update-task

A command for changing one or many project tasks from natural-language instructions, including their status, priority, dependencies, ownership, and timing.

In plain words
What is it for?
Use it to complete tasks, change priorities, add dependencies, assign owners, update estimates, or apply the same change to matching tasks.
Why use it?
It removes the need to edit task fields separately and checks common problems such as invalid status changes or dependency cycles.

Command 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 commands/asachs01/float-mcp/update-task
Clone the repo
git clone --depth 1 https://github.com/asachs01/float-mcp

Made for: Claude Code.

Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 447 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin 100% copy Near-identical to another mod 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 $0.00000 $0.00447
Opus 5 $0.00000 $0.00224
Sonnet 5 $0.00000 $0.00089
Haiku 4.5 $0.00000 $0.00045

Measured yesterday against content hash f832eb41ad64, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

update-task 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.

Origin

This is a copy

100% identical to update-task — 8 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.

.claude/commands/tm/update/update-task.md · 80 lines

What it actually says

Update tasks with intelligent field detection and bulk operations.

Arguments: $ARGUMENTS

Intelligent Task Updates

Parse arguments to determine update intent and execute smartly.

1. Natural Language Processing

Understand update requests like:

  • "mark 23 as done" → Update status to done
  • "increase priority of 45" → Set priority to high
  • "add dependency on 12 to task 34" → Add dependency
  • "tasks 20-25 need review" → Bulk status update
  • "all API tasks high priority" → Pattern-based update

2. Smart Field Detection

Automatically detect what to update:

  • Status keywords: done, complete, start, pause, review
  • Priority changes: urgent, high, low, deprioritize
  • Dependency updates: depends on, blocks, after
  • Assignment: assign to, owner, responsible
  • Time: estimate, spent, deadline

3. Bulk Operations

Support for multiple task updates:

Examples:
- "complete tasks 12, 15, 18"
- "all pending auth tasks to in-progress"
- "increase priority for tasks blocking 45"
- "defer all documentation tasks"

4. Contextual Validation

Before updating, check:

  • Status transitions are valid
  • Dependencies don't create cycles
  • Priority changes make sense
  • Bulk updates won't break project flow

Show preview:

Update Preview:
─────────────────
Tasks to update: #23, #24, #25
Change: status → in-progress
Impact: Will unblock tasks #30, #31
Warning: Task #24 has unmet dependencies

5. Smart Suggestions

Based on update:

  • Completing task? → Show newly unblocked tasks
  • Changing priority? → Show impact on sprint
  • Adding dependency? → Check for conflicts
  • Bulk update? → Show summary of changes

6. Workflow Integration

After updates:

  • Auto-update dependent task states
  • Trigger status recalculation
  • Update sprint/milestone progress
  • Log changes with context

Result: Flexible, intelligent task updates with safety checks.

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 · 80 lines · 0 tokens per session scan A f832eb41ad64

Subscribe to this mod's changes

update-task is a command published in the GitHub repository asachs01/float-mcp (2 stars, last pushed 6mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 447 tokens. A static security scan graded it A with 0 findings. It is 100% identical to update-task, differing in 8 lines, and is treated as a copy.