agentmods.dev

agent-spec: Cursor rule for Cursor

.cursorrules

cursorrules is a cursor rule for Cursor from ZhangHanDong/agent-spec. It costs 346 tokens per session, scanned A, original, MIT.

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

Written for Cursor: installed under .cursor/.

This is ZhangHanDong/agent-spec's own configuration. It tells Cursor how to work on agent-spec itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything agent-spec configures →

not rated 462repo +2 2mo ago A scan 346 tokens original MIT
View source ↗ ZhangHanDong/agent-spec zhanghandong.github.io
Reuse

Borrowing it

Nothing to install: this file belongs to ZhangHanDong/agent-spec. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/ZhangHanDong/agent-spec/main/.cursorrules
Clone the repo
git clone --depth 1 https://github.com/ZhangHanDong/agent-spec

Made for: Cursor.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for cursorrules

README.md
[![agentmods](https://agentmods.dev/badge/rules/zhanghandong/agent-spec/cursorrules/github.svg)](https://agentmods.dev/rules/zhanghandong/agent-spec/cursorrules)
Your own site
<a href="https://agentmods.dev/rules/zhanghandong/agent-spec/cursorrules"><img src="https://agentmods.dev/badge/rules/zhanghandong/agent-spec/cursorrules/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for cursorrules

Your own site · 80×15
<a href="https://agentmods.dev/rules/zhanghandong/agent-spec/cursorrules"><img src="https://agentmods.dev/badge/rules/zhanghandong/agent-spec/cursorrules.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
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. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.00346 $0.00346
Opus 5.5 $0.00138 $0.00138
Sonnet 5.5 $0.00069 $0.00069
Haiku 4.5 $0.00035 $0.00035

Measured 2mo ago against content hash ca6fe72fbfe9, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, 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 2mo 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.

.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. 2mo ago 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 (462 stars, last pushed 2mo ago), licensed MIT. It adds 346 tokens to every session, about $0.0014 per session on Opus 5.5. 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.

Planningagentai-codingsddspec
Related

cursorrules compared with cursor rules from other repositories

cursorrules next to 6 cursor rules from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
cursorrulesZhangHanDong/agent-specCursor rule4622mo agoMITA346Cursor
ponytailDietrichGebert/ponytailCursor rule185k8d agoMITA604Cursor
angular-20angular/angularCursor rule101kyesterdayMITA0Cursor
dev-standardapache/supersetCursor rule75ktodayApache-2.0A1,147Cursor
prefer-direct-imports-over-module-mocksprisma/ormCursor rule48kyesterdayApache-2.0A0Cursor
config-validation-and-normalizationprisma/ormCursor rule48kyesterdayApache-2.0A0Cursor
control-plane-descriptorsprisma/ormCursor rule48kyesterdayApache-2.0A0Cursor