specify-rules

A set of project rules that tells an agent where to find the active feature specification, plan, research, tasks, and project status. It also describes the current feature pointer and expected confirmation when that pointer is stale.

In plain words
What is it for?
It helps agents gather feature requirements, implementation plans, research, task lists, and shipped-status information for the active project work.
Why use it?
It prevents coding against outdated plans or missing context. It gives the agent a defined set of project documents to read before changing the code.

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/mablanco/pricegrab/specify-rules
Clone the repo
git clone --depth 1 https://github.com/mablanco/pricegrab

Made for: Cursor.

Per session 193 This file is loaded in full into every session.
When invoked 193 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 $0.00193 $0.00193
Opus 5 $0.00097 $0.00097
Sonnet 5 $0.00039 $0.00039
Haiku 4.5 $0.00019 $0.00019

Measured 2d ago against content hash 3e4568ae5f9f, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

specify-rules 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/specify-rules.mdc · 20 lines

What it actually says

For additional context about the active feature, technologies, project structure, shell commands, and other important information:

  1. Read the active feature pointer: .specify/feature.json (currently specs/008-richer-result-card).
  2. Open the active plan: specs/008-richer-result-card/plan.md (and sibling spec.md, research.md, tasks.md).
  3. For shipped state and the product backlog, read docs/project-status.md.

When feature.json is missing or stale after a release, default to the latest specs/<nnn-*>/ directory and confirm with Marco before starting new work.

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 · 20 lines · 193 tokens per session scan A 3e4568ae5f9f

Subscribe to this mod's changes

specify-rules is a cursor rule published in the GitHub repository mablanco/pricegrab (11 stars, last pushed 22d ago), licensed MIT. It adds 193 tokens to every session, about $0.0010 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.