workflow

Rules for managing project plans, tasks, decisions, and open questions, including where these files belong and how they should be updated.

In plain words
What is it for?
Use them when editing project-management files and tracking unresolved questions, research, decisions, and implementation tasks.
Why use it?
They prevent planning records from becoming inconsistent, such as by reusing question numbers or losing the history of decisions.

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/hlalljie/agent-workflow-presets/workflow
Clone the repo
git clone --depth 1 https://github.com/hlalljie/agent-workflow-presets

Made for: Cursor.

Per session 0 Nothing until a file matches its globs; then the whole rule loads.
When invoked 869 The whole file, excluding the scripts and references it only reads on demand.
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 $0.00000 $0.00869
Opus 5 $0.00000 $0.00434
Sonnet 5 $0.00000 $0.00174
Haiku 4.5 $0.00000 $0.00087

Measured 2d ago against content hash e2c2a434e1ac, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

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 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/workflow.mdc · 63 lines

How it starts

The opening of the file, as written. The whole thing — 63 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Open questions

Each plan folder has its own open-questions.md. Numbers are scoped to that file (each file starts at 1). Numbers are permanent within their file — never renumber, never reuse.

Format: - [ ] N. Short description. Context/links inline.

Adding: pick next unused number in that file. One line with - [ ]. If it needs research, create a research doc and link it.

Resolving: check the box (- [x]). Record in that plan's decisions.md. Update the plan to reflect the decision — remove blocker references, update any sections that were pending this answer. Removing lines from this file after resolution is handled by the /commit flow (commit skill, "After committing") — not here.

Questions can be "parked" or "future" inline if not blocking anything now.

Reference from other docs within the same plan: "blocked by open question 2." Cross-plan references: "blocked by project open question 2" or "blocked by meta open question 6."

Research docs

Research is standalone. It does not contain status markers, links to open questions, or links to plans. Other docs link to research; research links to nothing upstream.

Executing tasks

Normative scope for how many tasks to touch lives in task-scope.mdc (alwaysApply: true). This section is the plan-format companion.

  • One task at a time. Complete it, commit, and stop for verification before starting the next.
  • Batch: only when task-scope.mdc allows it (explicit multiple task numbers in one message, or batchable: true on the task file's first line and the user asked to batch in that message).
  • When delegating to subagents: the prompt must enforce this cadence. Tell the agent to do one task, commit, and return. Do not tell it to "implement all tasks."
  • Spawn implementation subagents using [MODEL:coder]. See agent-models.mdc for all role assignments.

When a task completes

  1. Check task box.
  2. If it resolves an open question: check that box too, update decisions.
  3. If it changes plan scope: update the plan.
  4. Otherwise just check and move on.

Read the full file on GitHub · 63 lines

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 · 63 lines · 0 tokens per session scan A e2c2a434e1ac

Subscribe to this mod's changes

workflow is a cursor rule published in the GitHub repository hlalljie/agent-workflow-presets (2 stars, last pushed 1mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 869 tokens. 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.