/fmflurry/settings-opencodeWrote 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.
[](https://agentmods.dev/rules/fmflurry/settings-opencode/open-pr-check)<a href="https://agentmods.dev/rules/fmflurry/settings-opencode/open-pr-check"><img src="https://agentmods.dev/badge/rules/fmflurry/settings-opencode/open-pr-check/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/rules/fmflurry/settings-opencode/open-pr-check"><img src="https://agentmods.dev/badge/rules/fmflurry/settings-opencode/open-pr-check.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 5.1 | $0.00536 | $0.00536 |
| Opus 5.5 | $0.00214 | $0.00214 |
| Sonnet 5.5 | $0.00107 | $0.00107 |
| Haiku 4.5 | $0.00054 | $0.00054 |
Grade A, and why
open-pr-check 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 3d 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.
What it actually says
Open PR check (mandatory)
Why: an implementation once duplicated an open PR from another maintainer or co-owner (a license proposal) because nobody looked at open PRs first.
Before implementing a change, and before opening a new PR, check the open PRs. This applies to a /ship goal and to any coder, tdd-guide or writer dispatch that changes repo files.
- List open PRs.
gh pr list --state open --limit 100 --json number,title,author,headRefName,isDraft,updatedAt,files - Find overlap with the planned change:
- the same files or directories,
- the same topic in the title or body (search with keywords from the goal),
- the same issue.
Read the body and diff of every candidate:
gh pr view <n>andgh pr diff <n>.
- Decide one outcome per overlapping PR:
- Build on it. The PR already does part or all of the work and is sound. Base the work on its branch, or reuse its content (cherry-pick or copy, crediting the PR). Do not redo it.
- Supersede. The new work replaces the PR. Proceed, link the PR from the new PR, and say what was reused and what was dropped. Never close, edit or push to someone else's PR. Propose closure in a comment only with the owner's agreement.
- Wait or cancel. The PR covers the goal, or it asks for sign-off before anything is applied (for example "do not merge" or "to validate"). Do not implement. Interactive: ask the user. Autonomous: escalate as a human-only blocker with
agent-harness goal escalate "<reason>". - Unrelated. The overlap is incidental. Proceed.
- Record the decision.
- One row per PR in
.claude/state/decisions.tsv(see theshow-your-workskill). - A
## Related open PRslist in the new PR body: number, decision, one-line reason. If the PR template has no such section, put the list under## Locked decisions.
- One row per PR in
Shared ownership. A PR authored by another maintainer or co-owner that touches shared ownership, licensing or legal text always needs that person's sign-off before conflicting work is merged. This holds in autonomous mode too: it is a human-only blocker.
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.
- 3d ago First seen · 28 lines · 536 tokens per session scan A 99abc4dd8b70
open-pr-check is a cursor rule published in the GitHub repository fmflurry/settings-opencode (171 stars, last pushed yesterday), licensed MIT. It adds 536 tokens to every session, about $0.0021 per session on Opus 5.5. 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 2026-10-13.
Other cursor rules, from other repositories
gitlab-mr-review
Review GitLab merge requests via glab when user says "mr this" or "pr this".
check
Analyze staged git changes with archguardian before committing.
ponytail
Ponytail, lazy senior dev mode. Always pick the simplest solution that works.
angular-20
This rule provides comprehensive best practices and coding standards for Angular development, focusing on modern TypeScript, standalone components, signals, and performance optimizations.
dev-standard
Apache Superset development standards and guidelines for Cursor IDE.
prefer-assertions-over-defensive-checks
Prefer assertions over defensive checks when data is guaranteed to be valid.