Cursor rules for using Pulse, a contract-based process for taking requirements through planning and coding. Cursor is a coding editor, and Pulse uses a project board plus validation and human approval steps.

Running Pulse engagements, submitting structured results, resolving schema errors, requesting decisions on product blockers, claiming board items, and verifying completed work.

It defines who handles each part of the process and prevents work from being treated as finished before the validation gate passes.

cursor — Cursor rule by ashishcloud

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/ashishcloud/agentpulse-pulse/cursor

Clone the repo

git clone --depth 1 https://github.com/ashishcloud/agentpulse-pulse

Per session 20 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 327 The whole file, excluding the scripts and references it only reads on demand.

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.

Model	Per session	Once invoked
Fable 5	$0.00020	$0.00327
Opus 5	$0.00010	$0.00163
Sonnet 5	$0.00004	$0.00065
Haiku 4.5	$0.00002	$0.00033

Measured yesterday against content hash 26107e322b7e, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

cursor 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.

src/adapters/cursor.mdc · 27 lines

What it actually says

Pulse engagement (Cursor)

{ "mcpServers": { "pulse": { "command": "npx", "args": ["pulse-mcp"] } } }

When the user asks to run an engagement, drive the pulse MCP tools — Pulse owns the method + contract + validation; you own the model, the UI, and the human gate:

pulse_start with the requirements.
pulse_next → run each task prompt on your model; fill its JSON schema exactly.
pulse_submit the results. Fix any schemaErrors and resubmit. Surface productBlockers to the user for a decision; do NOT surface autoResolved (architecture points the contract already dictates).
pulse_gate({approved:true, decisions}) only after the user approves. Silence = not approved.
Repeat Stories → Architecture → Build. In Build, implement one board item at a time; pulse_claim it first.
pulse_verify — "done" is the gate command going green, never your judgment.
If .pulse/sync.json is enabled, pulse_sync then reflect the board into the connected PM MCP.

The project board is .pulse/board.json (truth) / .pulse/BOARD.md (view). Never hand-edit BOARD.md.

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.

yesterday First seen · 27 lines · 20 tokens per session scan A 26107e322b7e

Subscribe to this mod's changes

cursor is a cursor rule published in the GitHub repository ashishcloud/agentpulse-pulse (0 stars, last pushed 19d ago), licensed MIT. It adds 20 tokens to every session and 327 once invoked, about $0.0001 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 2026-08-31.

Planning

cursor

Getting it into your agent

What it costs to keep this loaded

Grade A, and why

Nothing flagged

What it actually says

Pulse engagement (Cursor)

What this file has done since we first saw it

Other cursor rules, from other repositories

angular-20

dev-standard

typescript

coolify-ai-docs

python_lib

specs