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.
npx agentmods add rules/ajgreyling/cursor-doctor/agent-workflowgit clone --depth 1 https://github.com/ajgreyling/cursor-doctorWhat 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 | $0.00421 | $0.00421 |
| Opus 5 | $0.00211 | $0.00211 |
| Sonnet 5 | $0.00084 | $0.00084 |
| Haiku 4.5 | $0.00042 | $0.00042 |
Grade A, and why
agent-workflow 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.
What it actually says
Agent Workflow
Planning and clarification
- Ask clarifying questions when scope, acceptance criteria, or implementation approach is ambiguous.
- Prefer small decisions early (scope first, then implementation details) before editing files.
After code/config changes
- Always run a build check:
npm run build. - If command behavior changed, run command-level smoke checks (
generate,audit,readas relevant). - Fix build/runtime issues before considering the task complete.
Testing discipline
- Run relevant validations for touched behavior:
- CLI output/usage changes: run the changed commands in
distor vianpxworkflow. - Documentation/rule/skill changes: regenerate the prescription and verify expected concept detection.
- CLI output/usage changes: run the changed commands in
Documentation update discipline
Reference and update the correct docs in the same change set.
| Document | When to reference | When to update |
|---|---|---|
README.md |
Changing commands, setup, behavior, or release workflow | Any user-facing usage/setup/feature change |
docs/ARCHITECTURE.md |
Changing scanner/analyzer/prescription flow | Any system design/data-flow changes |
docs/DATA_MODEL.md |
Changing types, frontmatter shapes, concept metadata | Any schema/model/type changes |
docs/AGENTS.md |
Changing conventions, paths, or workflows | Any update to rules/skills/locations |
.cursor/rules/*.mdc |
Changing project conventions or expected structure | Rule additions/removals or scope changes |
.cursor/skills/**/SKILL.md |
Changing operational guidance or triggers | Skill behavior or command changes |
Final artifact sync
- Complete the final artifact sync step by reviewing
README.md,docs/,.cursor/rules/, and.cursor/skills/for consistency before finishing.
Completeness checklist
- planning or clarify before implementing
- build and test steps
- when to update which docs
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 · 47 lines · 421 tokens per session scan A fea5244f9d2e
agent-workflow is a cursor rule published in the GitHub repository ajgreyling/cursor-doctor (0 stars, last pushed 27d ago), licensed MIT. It adds 421 tokens to every session, about $0.0021 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.
Other cursor rules, from other repositories
engine-internals
Coding Agent engine implementation details (Cursor + Claude Code) — reference when modifying engine.ts or debugging Agent behavior.
testing-conventions
Testing conventions — must reference when modifying src/ code or tests.
architecture-constraints
GolemBot architecture hard constraints — must check before modifying any src/ code.
app_rules
This document outlines the essential rules and guidelines for developing with the MobileLauncher LT boilerplate. Follow these rules to maintain consistency, scalability, and code quality across the project.
app_feature_first_architecture
Feature-first architecture is a design pattern that organizes code by business features rather than technical layers. This approach promotes better maintainability, scalability, and team collaboration by keeping related functionality together and reducing coupling between different parts of the application.
best_practices
Advanced Best Practices covering Error Handling, Environment Variables, Performance, and Accessibility rules.