claude-sdk-rs: Command for Claude Code

.claude/commands/update-task.md

update-task is a command for Claude Code from bredmond1019/claude-sdk-rs. It costs 0 tokens per session (1,278 once invoked), scanned A, original, Apache-2.0.

A task-progress command that marks a step complete and appends a note to a project's amendment log. It can find the current project specification automatically or accept one explicitly.

In plain words
What is it for?
Use it to finish a numbered task, record an update, or document an amendment while work is in progress.
Why use it?
It keeps task status and changes to the plan recorded together instead of relying on informal notes. It also supports adding an investigation note without marking a step complete.

Command for Claude Code

Written for Claude Code: $ARGUMENTS substitution. Also seen: mentions subagents.

This is bredmond1019/claude-sdk-rs's own configuration. It tells Claude Code how to work on claude-sdk-rs itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything claude-sdk-rs configures →

Reuse

Borrowing it

Nothing to install: this file belongs to bredmond1019/claude-sdk-rs. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/bredmond1019/claude-sdk-rs/main/.claude/commands/update-task.md
Clone the repo
git clone --depth 1 https://github.com/bredmond1019/claude-sdk-rs

Made for: Claude Code.

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 update-task

README.md
[![agentmods](https://agentmods.dev/badge/commands/bredmond1019/claude-sdk-rs/update-task/github.svg)](https://agentmods.dev/commands/bredmond1019/claude-sdk-rs/update-task)
Your own site
<a href="https://agentmods.dev/commands/bredmond1019/claude-sdk-rs/update-task"><img src="https://agentmods.dev/badge/commands/bredmond1019/claude-sdk-rs/update-task/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for update-task

Your own site · 80×15
<a href="https://agentmods.dev/commands/bredmond1019/claude-sdk-rs/update-task"><img src="https://agentmods.dev/badge/commands/bredmond1019/claude-sdk-rs/update-task.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
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 1,278 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.00000 $0.01278
Opus 5.5 $0.00000 $0.00511
Sonnet 5.5 $0.00000 $0.00256
Haiku 4.5 $0.00000 $0.00128

Measured 11d ago against content hash 47afa30cf2e5, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, 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 11d 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.

.claude/commands/update-task.md · 101 lines

How it starts

The opening of the file, as written. The whole thing — 101 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Update Task — Record progress in a task spec.

Variables

$ARGUMENTS — space-separated values in this order:

  1. Target spec identifier, e.g. <spec-slug> (optional — if omitted, auto-detects the current spec from planning/status.md).
  2. Step number to mark done, e.g. 3. Pass 0 to append a note without marking a step.
  3. Note text (everything after the step number) to append to the spec's Amendment Log, in planning/<spec-slug>/amendments.md — a sibling file to tasks.md/tasks.json, never inside tasks.md itself.

Examples: /update-task 3 Finished scaffolding ← auto-detect spec, mark step 3, log amendment /update-task 0 Still investigating the failing edge case ← auto-detect spec, amendment only /update-task <spec-slug> 2 Fixed the retired model id in frontmatter ← explicit spec, mark step 2, log amendment /update-task <spec-slug> 0 Investigating the failing edge case ← explicit spec, amendment only

Execution Model

Run entirely inline. Spawn no subagent. This is a single-file mark-done-and-append-note edit — a subagent round trip adds latency without adding value.

Instructions

  1. Resolve the target spec.

    • If the first token of $ARGUMENTS matches a spec identifier pattern (e.g. <spec-slug>, <spec-slug>), resolve to planning/<name>/tasks.md and verify the file exists. If it does not exist, stop:

      "No spec found at planning//tasks.md — run /generate-tasks <name> to create it."

    • Otherwise (first token is a number or $ARGUMENTS is empty), read planning/status.md to identify the current spec and load it. If no spec exists, say so and stop.
  2. Parse the remaining arguments:

    • Step number: first integer token after the (optional) spec identifier. 0 = note-only.
    • Note text: all remaining text after the step number. May be empty.
  3. Read the task spec.

  4. If a non-zero step number was given, mark that step heading done by prepending [done] to the matching ### <N>. line. If the step is already marked done, report that and skip.

Read the full file on GitHub · 101 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. 11d ago First seen · 101 lines · 0 tokens per session scan A 47afa30cf2e5

Subscribe to this mod's changes

update-task is a command published in the GitHub repository bredmond1019/claude-sdk-rs (23 stars, last pushed 1mo ago), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 1,278 tokens. 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 2026-10-26.

Related

update-task compared with commands from other repositories

update-task next to 6 commands from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
update-taskbredmond1019/claude-sdk-rsCommand231mo agoApache-2.0A0Claude Code
checklistgithub/spec-kitCommand148kyesterdayMITA13Claude Code
clarifygithub/spec-kitCommand148kyesterdayMITA27Claude Code
specifygithub/spec-kitCommand148kyesterdayMITA13Claude Code
analyzegithub/spec-kitCommand148kyesterdayMITA26Claude Code
convergegithub/spec-kitCommand148kyesterdayMITA35Claude Code
implementgithub/spec-kitCommand148kyesterdayMITA14Claude Code