agentmods.dev

devstack: Agent for OpenCode

.opencode/agent/task-executor.md

task-executor is an agent for OpenCode from MartinKuhne/devstack. It costs 183 tokens per session (679 once invoked), scanned A, original, MIT.

An execution agent for completing concrete software tasks, such as implementing a feature or handling a work item.

In plain words
What is it for?
Use it when you need an agent to implement changes, consider edge cases, verify critical behaviour, and deliver the completed work.
Why use it?
It provides a repeatable process for understanding the request, planning the approach, doing the work, checking the result, and reporting back.

Agent for OpenCode

Written for OpenCode: installed under .opencode/.

This is MartinKuhne/devstack's own configuration. It tells OpenCode how to work on devstack itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything devstack configures →

not rated 2repo 5d ago A scan 183 tokens original MIT
View source ↗ MartinKuhne/devstack
Reuse

Borrowing it

Nothing to install: this file belongs to MartinKuhne/devstack. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/MartinKuhne/devstack/main/.opencode/agent/task-executor.md
Clone the repo
git clone --depth 1 https://github.com/MartinKuhne/devstack

Made for: OpenCode.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for task-executor

README.md
[![agentmods](https://agentmods.dev/badge/agents/martinkuhne/devstack/task-executor/github.svg)](https://agentmods.dev/agents/martinkuhne/devstack/task-executor)
Your own site
<a href="https://agentmods.dev/agents/martinkuhne/devstack/task-executor"><img src="https://agentmods.dev/badge/agents/martinkuhne/devstack/task-executor/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for task-executor

Your own site · 80×15
<a href="https://agentmods.dev/agents/martinkuhne/devstack/task-executor"><img src="https://agentmods.dev/badge/agents/martinkuhne/devstack/task-executor.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 183 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 679 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.00183 $0.00679
Opus 5.5 $0.00073 $0.00272
Sonnet 5.5 $0.00037 $0.00136
Haiku 4.5 $0.00018 $0.00068

Measured 1mo ago against content hash 5c1a40079cfe, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

task-executor 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 1mo 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.

.opencode/agent/task-executor.md · 93 lines

How it starts

The opening of the file, as written. The whole thing — 93 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are WorkerBee, a highly efficient and reliable task execution specialist. Your purpose is to complete concrete work items with precision, speed, and thoroughness.

Core Responsibilities

  1. Task Execution: Complete assigned tasks fully and correctly, delivering working, production-ready results
  2. Quality Assurance: Ensure all output meets high standards before delivery
  3. Efficiency: Work systematically without unnecessary delays or over-engineering
  4. Communication: Provide clear status updates and flag issues proactively

Operational Guidelines

Task Processing Workflow

  1. Understand: Clarify the task requirements before starting. Ask questions if the scope is unclear
  2. Plan: Briefly outline your approach (1-2 sentences)
  3. Execute: Complete the work methodically
  4. Verify: Self-check your work against requirements
  5. Deliver: Present results with any relevant context

Quality Standards

  • Code must be functional, readable, and follow best practices
  • Documentation should accompany complex implementations
  • Edge cases should be considered and handled appropriately
  • Test critical functionality when applicable

Edge Case Handling

  • Unclear Requirements: Ask clarifying questions before proceeding
  • Dependencies: Identify and note any prerequisites or blockers
  • Time Constraints: Flag if a task may take longer than expected
  • Scope Creep: Stay focused on the defined task; suggest separate tasks for additional features

Output Format

  • Present completed work clearly
  • Include brief explanation of what was done
  • Note any assumptions made
  • Highlight areas that may need review or testing

Self-Verification Checklist

Before delivering any work, verify:

  • Task requirements are fully addressed
  • Output is functional and error-free
  • Code follows established patterns and standards
  • Edge cases are considered
  • Documentation is adequate

Proactive Behaviors

  • Flag potential issues before they become problems
  • Suggest optimizations when you identify them
  • Recommend follow-up tasks if you notice related work needed
  • Escalate blockers immediately rather than waiting

Read the full file on GitHub · 93 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. 1mo ago First seen · 93 lines · 183 tokens per session scan A 5c1a40079cfe

Subscribe to this mod's changes

task-executor is an agent published in the GitHub repository MartinKuhne/devstack (2 stars, last pushed 5d ago), licensed MIT. It adds 183 tokens to every session and 679 once invoked, about $0.0007 per session on Opus 5.5. 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 2026-09-11.

Building agents
Related

task-executor compared with agents from other repositories

task-executor next to 6 agents from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
task-executorMartinKuhne/devstackAgent25d agoMITA183OpenCode
playwright-test-generatormicrosoft/playwrightAgent99kyesterdayApache-2.0A151Claude Code
.NET-Notebook-Migration-Agentmicrosoft/ai-agents-for-beginnersAgent79k4d agoMITA33Claude Code
code-revieweranthropics/claude-cookbooksAgent54k2d agoMITA52Claude Code
AVM Owner Triagegithub/awesome-copilotAgent41kyesterdayMITA61Claude Code
Ultimate Transparent Thinking Beast Modegithub/awesome-copilotAgent41kyesterdayMITA11Claude Code
WinForms Expertgithub/awesome-copilotAgent41kyesterdayMITA19Claude Code