ccc-tm

ccc-tm is a command for coding agents from KevinZai/commander. It costs 23 tokens per session (542 once invoked), scanned A, original, MIT.

TaskMaster — structured PRD→task decomposition, complexity analysis, and implementation pipeline. Paid tier project planning engine.

Command

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 commands/kevinzai/commander/ccc-tm
Clone the repo
git clone --depth 1 https://github.com/KevinZai/commander

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 ccc-tm

README.md
[![agentmods](https://agentmods.dev/badge/commands/kevinzai/commander/ccc-tm.svg)](https://agentmods.dev/commands/kevinzai/commander/ccc-tm)
Your own site
<a href="https://agentmods.dev/commands/kevinzai/commander/ccc-tm"><img src="https://agentmods.dev/badge/commands/kevinzai/commander/ccc-tm.svg" alt="Measured on agentmods" height="20"></a>
Per session 23 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 542 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin unknown 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 $0.00023 $0.00542
Opus 5 $0.00012 $0.00271
Sonnet 5 $0.00005 $0.00108
Haiku 4.5 $0.00002 $0.00054

Measured today against content hash b190b1a7ea90, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

ccc-tm 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 today.

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.

commands/ccc-tm.md · 60 lines

How it starts

The opening of the file, as written. The whole thing — 60 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/tm — TaskMaster Project Planning

TaskMaster CLI (task-master, v0.43.1) provides structured project planning that complements /plan:

  • /plan = quick planning, 1-3 steps, immediate action
  • /tm = full PRD parse → complexity analysis → task expansion → implementation tracking

When activated:

Check if task-master CLI is available: which task-master If not found: "TaskMaster not installed. Run: npm i -g task-master-ai"

If found, present via AskUserQuestion:

Option What it does
Parse a PRD into tasks (Recommended) Feed a requirements doc → get structured task list with dependencies
Analyze task complexity Score tasks by complexity, identify high-risk items
Expand a task into subtasks Break a large task into implementable pieces
Get next task to work on Find the highest-priority unblocked task
View all tasks List tasks with status, priority, dependencies
Auto-implement tasks Let TaskMaster drive implementation autonomously
Project status Overview of progress, blockers, completion %
Something else Free text

Parse PRD Flow

  1. Ask: "Paste the PRD or describe what you're building"
  2. Run: task-master parse-prd with the input
  3. Show generated tasks with dependencies
  4. Ask: "Want to start implementing? I'll pick the first unblocked task."

Next Task → Paperclip Flow

When user picks "Get next task":

  1. Run: task-master next-task to find highest-priority unblocked task
  2. Display the task with subtasks and dependencies
  3. Ask via AskUserQuestion:
    • "Start building this task (Recommended)" — dispatch to subagent
    • "Create Paperclip issue for this" — POST to Paperclip API at localhost:3110
    • "Skip to next task"
    • "Something else"

Auto-Implement Flow

  1. Run: task-master auto-implement-tasks
  2. Monitor progress, show completion bars
  3. After each task: update status, suggest next

Complexity Analysis

  1. Run: task-master analyze-complexity
  2. Show complexity report with risk scores
  3. Recommend: high-complexity tasks should be broken down first

Read the full file on GitHub · 60 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. today First seen · 60 lines · 23 tokens per session scan A b190b1a7ea90

Subscribe to this mod's changes

ccc-tm is a command published in the GitHub repository KevinZai/commander (6 stars, last pushed today), licensed MIT. It adds 23 tokens to every session and 542 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 2026-09-04.