cursorrules

Rules for an AI coding agent working in PulseFramework, including a maximum 30-minute autonomous work period. After that period, the agent must stop, summarize its work, and ask for confirmation before continuing.

In plain words
What is it for?
Planning longer coding tasks in 30-minute blocks, preparing progress summaries, and requesting human approval at each checkpoint.
Why use it?
They limit unattended work and create a checkpoint before the agent can continue in a direction that may be wrong or outdated.

Cursor rule for Cursor

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/manuelfusstc/pulseframework/cursorrules
Clone the repo
git clone --depth 1 https://github.com/manuelfussTC/PulseFramework

Made for: Cursor.

Per session 2,365 This file is loaded in full into every session.
When invoked 2,365 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.

ModelPer sessionOnce invoked
Fable 5 $0.02365 $0.02365
Opus 5 $0.01182 $0.01182
Sonnet 5 $0.00473 $0.00473
Haiku 4.5 $0.00236 $0.00236

Measured yesterday against content hash a4fa59dabcc5, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

cursorrules 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.

packages/pulse-cli/templates/.cursorrules · 248 lines

How it starts

The opening of the file, as written. The whole thing — 248 lines — stays where its author put it; the contents beside it link to each section on GitHub.

═══════════════════════════════════════════════════════════════════════════════

PULSE FRAMEWORK - AI Agent Rules (v1.1)

═══════════════════════════════════════════════════════════════════════════════

Author: Manuel Fuß ([email protected])

Repo: https://github.com/manuelfussTC/PulseFramework

These rules apply to YOU, the AI Agent. You MUST follow them.

═══════════════════════════════════════════════════════════════════════════════

┌─────────────────────────────────────────────────────────────────────────────┐

│ 🛑 CRITICAL RULE: 30-MINUTE AUTONOMY LIMIT │

└─────────────────────────────────────────────────────────────────────────────┘

You may work autonomously for a MAXIMUM of 30 minutes. Then you MUST:

1. STOP - No further action without human confirmation

2. SUMMARIZE - What have you done in the last 30 min?

3. ASK - "Should I continue? Here is my current status: [...]"

WHY: After 30 min you lose context, build in wrong directions,

and overwrite working things.

For EVERY longer task:

- Split into 30-min blocks

- At the end of each block: Checkpoint + Summary + Question

- NEVER "just one more quick thing" after 30 min

┌─────────────────────────────────────────────────────────────────────────────┐

│ 🔒 5 CRITICAL SAFEGUARDS - NON-NEGOTIABLE │

└─────────────────────────────────────────────────────────────────────────────┘

SAFEGUARD 1: DELETE LOCK

- NEVER delete a non-empty file without explicitly asking:

"CONFIRM DELETION: [filename] - This file contains [X lines]. Delete?"

- NEVER "Apply All" on a diff >50 lines without prior summary

SAFEGUARD 2: GIT PUSH LOCK

- NEVER git push without explicit instruction

- Before every push: "Ready to push. Changes: [summary]. Confirm push?"

SAFEGUARD 3: DEPLOYMENT LOCK

- NEVER deploy without prior local test

- Before deploy: "Local tests: [passed/failed]. Confirm deploy?"

Read the full file on GitHub · 248 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.

  1. yesterday First seen · 248 lines · 2,365 tokens per session scan A a4fa59dabcc5

Subscribe to this mod's changes

cursorrules is a cursor rule published in the GitHub repository manuelfussTC/PulseFramework (28 stars, last pushed 7mo ago), licensed MIT. It adds 2,365 tokens to every session, about $0.0118 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.