developer-execution

Instructions for an agent that implements one small scheduled development task at a time. It writes code, runs tests, fixes failures, and leaves final task completion to the coordinator.

In plain words
What is it for?
Use it when a task is assigned to implement code, update tests, run the test suite, and return the work for review.
Why use it?
It gives individual coding tasks a consistent path from assignment through testing without mixing them with scheduling decisions.

Skill for Claude CodeCodexCursor

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 skills/budagov-lab/dreamteam/developer-execution
Any agent
npx skills add budagov-lab/DreamTeam --skill developer-execution
Clone the repo
git clone --depth 1 https://github.com/budagov-lab/DreamTeam

Made for: Claude Code, Codex, Cursor.

Per session 41 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 329 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 $0.00041 $0.00329
Opus 5 $0.00020 $0.00164
Sonnet 5 $0.00008 $0.00066
Haiku 4.5 $0.00004 $0.00033

Measured 2d ago against content hash d6cd135dedb4, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

developer-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 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/skills/developer-execution/SKILL.md · 40 lines

What it actually says

Developer Execution

When to Use

  • Scheduler returns a task ID
  • User assigns a specific task to implement
  • Task file has status todo and dependencies are done

Workflow

  1. Get task: Dispatch Terminal subagent → python -m dreamteam get-task [id] → read task content
  2. Verify dependencies: All dependencies must be done
  3. Implement: Write code per task requirements (task is in_progress from run-next)
  4. Test: Dispatch Terminal subagent → run pytest, fix failures
  5. Return: Deliver code. Do NOT mark done — Orchestrator does that after Reviewer + Git-Ops.

Input

  • Task ID (e.g. T001) from Orchestrator
  • Architecture excerpt

Output

  • Code changes
  • Test updates
  • Task remains in_progress until Orchestrator runs update-task done (after Git-Ops)

Rules

  • NO parallelism — One task only.
  • Terminal subagent — Developer dispatches Terminal (mcp_task, shell) for get-task, pytest, build. One command at a time.
  • Check .dreamteam/memory/architecture.md for module ownership
  • Run tests before returning
  • Do NOT run update-task — Orchestrator runs it after Reviewer and Git-Ops
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 · 40 lines · 0 tokens per session scan A d6cd135dedb4

Subscribe to this mod's changes

developer-execution is a skill published in the GitHub repository budagov-lab/DreamTeam (1 stars, last pushed 5mo ago), licensed MIT. It adds 41 tokens to every session and 329 once invoked, about $0.0002 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.

Related

Other skills, from other repositories

ponytail

Native Lean quality bar: no code → reuse → stdlib → platform → installed dep → one line → minimum. Split recovery, neighbor match, types, trust floors. Use when writing app code or when thin ponytail.mdc points here.

kleosr/kleosrules · 53 tokens

redesign-existing-projects

Elaya audit for existing sites/apps that look generic, cheap, or AI-made. Diagnose first, then fix in place (fonts, color, states, layout, motion). Use when Mario says polish, audit, upgrade, or it looks horrible. Product apps apply diagnosis through premium-ui-craft values, not Elaya black/Geist/700ms. Upstream…

kleosr/kleosrules · 92 tokens

122-java-type-design

Use when you need to review, improve, or refactor Java code for type design quality — including establishing clear type hierarchies, applying consistent naming conventions, eliminating primitive obsession with domain-specific value objects, leveraging generic type parameters, creating type-safe wrappers, designing…

jabrena/cursor-rules-examples · 91 tokens

testing

Test writing workflows: TDD order, mocks, house gauntlet, regression naming. Use when writing/editing tests or when testing.mdc globs match. Thin rule = roofs; this skill = procedure.

kleosr/kleosrules · 45 tokens

032-architecture-adr-non-functional-requirements

Facilitates conversational discovery to create Architectural Decision Records (ADRs) for non-functional requirements using the ISO/IEC 25010:2023 quality model. Use when the user wants to document quality attributes, NFR decisions, security/performance/scalability architecture, or design systems with measurable…

jabrena/cursor-rules-examples · 81 tokens

124-java-secure-coding

Use when you need to apply Java secure coding best practices — including validating untrusted inputs, defending against injection attacks with parameterized queries, minimizing attack surface via least privilege, applying strong cryptographic algorithms, handling exceptions securely without exposing sensitive data…

jabrena/cursor-rules-examples · 80 tokens