show-group

A command that displays the tasks, dependencies, progress, and status of one context group. A context group is a batch of related tasks prepared for an AI coding agent.

In plain words
What is it for?
Use it with a group ID to inspect its tasks, completion percentage, dependencies, and blocked or unfinished work.
Why use it?
It makes it easier to see what a group contains and what remains before work continues.

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/sequenzia/claude-plugins/show-group
Clone the repo
git clone --depth 1 https://github.com/sequenzia/claude-plugins
Per session 8 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,487 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 $0.00008 $0.01487
Opus 5 $0.00004 $0.00744
Sonnet 5 $0.00002 $0.00297
Haiku 4.5 $0.00001 $0.00149

Measured 2d ago against content hash 9f7945625327, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

show-group 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.

plugins/task-manager/commands/show-group.md · 226 lines

How it starts

The opening of the file, as written. The whole thing — 226 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Show detailed information about a specific context group, including all tasks, dependencies, and progress.

Process

  1. Parse arguments

    • $1 = Group ID (required, e.g., "CG-001")
    • $2 = Project name (optional)
  2. Validate arguments

    • Group ID must match pattern CG-XXX
    • If invalid, show usage help
  3. 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
  4. Find the requested context group

    • Search context_groups array for matching ID
    • If not found, list available groups
  5. Gather task details

    • For each task in the group, collect full task information
    • Calculate completion status
    • Identify dependencies within and outside the group
  6. Display group details

Format output as:

## Context Group: CG-001

**Status:** active
**Estimated Tokens:** 72,000 / 80,000 effective limit
**Phases Covered:** 1, 2

### Progress
- **Completed:** 2 of 5 tasks (40%)
- **In Progress:** 1 task
- **Blocked:** 0 tasks
- **Not Started:** 2 tasks

---

### Tasks

#### TASK-001: Initialize project structure [COMPLETE]
- **Priority:** high | **Complexity:** S | **Tokens:** 1,700
- **Description:** Set up the base project directory structure and configuration files
- **Acceptance Criteria:**
  - [x] Directory structure created
  - [x] package.json configured
  - [x] TypeScript config in place

---

#### TASK-002: Setup database schema [COMPLETE]
- **Priority:** high | **Complexity:** M | **Tokens:** 4,200
- **Dependencies:** TASK-001 (complete)
- **Description:** Define database tables and relationships
- **Acceptance Criteria:**
  - [x] User table created
  - [x] Session table created
  - [x] Migrations written

---

#### TASK-003: Implement user model [IN PROGRESS]
- **Priority:** high | **Complexity:** M | **Tokens:** 4,200
- **Dependencies:** TASK-002 (complete)
- **Description:** Create the User model with CRUD operations
- **Acceptance Criteria:**
  - [ ] User class implemented
  - [ ] Validation logic added
  - [ ] Unit tests passing

---

#### TASK-004: Create authentication service [NOT STARTED]
- **Priority:** critical | **Complexity:** L | **Tokens:** 10,200
- **Dependencies:** TASK-003 (in progress)
- **Blocked By:** TASK-003
- **Description:** Implement authentication logic with JWT
- **Acceptance Criteria:**
  - [ ] Login endpoint working
  - [ ] Token generation implemented
  - [ ] Token validation middleware

---

#### TASK-005: Add password hashing [NOT STARTED]
- **Priority:** high | **Complexity:** S | **Tokens:** 1,700
- **Dependencies:** TASK-001 (complete)
- **Description:** Implement secure password hashing utility
- **Acceptance Criteria:**
  - [ ] bcrypt integration
  - [ ] Hash and verify functions
  - [ ] Salt rounds configurable

---

### Dependency Graph (This Group)

TASK-001 (complete) ├── TASK-002 (complete) │ └── TASK-003 (in_progress) │ └── TASK-004 (blocked) └── TASK-005 (not_started)


### External Dependencies
- **From Previous Groups:** None
- **For Next Groups:**
  - CG-002 depends on: TASK-003, TASK-004

### Token Breakdown

| Task | Base | Overhead | Total |
|------|------|----------|-------|
| TASK-001 | 1,500 | 200 | 1,700 |
| TASK-002 | 4,000 | 200 | 4,200 |
| TASK-003 | 4,000 | 200 | 4,200 |
| TASK-004 | 10,000 | 200 | 10,200 |
| TASK-005 | 1,500 | 200 | 1,700 |
| **Total** | | | **22,000** |

---

### Ready to Start Now
Tasks with all dependencies satisfied:
- **TASK-005:** Add password hashing (high, S)

### Blocked Tasks
- **TASK-004:** Waiting on TASK-003

---

**Commands:**
- Mark complete: `/task-manager:complete TASK-XXX`
- Update task: `/task-manager:update TASK-XXX --status in_progress`
- See all groups: `/task-manager:status`

Read the full file on GitHub · 226 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. 2d ago First seen · 226 lines · 8 tokens per session scan A 9f7945625327

Subscribe to this mod's changes

show-group is a command published in the GitHub repository sequenzia/claude-plugins (2 stars, last pushed 7mo ago), licensed MIT. It adds 8 tokens to every session and 1,487 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.