task-implementer

task-implementer is a skill for Claude Code, Codex from mkmeral/containerized-strands-agents. It costs 37 tokens per session (4,741 once invoked), scanned A, original, MIT.

A workflow for implementing tasks described in GitHub issues using test-driven development, which means writing tests as part of guiding the code change. It covers repository setup, implementation, documentation, and review.

In plain words
What is it for?
Use it to inspect project guidance, implement a GitHub issue, create tests and documentation, check GitHub write permissions, prepare a pull request, and respond to review feedback.
Why use it?
It gives developers a repeatable process for turning an issue into a tested change while following the repository's existing patterns and instructions.

Skill for Claude CodeCodex

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/mkmeral/containerized-strands-agents/task-implementer
Any agent
npx skills add mkmeral/containerized-strands-agents --skill task-implementer
Clone the repo
git clone --depth 1 https://github.com/mkmeral/containerized-strands-agents

Made for: Claude Code, Codex.

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-implementer

README.md
[![agentmods](https://agentmods.dev/badge/skills/mkmeral/containerized-strands-agents/task-implementer.svg)](https://agentmods.dev/skills/mkmeral/containerized-strands-agents/task-implementer)
Your own site
<a href="https://agentmods.dev/skills/mkmeral/containerized-strands-agents/task-implementer"><img src="https://agentmods.dev/badge/skills/mkmeral/containerized-strands-agents/task-implementer.svg" alt="Measured on agentmods" height="20"></a>
Per session 37 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 4,741 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 $0.00037 $0.04741
Opus 5 $0.00018 $0.02371
Sonnet 5 $0.00007 $0.00948
Haiku 4.5 $0.00004 $0.00474

Measured 3d ago against content hash f30e7d302ce4, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

task-implementer 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 3d 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.

skills/task-implementer/SKILL.md · 416 lines

How it starts

The opening of the file, as written. The whole thing — 416 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Task Implementer SOP

Role

You are a Task Implementer, and your goal is to implement a task defined in a GitHub issue. You will write code using test-driven development principles, following a structured Explore, Plan, Code, Commit workflow. During your implementation, you will write code that follows existing patterns, create comprehensive documentation, generate test cases, create pull requests for review, and iterate on the provided feedback until the pull request is accepted.

Steps

1. Setup Task Environment

Initialize the task environment and discover repository instruction files.

Constraints:

  • You MUST create a progress notebook to track script execution using markdown checklists, setup notes, and implementation progress
  • You MUST check for environment setup instructions in the following locations:
    • AGENTS.md
    • DEVELOPMENT.md
    • CONTRIBUTING.md
    • README.md
  • You MAY explore more files in the repository if you did not find instructions
  • You MUST check the GITHUB_WRITE environment variable value to determine if you have github write permission
    • If the value is true, then you can run git write command like add_comment or run git push
    • If the value is not true, you are running in a read-restricted sandbox. Any write commands you do run will be deferred to run outside the sandbox
      • Any staged or unstaged changes will be pushed after you finish executing to the feature branch
  • You MUST make a note of environment setup and testing instructions
  • You MUST make note of the tasks number from the issue title
  • You MUST make note of the issue number
  • You MUST run unit test to ensure the repository and environment are functional
  • You MAY run integration tests if your feature requires new tests to be added
  • You MUST comment on the github issue if the tests fail, and use the handoff_to_user tool to get feedback on how to continue.
  • You MUST check the current branch using git branch --show-current
  • You MUST create a new feature branch if currently on main branch:
    • You MUST use git checkout -b <BRANCH_NAME> to create and switch to a new feature branch
    • You SHOULD use the BRANCH_NAME pattern agent-tasks/{ISSUE_NUMBER} unless this branch already exists
    • You MUST make note of the newly created branch name
    • You MUST use git push origin <BRANCH_NAME> to create the feature branch in remote
    • If the push operation is deferred, continue with the workflow and note the deferred status
  • You MAY continue on the current branch if not on main branch

Read the full file on GitHub · 416 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. 3d ago First seen · 416 lines · 37 tokens per session scan A f30e7d302ce4

Subscribe to this mod's changes

task-implementer is a skill published in the GitHub repository mkmeral/containerized-strands-agents (3 stars, last pushed 3mo ago), licensed MIT. It adds 37 tokens to every session and 4,741 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.