A command that exports a project’s task list as JSON, Markdown, or CSV. It reads the selected task file, or the most recently modified one when no project is named.

Use it to create a readable task export for a project, including task statuses and context groups in JSON or Markdown, or task data in CSV.

It saves the work of manually converting task data and preserves progress, context-group, and summary information in the export.

export — Command by sequenzia

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/sequenzia/claude-plugins/export

Clone the repo

git clone --depth 1 https://github.com/sequenzia/claude-plugins

Per session 6 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 948 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.

Model	Per session	Once invoked
Fable 5	$0.00006	$0.00948
Opus 5	$0.00003	$0.00474
Sonnet 5	$0.00001	$0.00190
Haiku 4.5	$0.00001	$0.00095

Measured yesterday against content hash 0b98f79c02e3, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

export 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.

plugins/task-manager/commands/export.md · 141 lines

How it starts

The opening of the file, as written. The whole thing — 141 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Export the task list in the specified format.

Process

Parse arguments
- $1 = Format: json (default), markdown, csv
- $2 = Project name (optional)
Locate and read the task file
- If project name provided: Read tasks/$2.tasks.json
- If no project name: Find most recently modified .tasks.json
Generate export based on format

JSON Format (default)

Write formatted, readable JSON
Include all fields including context_groups array
Include context_group_id, context_group_start, context_group_end on tasks
Include metadata.context_config and metadata.total_context_groups
Output to tasks/<project>.export.json

Markdown Format

Generate human-readable markdown:

# Task List: <project-name>

**Source:** <source_document>
**Generated:** <date>
**Progress:** X% complete

## Summary
- Total: X tasks
- Complete: Y
- In Progress: Z
- Blocked: W
- Not Started: V

## Context Groups (if configured)

**Configuration:**
- Max Tokens: 100,000
- Reserved: 20,000
- Effective Limit: 80,000

| Group | Status | Tasks | Est. Tokens | Phases |
|-------|--------|-------|-------------|--------|
| CG-001 | completed | 5 | 72,000 | 1, 2 |
| CG-002 | active | 4 | 68,500 | 2, 3 |
| CG-003 | pending | 3 | 45,200 | 3 |

### CG-001: Foundation & Setup
- TASK-001: Initialize project structure [complete]
- TASK-002: Setup database schema [complete]
- TASK-003: Configure authentication [complete]
- TASK-004: Create base models [complete]
- TASK-005: Add password hashing [complete]

### CG-002: Core Features (Active)
- TASK-006: Implement login flow [in_progress]
- TASK-007: Add session handling [not_started]
- TASK-008: Create logout endpoint [not_started]
- TASK-009: Add remember me [not_started]

### CG-003: Advanced Features
- TASK-010: Implement OAuth [not_started]
- TASK-011: Add 2FA support [not_started]
- TASK-012: Create password reset [not_started]

## Execution Phases

### Phase 1: Foundation
Tasks with no dependencies.

#### TASK-001: <title>
- **Priority:** high | **Complexity:** M
- **Status:** not_started
- **Context Group:** CG-001

**Description:**
<description>

**Acceptance Criteria:**
- [ ] <criterion 1>
- [ ] <criterion 2>

---

### Phase 2: Core Features
...

Read the full file on GitHub · 141 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.

yesterday First seen · 141 lines · 0 tokens per session scan A 0b98f79c02e3

Subscribe to this mod's changes

export is a command published in the GitHub repository sequenzia/claude-plugins (2 stars, last pushed 7mo ago), licensed MIT. It adds 6 tokens to every session and 948 once invoked, about $0.0000 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.

Documents Planning

export

Getting it into your agent

What it costs to keep this loaded

Grade A, and why

Nothing flagged

How it starts

Process

JSON Format (default)

Markdown Format

What this file has done since we first saw it

Other commands, from other repositories

checklist

clarify

specify

analyze

converge

implement