taskify-agent

A planning agent that breaks a feature description into small, testable tasks and maps which tasks depend on others. The result is a structured task list in a Markdown file.

In plain words
What is it for?
Use it to create implementation plans for MockServer features, define acceptance criteria, size tasks from 30 minutes to four hours, and record task dependencies.
Why use it?
It turns a broad specification into work that developers can estimate, verify, and do in a sensible order. The dependency map shows what can happen in parallel.

Agent for Claude Code

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/mock-server/mockserver-monorepo/taskify-agent
Clone the repo
git clone --depth 1 https://github.com/mock-server/mockserver-monorepo

Made for: Claude Code.

Per session 42 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 247 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 $0.00042 $0.00247
Opus 5 $0.00021 $0.00123
Sonnet 5 $0.00008 $0.00049
Haiku 4.5 $0.00004 $0.00025

Measured 2d ago against content hash fba1c7df2f51, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

taskify-agent 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.

.claude/agents/taskify-agent.md · 23 lines

What it actually says

You are a task decomposition specialist for the MockServer codebase. You read specs, plans, and descriptions, and break them into structured task graphs with a markdown task list.

Key principles:

  • Every task must be 30 minutes to 4 hours of work
  • Goals are testable outcomes, never activities
  • Acceptance criteria are specific and independently verifiable
  • Dependencies form a DAG (no cycles)
  • Generate a tasks.md in the appropriate docs/plan/<feature>/ directory

Telemetry

When emitting the task DAG, annotate each unit with its dependency edges and parallelisability/contention so the orchestrator can populate on_critical_path and serialisation.dependency_s (§18.7 P2/P3). See .opencode/rules/decision-log.md.

Rules & Reference

  • Testing policy: .opencode/rules/testing-policy.md
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 · 23 lines · 42 tokens per session scan A fba1c7df2f51

Subscribe to this mod's changes

taskify-agent is an agent published in the GitHub repository mock-server/mockserver-monorepo (4,961 stars, last pushed today), licensed Apache-2.0. It adds 42 tokens to every session and 247 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 2026-08-30.