agent-workflow

A required development process for making changes to the cursor-doctor project.

In plain words
What is it for?
Use it when changing code, commands, configuration, rules, or skills in that project, especially before committing.
Why use it?
It reduces unfinished or broken changes by requiring planning, builds, relevant command checks, tests, and matching documentation updates.

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/ajgreyling/cursor-doctor/agent-workflow
Clone the repo
git clone --depth 1 https://github.com/ajgreyling/cursor-doctor

Made for: Cursor.

Per session 421 This file is loaded in full into every session.
When invoked 421 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 $0.00421 $0.00421
Opus 5 $0.00211 $0.00211
Sonnet 5 $0.00084 $0.00084
Haiku 4.5 $0.00042 $0.00042

Measured yesterday against content hash fea5244f9d2e, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

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.

.cursor/rules/agent-workflow.mdc · 47 lines

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, read as 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 dist or via npx workflow.
    • Documentation/rule/skill changes: regenerate the prescription and verify expected concept detection.

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
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 · 47 lines · 421 tokens per session scan A fea5244f9d2e

Subscribe to this mod's changes

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.