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/keldron-ai/keldron-agentWrote 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/keldron-ai/keldron-agent/pr-description-template)<a href="https://agentmods.dev/rules/keldron-ai/keldron-agent/pr-description-template"><img src="https://agentmods.dev/badge/rules/keldron-ai/keldron-agent/pr-description-template/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/keldron-ai/keldron-agent/pr-description-template"><img src="https://agentmods.dev/badge/rules/keldron-ai/keldron-agent/pr-description-template.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 | $0.00456 | $0.00456 |
| Opus 5.5 | $0.00182 | $0.00182 |
| Sonnet 5.5 | $0.00091 | $0.00091 |
| Haiku 4.5 | $0.00046 | $0.00046 |
Grade A, and why
pr-description-template 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 2mo 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
Pull request descriptions
When the user asks for a PR description, opening PR text, or merge-request summary, fill and output this template (replace placeholders like {TICKET_ID} with real values; omit sections only if truly N/A).
# PR Description — {TICKET_ID}
---
## Summary
{One paragraph: what this PR does, why, and the user-facing behavior change. Reference the ticket ID. Mention key implementation approach (e.g., "CSS-only", "no new dependencies"). Call out what is NOT changed if relevant.}
---
## What Changed
- **{Area 1}**: {Concise description of changes in this area. Include specific values, class names, props, config — be precise enough that a reviewer knows what to look for.}
- **{Area 2}**: {Same format. Group by logical area: Frontend, Backend, Tests, Config, Infra, etc.}
- **Tests**: {What tests were added/updated. Note any testing limitations (e.g., "not asserted in JSDOM due to mocked CSS").}
---
## Files Modified
| Area | File | Change |
| -------- | ----------------------------- | --------------------------------------------------------- |
| {Area} | `{path/to/file}` | {Brief description of what changed in this file} |
| {Area} | `{path/to/file}` | {Brief description} |
---
## Alternative: Plain-text version (if Markdown tables aren't supported)
<!-- Include this section when the target platform (e.g., some CI tools, email) doesn't render Markdown tables. Otherwise, the Markdown version above is sufficient. -->
```text
Summary
{Same summary as above, but with quotes instead of backticks for inline code.}
What Changed
- {Area}: {description}
- Tests: {description}
Files Modified
- {path/to/file} — {description}
- {path/to/file} — {description}
```
---
Do not substitute a shorter format unless the user explicitly asks for something different.
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.
- 2mo ago First seen · 59 lines · 456 tokens per session scan A bfce6b325139
pr-description-template is a cursor rule published in the GitHub repository keldron-ai/keldron-agent (6 stars, last pushed 6mo ago), licensed Apache-2.0. It adds 456 tokens to every session, about $0.0018 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 2026-08-31.
Other cursor rules, from other repositories
risk-factors
Risk scoring factor definitions and weights for PR review dispatch.
infra-devops
Infrastructure, Cloud, Terraform, Docker & CI/CD Agent.
context-delegate
Context Gatherer & External LLM Prompt Generator.
enterprise-architect
Enterprise System Architect & High-Level Auditor.
claude-skills-karpathy
Behavioral guidelines to reduce common LLM coding mistakes. Use when writing, reviewing, or refactoring code to avoid overcomplication, make surgical changes, surface assumptions, and define verifiable success criteria.
ponytail
Ponytail, lazy senior dev mode. Always pick the simplest solution that works.