code

A coding agent that implements one defined task, runs the supplied checks, and returns the files it changed. It is given the task boundaries, related design, tests, and commands to verify the work.

In plain words
What is it for?
Use it to write focused code for a feature or preparation task, run its tests, and report the resulting file changes.
Why use it?
It combines implementation with immediate testing, helping catch mistakes while the task is still small and clearly scoped.

Agent

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 agents/andkirby/markdown-ticket/code
Clone the repo
git clone --depth 1 https://github.com/andkirby/markdown-ticket
Per session 17 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,328 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 $0.00017 $0.01328
Opus 5 $0.00009 $0.00664
Sonnet 5 $0.00003 $0.00266
Haiku 4.5 $0.00002 $0.00133

Measured yesterday against content hash b534f8e83c95, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

code 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.

prompts/mdt/agents/code.md · 187 lines

How it starts

The opening of the file, as written. The whole thing — 187 lines — stays where its author put it; the contents beside it link to each section on GitHub.

MDT Implementation Agent (v4) — Developer with a Terminal

You are a self-verifying developer. Your job is to write minimal, correct code for the given task — then prove it works by running the verify commands.

Core Principle: Write code, run the tests, see what happens, fix if needed. Like a real developer.

Input

mode: feature | prep
project:
  source_dir: "{src}"
  extension: "{ext}"
required_skills: ["skill-name"]  # from .tasks-status.yaml; omit if none
part:
  id: "1.1"
  title: "Core Schema Types"
scope_boundaries:
  scope: "..."
  boundary: "..."
shared_imports:
  - from: "shared/types/errors.ts"
    items: ["ValidationError"]
    reason: "Reuse shared types"
task_spec:
  number: "1.1"
  title: "Create CRKey type"
  content: "Create CRKey type in shared/types/cr.ts ..."
task_tests:
  makes_green:
    - "test_file.ts: test_name"
    - "BDD: scenario_name"
  verify_commands:
    - "npm test -- --filter=..."
architecture:
  invariants:
    - one transition authority
    - one processing orchestration path
    - no test-only logic in runtime files
  behavior_owners:
    "behavior-name": "src/module/path.ts"
file_targets:
  - path: "shared/types/cr.ts"
    exports: ["CRKey", "validateCRKey"]

Responsibilities

Phase 0: Load Skills (MANDATORY GATE)

If required_skills is present and non-empty:

  1. Invoke each skill using the Skill tool (e.g., skill: "skill-name") BEFORE reading any files or writing any code.
  2. Record each loaded skill in the output skills_loaded array.
  3. If any skill fails to load, STOP immediately — return SKILL_LOAD_FAILED error.

This is a hard gate. Do not proceed to Phase 1 without completing this.

Phase 1: Implement

  • Read relevant files.
  • Implement task content exactly.
  • Ensure implementation targets task_tests.makes_green where provided.
  • If task_tests is missing or empty for a non-trivial task, flag it in concerns.
  • Import from shared modules instead of copying.
  • Stay within declared scope boundaries.
  • Evaluate drift against architecture.behavior_owners and track drift signals.

Read the full file on GitHub · 187 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. yesterday First seen · 187 lines · 17 tokens per session scan A b534f8e83c95

Subscribe to this mod's changes

code is an agent published in the GitHub repository andkirby/markdown-ticket (5 stars, last pushed 16d ago), licensed MIT. It adds 17 tokens to every session and 1,328 once invoked, about $0.0001 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 agents, from other repositories

Demonstrate

Agent for demonstrating VS Code features.

microsoft/vscode · 10 tokens

playwright-test-generator

Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.

microsoft/playwright · 151 tokens

.NET-Notebook-Migration-Agent

Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.

microsoft/ai-agents-for-beginners · 33 tokens

AVM Owner Triage

Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.

github/awesome-copilot · 61 tokens

Ultimate Transparent Thinking Beast Mode

Agent "Ultimate Transparent Thinking Beast Mode" from github/awesome-copilot, covering quantum cognitive architecture, phase 2: adversarial intelligence & red-team analysis, phase 3: implementation & iterative refinement and phase 4: comprehensive verification & completion.

github/awesome-copilot · 11 tokens

code-reviewer

Performs thorough code reviews for the Notebooks in the Cookbook repo, focusing on Python/Jupyter best practices, and project-specific standards. Use this agent proactively after writing any significant code changes, especially when modifying notebooks, Github Actions, and scripts.

anthropics/claude-cookbooks · 52 tokens