task-execution

A set of rules for developer agents working on assigned tasks, including reading task details, checking dependencies, implementing changes, and running tests.

In plain words
What is it for?
Use it when implementing a task, checking that prerequisite tasks are finished, documenting blocked work, and verifying the result with tests.
Why use it?
It prevents work from starting too early, keeps task files and their database statuses consistent, and leaves completion reporting to the orchestrator.

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/budagov-lab/dreamteam/task-execution
Clone the repo
git clone --depth 1 https://github.com/budagov-lab/DreamTeam

Made for: Cursor.

Per session 0 Nothing until a file matches its globs; then the whole rule loads.
When invoked 277 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 $0.00277
Opus 5 $0.00000 $0.00138
Sonnet 5 $0.00000 $0.00055
Haiku 4.5 $0.00000 $0.00028

Measured yesterday against content hash 05907c5ff018, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

task-execution 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/task-execution.mdc · 34 lines

What it actually says

Task Execution Rules

When Working on Tasks

  1. Read the full task file before starting.
  2. Verify all dependencies are done in the database.
  3. Task is set to in_progress by run-next when Orchestrator assigns it.
  4. Implement the changes specified in the task.
  5. Run tests and fix any failures.
  6. Do NOT run update-task done — Orchestrator runs it after Reviewer approval and Git-Ops commit. Developer only delivers code.
  7. Run dreamteam verify-tasks periodically to check DB/file consistency.

Task File Structure

Each task file must contain:

  • id — Unique identifier (e.g. T001)
  • title — Short description
  • status — todo | in_progress | done | blocked | deprecated
  • sort_order — optional, integer (lower = earlier in queue)
  • priority — Integer (higher = more urgent)
  • dependencies — List of task IDs that must be done first
  • owner — Optional agent identifier

Blocked Tasks

If a task is blocked, document the reason in the task file and ensure the database status is blocked.

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 · 34 lines · 0 tokens per session scan A 05907c5ff018

Subscribe to this mod's changes

task-execution is a cursor rule published in the GitHub repository budagov-lab/DreamTeam (1 stars, last pushed 5mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 277 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.