pulse

Always-on instructions for the PULSE workflow, which requires status checks on every message and additional checks after code changes or extended work.

In plain words
What is it for?
Use them to enforce the listed status, health, checkpoint, correction, escalation, and review steps during an agent session.
Why use it?
They provide a fixed process for tracking work, checking changes, correcting mistakes, and reviewing completed tasks.

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

Made for: Cursor.

Per session 224 This file is loaded in full into every session.
When invoked 224 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 $0.00224 $0.00224
Opus 5 $0.00112 $0.00112
Sonnet 5 $0.00045 $0.00045
Haiku 4.5 $0.00022 $0.00022

Measured 2d ago against content hash 8942032dabbc, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

pulse 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 2d 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.

.cursor/rules/pulse.mdc · 39 lines

What it actually says

🛑 PULSE: Call MCP tools!

EVERY MESSAGE → pulse_status FIRST

CallMcpTool: pulse_status
Arguments: { "userMessage": "<user message>" }

AFTER CODE CHANGES → pulse_doctor

EVERY 10 MIN → pulse_checkpoint

Trigger Tool
Every message pulse_status
After edits pulse_doctor
10+ min work pulse_checkpoint
"wrong"/"stop" pulse_correct
2-3 failures pulse_escalate
Task done pulse_review

NON-NEGOTIABLE

  • ⏱️ MAX 30 min autonomous
  • 🗑️ NO delete without confirmation
  • 📤 NO push without confirmation
  • 🔐 NO secrets in code

DID YOU CALL pulse_status? If not, do it NOW.

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. 2d ago First seen · 39 lines · 224 tokens per session scan A 8942032dabbc

Subscribe to this mod's changes

pulse is a cursor rule published in the GitHub repository manuelfussTC/PulseFramework (28 stars, last pushed 7mo ago), licensed MIT. It adds 224 tokens to every session, about $0.0011 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.