ScalaSemantic: Agent for Claude Code

.claude/agents/task-tree-triage.md

task-tree-triage is an agent for Claude Code from MercurieVV/ScalaSemantic. It costs 54 tokens per session (657 once invoked), scanned A, original, MIT.

A per-issue classifier for breaking GitHub work requests into a task tree, meaning a plan of smaller dependent tasks.

In plain words
What is it for?
Reading one GitHub issue, checking whether it was handled already, and routing it to skipping, direct implementation, or further planning.
Why use it?
It separates simple implementation tasks from issues that need broader planning, while avoiding repeated processing.

Agent for Claude Code

Written for Claude Code: installed under .claude/. Also seen: model in frontmatter; reads .claude/ paths.

This is MercurieVV/ScalaSemantic's own configuration. It tells Claude Code how to work on ScalaSemantic 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 ScalaSemantic configures →

Reuse

Borrowing it

Nothing to install: this file belongs to MercurieVV/ScalaSemantic. 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/MercurieVV/ScalaSemantic/master/.claude/agents/task-tree-triage.md
Clone the repo
git clone --depth 1 https://github.com/MercurieVV/ScalaSemantic

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 task-tree-triage

README.md
[![agentmods](https://agentmods.dev/badge/agents/mercurievv/scalasemantic/task-tree-triage/github.svg)](https://agentmods.dev/agents/mercurievv/scalasemantic/task-tree-triage)
Your own site
<a href="https://agentmods.dev/agents/mercurievv/scalasemantic/task-tree-triage"><img src="https://agentmods.dev/badge/agents/mercurievv/scalasemantic/task-tree-triage/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 task-tree-triage

Your own site · 80×15
<a href="https://agentmods.dev/agents/mercurievv/scalasemantic/task-tree-triage"><img src="https://agentmods.dev/badge/agents/mercurievv/scalasemantic/task-tree-triage.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 54 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 657 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 $0.00054 $0.00657
Opus 5 $0.00027 $0.00329
Sonnet 5 $0.00011 $0.00131
Haiku 4.5 $0.00005 $0.00066

Measured 9d ago against content hash e892f4704797, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

task-tree-triage 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 9d 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/agents/task-tree-triage.md · 70 lines

How it starts

The opening of the file, as written. The whole thing — 70 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are the cheap classifier for the recursive ScalaSemantic task tree. Process exactly ONE GitHub issue. Do not implement code and do not create subtasks.

Input

A GitHub issue number, the current tree depth, and the run limits from .claude/skills/task-splitting-evaluation/SKILL.md.

Marker Rules

An issue is already processed if its body or comments contain:

### Agentic task-tree marker

with Status: leaf-ready, Status: expanded, or Status: skipped.

If already processed, return skip. Do not add another marker.

Steps

  1. Read the issue and comments:
    • gh issue view <N> --comments --json number,title,body,labels,comments
  2. If the task-tree marker already exists, return skip.
  3. Classify the task:
    • leaf-ready: the work is small, concrete, and can be implemented by one worker without a separate planning pass.
    • needs-expansion: the work is broad, ambiguous, cross-cutting, risky, or better represented as multiple dependent subtasks. This outcome must be handed to the smartest available LLM/model for planning.
    • skip: the task is already described well enough and already has a clear executor/model assignment, even if it lacks the task-tree marker.
  4. For leaf-ready, select the preferred executor engine/model from .claude/orchestrate-routing.md.
  5. For needs-expansion, say why the smartest available LLM/model is justified for planning.

Leaf Criteria

Prefer leaf-ready when all are true:

  • The deliverable is one coherent implementation unit.
  • The touched area is narrow or obvious.
  • A worker can act from the issue plus one concise comment.
  • Tests/checks are predictable.
  • The task does not need more than one dependent implementation step.

Prefer needs-expansion when any are true:

  • Multiple modules or APIs must change in sequence.
  • The issue mixes design, implementation, tests, docs, migration, or compatibility work.
  • There are natural dependencies between parts of the work.
  • The issue is too vague for direct execution.
  • A smart model should decide step boundaries before implementation.

Read the full file on GitHub · 70 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. 9d ago First seen · 70 lines · 54 tokens per session scan A e892f4704797

Subscribe to this mod's changes

task-tree-triage is an agent published in the GitHub repository MercurieVV/ScalaSemantic (21 stars, last pushed yesterday), licensed MIT. It adds 54 tokens to every session and 657 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 2026-08-30.

Related

Other agents, from other repositories

product-manager

Product requirements, user stories, roadmaps, prioritization frameworks, and sprint planning specialist. Use when writing PRDs, defining user stories, planning sprints, or making product decisions. Trigger phrases: PRD, user story, roadmap, sprint, backlog, prioritization, product requirements, acceptance criteria…

travisjneuman/.claude · 71 tokens

Project Manager Agent

Meta-layer agent that orchestrates specialists and manages project knowledge.

Fujigo-Software/f5-framework-claude · 15 tokens

project-orchestrator

Comprehensive project tracking and management agent for technical and non-technical work. Analyzes current status, tracks progress across research and implementation, monitors roadmap position, and provides actionable project insights with clear next steps.

manutej/luxor-claude-marketplace · 47 tokens

Task Manager

Goal-oriented agent for managing tasks, priorities, and project execution.

DollhouseMCP/collection · 15 tokens

cto-advisor

A CTO advisor who makes strategic technology decisions — evaluating build-vs-buy at the org level, setting technical vision, managing engineering investment, and navigating technology transitions. Use for technology strategy, engineering org design, technical due diligence, and vendor evaluation.

The-AI-Directory-Company/agents-and-skills · 53 tokens

product-operations

A product operations specialist who designs the systems behind product development — feature rollout processes, experiment operations, internal tooling, and cross-functional workflows. Use for feature flagging strategy, experiment ops, process automation, and operational efficiency.

The-AI-Directory-Company/agents-and-skills · 48 tokens