agentmods.dev

cursorrules

A set of Cursor rules for using agent-spec, a command-line tool that turns task requirements into checkable contracts. It defines a workflow for planning, verifying, reviewing, and retrying coding tasks.

In plain words
What is it for?
Use it to render task contracts, run lifecycle and repository checks, review results, preview Git metadata, and guide fixes without changing the specification.
Why use it?
It keeps implementation aligned with stated requirements and provides evidence when checks fail. It also sets a point where repeated failures should be handed to a person.

Cursor rule for Cursor

447 2d ago A scan 346 tokens original MIT
View the source file ZhangHanDong/agent-spec
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/zhanghandong/agent-spec/cursorrules
Clone the repo
git clone --depth 1 https://github.com/ZhangHanDong/agent-spec

Made for: Cursor.

Per session 346 This file is loaded in full into every session.
When invoked 346 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 $0.00346 $0.00346
Opus 5 $0.00173 $0.00173
Sonnet 5 $0.00069 $0.00069
Haiku 4.5 $0.00035 $0.00035

Measured yesterday against content hash ca6fe72fbfe9, 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.

.cursorrules · 35 lines

What it actually says

agent-spec Integration for Cursor

Workflow

  1. Read the contract: agent-spec contract specs/<task>.spec
  2. Implement against the contract's Intent, Decisions, and Boundaries
  3. Verify: agent-spec lifecycle specs/<task>.spec --code . --format json
  4. Guard: agent-spec guard --spec-dir specs --code .
  5. Review: agent-spec explain specs/<task>.spec --code . --format markdown

Key Commands

  • agent-spec contract <spec> — render the Task Contract for planning
  • agent-spec lifecycle <spec> --code <dir> — full lint + verify pipeline
  • agent-spec guard --spec-dir specs --code . — repo-wide pre-commit check
  • agent-spec explain <spec> — human-readable contract review summary
  • agent-spec stamp <spec> --dry-run — preview git trailers

Retry Protocol

When lifecycle fails:

  1. Parse JSON output, find each scenario's verdict and evidence
  2. For fail: read evidence, fix code
  3. For skip: check Test: selector matches a real test name
  4. Fix code based on evidence. Do NOT modify the spec file.
  5. Re-run lifecycle
  6. After 3 consecutive failures on the same scenario, escalate to the human

Conventions

  • Task specs live in specs/
  • Verdicts: pass, fail, skip, uncertain — all four are distinct
  • skip ≠ pass: skipped scenarios block the pipeline
  • Exception scenarios should be >= happy path scenarios
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 · 35 lines · 346 tokens per session scan A ca6fe72fbfe9

Subscribe to this mod's changes

cursorrules is a cursor rule published in the GitHub repository ZhangHanDong/agent-spec (447 stars, last pushed 2d ago), licensed MIT. It adds 346 tokens to every session, about $0.0017 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.

Code reviewGit and workflowPlanningagentai-codingsddspec
Related

Other cursor rules, from other repositories

angular-20

This rule provides comprehensive best practices and coding standards for Angular development, focusing on modern TypeScript, standalone components, signals, and performance optimizations.

angular/angular · 0 tokens

dev-standard

Apache Superset development standards and guidelines for Cursor IDE.

apache/superset · 1,147 tokens

typescript

Changes to these high-fan-out internals can affect every message, delta, element, or rerun. Keep work in them minimal, and benchmark changes with representative stress-test apps.

streamlit/streamlit · 4,669 tokens

coolify-ai-docs

Master reference to all Coolify AI documentation in .ai/ directory.

coollabsio/coolify · 1,426 tokens

python_lib

Tips and guidelines specific to the development of the Streamlit Python library, not applicable to scripts and e2e tests.

streamlit/streamlit · 0 tokens

specs

This directory contains product and tech specs for Streamlit features.

streamlit/streamlit · 0 tokens