update

A command that compares an updated specification with an existing task list and revises the list. A task list tracks project requirements, statuses, dependencies, and work phases.

In plain words
What is it for?
Use it to update task descriptions, add new tasks, preserve task statuses, recalculate dependencies, and update task-list metadata from a specification document.
Why use it?
It keeps project tasks aligned with changing requirements while preserving completed work and marking removed requirements as obsolete.

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/update
Clone the repo
git clone --depth 1 https://github.com/sequenzia/claude-plugins
Per session 9 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 519 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 $0.00009 $0.00519
Opus 5 $0.00005 $0.00260
Sonnet 5 $0.00002 $0.00104
Haiku 4.5 $0.00001 $0.00052

Measured yesterday against content hash 2293b5373c09, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

update 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/update.md · 83 lines

What it actually says

Re-analyze the specification document and update the existing task list with changes.

Input document: @$1

Process

  1. Locate existing task list

    • If project name provided ($2): Read tasks/$2.tasks.json
    • Otherwise: Derive project name from spec filename
  2. Read current task list

    • Load existing tasks with their current statuses
    • Note which tasks are complete, in_progress, or blocked
  3. Re-analyze the specification

    • Parse the updated specification document
    • Extract all current requirements
  4. Compare and reconcile

    For each requirement in the updated spec:

    • Unchanged: Keep existing task, preserve status
    • Modified: Update task description/criteria, preserve status if in_progress
    • New: Create new task with stable ID

    For existing tasks not in updated spec:

    • Mark as "obsolete" (don't delete - preserve history)
  5. Recalculate dependencies

    • Update dependency graph for any structural changes
    • Recalculate blocked_by for all non-complete tasks
    • Rebuild execution phases
  6. Update metadata

    • Increment version (minor bump for structural changes)
    • Update last_updated timestamp
    • Recalculate total_tasks and completion_percentage
  7. Write updated task file

    • Backup previous version (rename to .tasks.json.bak)
    • Write new task list
  8. Display change summary

Format output as:

## Task List Updated: <project-name>

**Version:** <old> -> <new>

### Changes Summary
- **New tasks:** X
- **Modified tasks:** Y
- **Obsolete tasks:** Z
- **Unchanged tasks:** W

### New Tasks Added
- TASK-XXX: <title> (priority, complexity)
- TASK-YYY: <title> (priority, complexity)

### Tasks Marked Obsolete
- TASK-ZZZ: <title> (was: status)

### Modified Tasks
- TASK-AAA: <change description>

### Progress Impact
- Completion: X% -> Y%
- Total tasks: A -> B

### Next Actions
Run `/spec-task-manager:next` to see recommended tasks.

If this is a significant restructuring, warn about potential workflow disruption.

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 · 83 lines · 9 tokens per session scan A 2293b5373c09

Subscribe to this mod's changes

update is a command published in the GitHub repository sequenzia/claude-plugins (2 stars, last pushed 7mo ago), licensed MIT. It adds 9 tokens to every session and 519 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.