ScalaSemantic: Skill for Claude Code

.claude/skills/orchestrate/SKILL.md

orchestrate is a skill for Claude Code from MercurieVV/ScalaSemantic. It costs 101 tokens per session (4,259 once invoked), scanned A, original, MIT.

A coordinator for coding tasks stored as GitHub issues, arranged in a task tree. It assigns workers to branches of the tree and tracks each task's progress.

In plain words
What is it for?
Use it to plan and run large coding efforts across multiple agents, including tasks that depend on other tasks.
Why use it?
It removes the need to manually split work, manage task dependencies, and follow up on each worker's status.

Skill for Claude Code

Written for Claude Code: installed under .claude/. Also seen: mentions Codex.

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/skills/orchestrate/SKILL.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 orchestrate

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

Your own site · 80×15
<a href="https://agentmods.dev/skills/mercurievv/scalasemantic/orchestrate"><img src="https://agentmods.dev/badge/skills/mercurievv/scalasemantic/orchestrate.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 101 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 4,259 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. Third-party audits
  • NVIDIA SkillSpector warn 7 Sept 2026
SkillSpector: 1 finding, up to medium

These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →

  • medium Excessive Agency · line 350
    Skill allows unbounded resource consumption (API calls, storage, compute). Without rate limits or quotas, a compromised or misbehaving agent can cause denial-of-service or cost overruns.
    Fix: Set explicit rate limits, timeouts, and resource quotas for API calls, file operations, and compute. Implement circuit breakers for runaway loops.
How audits are shown
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 $0.00101 $0.04259
Opus 5 $0.00051 $0.02129
Sonnet 5 $0.00020 $0.00852
Haiku 4.5 $0.00010 $0.00426

Measured 10d ago against content hash f9c7def6a9e4, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

orchestrate 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.

.claude/skills/orchestrate/SKILL.md · 364 lines

How it starts

The opening of the file, as written. The whole thing — 364 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Orchestrate — tree-aware multi-agent execution

You are the conductor. You do NOT implement tasks. You manage the task tree from task-splitting-evaluation, schedule workers, track state, handle failures, and report.

Worker agents own their subtree lifecycle — one worker per tree root/orphan, each walks depth-first, fetching context from issue comments, executing sequentially respecting dependencies, and updating GitHub + .claude/task-state.json.

Routing knowledge: .claude/orchestrate-routing.md. Read it once at start. Default to codex/agy. Use claude (scala-coder) ONLY for hard Scala tasks needing scala-semantic MCP.

Tree structure (from task-splitting-evaluation)

Each task is a GitHub issue with:

  • task-tree-marker comment: Status (leaf-ready), Parent, Children, Preferred executor
  • Body: Task description, Acceptance criteria, Dependencies (e.g., "depends on #129")
  • Dependencies: explicitly listed in issue body (e.g., "Depends: #129 → read from comment")

Root issues (no parent): #111, #105, #112, #108, #106, #79, #73, #72, #80, #71

  • Leaf issues (no children): all others (30+ children from expansion)
  • Orphan issues (if any): leaves not linked to any parent via marker

Invocation modes

Normal

/orchestrate — build task tree, schedule workers, execute depth-first per branch with root/orphan parallelization.

Dry-run

/orchestrate --dry-run (or user says "preview"/"plan only") — build task tree, print execution plan but do NOT launch workers. Show:

Root Tree depth Leaf count First task Executor Status
#112 1 4 #128 (research) agy pending
#111 0 1 #111 (value_flow) claude pending

Let user inspect and approve before executing. Only spend tree-building (Haiku) tokens.

Resume (partial failure)

/orchestrate --resume — read .claude/task-state.json, continue from last halted/incomplete task, skip done tasks.

Read the full file on GitHub · 364 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. 10d ago First seen · 364 lines · 101 tokens per session scan A f9c7def6a9e4

Subscribe to this mod's changes

orchestrate is a skill published in the GitHub repository MercurieVV/ScalaSemantic (21 stars, last pushed 2d ago), licensed MIT. It adds 101 tokens to every session and 4,259 once invoked, about $0.0005 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.