threnody-subtasks

threnody-subtasks is a skill for Claude Code from timjensgrossinger/threnody. It costs 53 tokens per session (608 once invoked), scanned A, original, Apache-2.0.

A task monitor for delegated utility jobs run through Threnody, such as work sent to OpenCode, Aider, or local endpoints.

In plain words
What is it for?
Use it to list, stop, or resume utility subprocesses created by explicit execute_subtask calls.
Why use it?
It helps you see which delegated jobs are active and control them without confusing them with host-native agent groups.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: built for aider; mentions OpenCode.

Part of the threnody plugin — 10 skills, 3 agents shipped together

Good fit Use it to list, stop, or resume utility subprocesses created by explicit execute_subtask calls.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/timjensgrossinger/threnody/threnody-subtasks
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.

Any agent
npx skills add timjensgrossinger/threnody --skill threnody-subtasks
Clone the repo
git clone --depth 1 https://github.com/timjensgrossinger/threnody

Made for: Claude Code.

Or install threnody, the plugin that ships this one along with the rest of its 10 skills, 3 agents.

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 threnody-subtasks

README.md
[![agentmods](https://agentmods.dev/badge/skills/timjensgrossinger/threnody/threnody-subtasks/github.svg)](https://agentmods.dev/skills/timjensgrossinger/threnody/threnody-subtasks)
Your own site
<a href="https://agentmods.dev/skills/timjensgrossinger/threnody/threnody-subtasks"><img src="https://agentmods.dev/badge/skills/timjensgrossinger/threnody/threnody-subtasks/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 threnody-subtasks

Your own site · 80×15
<a href="https://agentmods.dev/skills/timjensgrossinger/threnody/threnody-subtasks"><img src="https://agentmods.dev/badge/skills/timjensgrossinger/threnody/threnody-subtasks.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 53 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 608 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 $0.00053 $0.00608
Opus 5 $0.00026 $0.00304
Sonnet 5 $0.00011 $0.00122
Haiku 4.5 $0.00005 $0.00061

Measured 10d ago against content hash a6d2fb66f328, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

threnody-subtasks 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 10d 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.

skills/threnody-subtasks/SKILL.md · 78 lines

What it actually says

Threnody subtask monitoring

list_subtasks tracks execute_subtask utility delegation only.

Host-native swarms and host_spawn_waves do not appear here — track those by wave completion in the host shell.

Token-cheap review and swarm changes happen on the host-native wave path, not in this utility subprocess monitor. Use this skill only after explicit execute_subtask delegation to utilities.

When to use

  • User enabled providers.delegation_utilities_enabled: true
  • Work was delegated via execute_subtask to OpenCode, Aider, or a local endpoint
  • Need to pause/resume a running utility subprocess

Process

  1. Call list_subtasks (MCP: Threnody).

  2. Format Running Active (active_count total):

For each group in active_groups:

Parallel wave (parallel: true):

WAVE: wave-1  (3 running in parallel)
  - abc123  [low]  gpt-5-mini    12.3s  -> config.py
  - def456  [low]  gpt-5-mini    12.1s  -> models.py

Single task:

abc123  [med]  claude-sonnet-4.6   4.2s  -> main.py

Each row: task_id (first 6 chars), [tier], model or resolving, elapsed seconds, target_file or prompt excerpt (60 chars).

If active_count == 0: No subtasks currently running.

  1. Format Recently Completed (last 10):
abc123  DONE   [low]  gpt-5-mini / Aider  28.1s  -> config.py
def456  FAILED [low]  unknown             31.0s  -> models.py

Group consecutive entries with the same wave_id under a WAVE label.

  1. Footer: X active / Y recent this session

  2. Tip when idle:

For live monitoring, run `threnody-watch` in another terminal tab.

Control

  • stop_subtask(task_id) — pause running utility subprocess
  • resume_subtask(task_id) — resume paused subprocess

Canonical location

Project skill: skills/threnody-subtasks/ in the Threnody repo. Supersedes the personal router-tasks skill (TGs-router naming).

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. 10d ago First seen · 78 lines · 53 tokens per session scan A a6d2fb66f328

Subscribe to this mod's changes

threnody-subtasks is a skill published in the GitHub repository timjensgrossinger/threnody (2 stars, last pushed 13d ago), licensed Apache-2.0. It adds 53 tokens to every session and 608 once invoked, about $0.0003 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.