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.
npx agentmods add rules/brad-edwards/aptl/no-jumping-aheadgit clone --depth 1 https://github.com/Brad-Edwards/aptlWrote 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/brad-edwards/aptl/no-jumping-ahead)<a href="https://agentmods.dev/rules/brad-edwards/aptl/no-jumping-ahead"><img src="https://agentmods.dev/badge/rules/brad-edwards/aptl/no-jumping-ahead.svg" alt="Measured on agentmods" 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 | $0.00407 | $0.00407 |
| Opus 5 | $0.00204 | $0.00204 |
| Sonnet 5 | $0.00081 | $0.00081 |
| Haiku 4.5 | $0.00041 | $0.00041 |
Grade A, and why
no-jumping-ahead 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 6d 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
DO NOT JUMP AHEAD
ALWAYS follow these rules when working on this codebase:
- ONLY do what is explicitly requested - Do not add extra features, scripts, or files that weren't asked for
- DO NOT assume what the user wants - If unclear, ask for clarification rather than making assumptions
- CHECK before going beyond the request - If you think something additional might be helpful, ask first
- STOP when the task is complete - Don't continue adding "helpful" extras
- RESPECT the user's workflow - They know their codebase and requirements better than you do
What NOT to do:
- Create helper scripts without being asked
- Add complex setup procedures when simple ones exist
- Generate documentation for features that don't exist yet
- Modify files beyond what was specifically requested
- Add "best practices" that weren't requested
What TO do:
- Answer the specific question asked
- Make only the changes explicitly requested
- Ask for clarification when requirements are unclear
- Keep responses focused and concise
- Respect existing code patterns and structure
Remember: Being helpful means doing exactly what was asked, not what you think might be helpful.
WRITING STYLE GUIDELINES
ALWAYS follow these writing rules for this technical/cyber audience:
DO NOT:
- Use marketing language, boosterism, or sales-y content
- Write verbose explanations or "value propositions"
- Use excessive emojis or excitement
- Create bulleted lists with bold formatting everywhere
- Write like you're selling something
DO:
- Use plain, simple, direct language
- Write for busy technical professionals
- Be concise and to the point
- Focus on facts and functionality
- Remember: technical people get turned off by marketing speak
Remember: This audience wants information, not persuasion. Write documentation like you're talking to a colleague, not a prospect.
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.
- 6d ago First seen · 51 lines · 407 tokens per session scan A 1ab26ee8ec54
no-jumping-ahead is a cursor rule published in the GitHub repository Brad-Edwards/aptl (24 stars, last pushed yesterday), licensed MIT. It adds 407 tokens to every session, about $0.0020 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.
Other cursor rules, from other repositories
shell-tilde-paths
Tilde () path handling in shell commands executed via SSH.
tool-registration-checklist
Checklist for adding or removing agent tools.
agent-config-test-confirmation
Require explicit user approval before running or creating tests that mutate active agent configs.
langchain-workflow-provider-agnostic
Langchain workflow changes must work regardless of model/provider choice.
ui-designer
UI designer rules — theme variables, color usage, no literal hex in app code.
fail-closed-verification
Fail-closed verification protocol — direct validation required; no speculation; mutable data/config protected.