subagent-orchestration

subagent-orchestration is a skill for Claude Code from ArtemioPadilla/agent-triforce. It costs 44 tokens per session (541 once invoked), scanned A, original, MIT.

A task-running workflow that gives each implementation task to a new coding agent, then checks the result against the requirements and code-quality standards.

In plain words
What is it for?
Use it to carry out a written implementation plan, assign simpler or more complex tasks to different model tiers, review failed tasks, and run the full test suite afterward.
Why use it?
It reduces the need to manually coordinate separate coding and review passes, and catches problems before the next task begins.

Skill for Claude Code

Written for Claude Code: $ARGUMENTS substitution. Also seen: reads .claude/ paths; mentions subagents.

Good fit Use it to carry out a written implementation plan, assign simpler or more complex tasks to different model tiers, review failed tasks, and run the full test suite afterward.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/artemiopadilla/agent-triforce/subagent-orchestration
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 ArtemioPadilla/agent-triforce --skill subagent-orchestration
Clone the repo
git clone --depth 1 https://github.com/ArtemioPadilla/agent-triforce

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 subagent-orchestration

README.md
[![agentmods](https://agentmods.dev/badge/skills/artemiopadilla/agent-triforce/subagent-orchestration/github.svg)](https://agentmods.dev/skills/artemiopadilla/agent-triforce/subagent-orchestration)
Your own site
<a href="https://agentmods.dev/skills/artemiopadilla/agent-triforce/subagent-orchestration"><img src="https://agentmods.dev/badge/skills/artemiopadilla/agent-triforce/subagent-orchestration/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 subagent-orchestration

Your own site · 80×15
<a href="https://agentmods.dev/skills/artemiopadilla/agent-triforce/subagent-orchestration"><img src="https://agentmods.dev/badge/skills/artemiopadilla/agent-triforce/subagent-orchestration.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 44 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 541 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 $0.00044 $0.00541
Opus 5 $0.00022 $0.00270
Sonnet 5 $0.00009 $0.00108
Haiku 4.5 $0.00004 $0.00054

Measured 11d ago against content hash ea81eb066f86, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

subagent-orchestration 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/skills/subagent-orchestration/SKILL.md · 52 lines

What it actually says

Subagent Orchestration

Execute the plan at: $ARGUMENTS

Process

  1. Read the plan file — extract all tasks with full text
  2. Create task tracking — one todo per task
  3. For each task: a. Select model tier based on task complexity (see Model Selection below) b. Dispatch implementer subagent using .claude/agents/forja-prompts/implementer-prompt.md c. Handle implementer status (DONE / DONE_WITH_CONCERNS / NEEDS_CONTEXT / BLOCKED) d. Dispatch spec-reviewer subagent using .claude/agents/forja-prompts/spec-reviewer-prompt.md e. If spec review fails: implementer fixes, re-review (loop until PASS) f. Dispatch code-quality-reviewer subagent using .claude/agents/forja-prompts/code-quality-reviewer-prompt.md g. If quality review fails: implementer fixes Critical/Important issues, re-review h. Mark task complete
  4. After all tasks: run full test suite, verify everything works together

Model Selection

Task Signals Model Examples
1-2 files, complete spec, mechanical haiku Add a field, write a test, rename
Multi-file, integration, judgment needed sonnet Wire up endpoint, refactor module
Architecture, design, broad codebase opus Design subsystem, complex debug

Subagent Dispatch Rules

  • Sequential only for implementation subagents (avoids file conflicts)
  • Spec review before code quality review (order matters)
  • Review loops repeat until approved — no "close enough"
  • Never make subagents read the plan file — provide full task text in the prompt
  • If implementer asks questions: answer clearly, then re-dispatch
  • If implementer is BLOCKED: assess and escalate (don't retry blindly)

Red Flags

  • Starting code quality review before spec compliance passes
  • Dispatching multiple implementers in parallel
  • Ignoring DONE_WITH_CONCERNS status
  • Skipping re-review after implementer fixes
  • Forcing retry without changing context, model, or task scope
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 · 52 lines · 44 tokens per session scan A ea81eb066f86

Subscribe to this mod's changes

subagent-orchestration is a skill published in the GitHub repository ArtemioPadilla/agent-triforce (3 stars, last pushed 4mo ago), licensed MIT. It adds 44 tokens to every session and 541 once invoked, about $0.0002 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.

Related

Other skills, from other repositories

fellowship

Multi-task orchestrator. Coordinates agent teammates (led by Gandalf) running /quest (code) or /scout (research) workflows. Use when you have multiple independent tasks to run in parallel.

justinjdev/fellowship · 45 tokens

quest

Use for multi-file or multi-step changes that need research and a plan — not single-file fixes under 50 lines that follow an existing pattern (see Escape Hatch below). Runs the Research → Plan → Implement → Review lifecycle with a hard gate leaving each of the first three phases and context compaction between them.

justinjdev/fellowship · 64 tokens

retro

Invoke after a fellowship disbands, or when the user explicitly asks for a retrospective. Collects gate history, palantir alerts, and quest metrics to surface patterns and interactively recommend configuration improvements.

justinjdev/fellowship · 42 tokens

council

Invoke when the user runs /council or from /scout. Quest inlines this orientation as its Research step 2 and does not call it. Loads focused, task-relevant context by reading CLAUDE.md, scanning for related files, and producing a structured Session Context block.

justinjdev/fellowship · 63 tokens

lembas

Use between workflow phases or when context feels bloated. Writes a structured checkpoint capturing task, findings, files, state, and next steps, then continues from that summary instead of the full history. Invoke standalone or automatically between quest phases.

justinjdev/fellowship · 51 tokens

missive

Invoke only when spawning a quest from a GitHub issue reference. Fetches GitHub issue context for quest spawning. Parses issue references, retrieves structured data via gh, and produces branch suggestions and PR keywords. Used standalone or as input to quest orchestration.

justinjdev/fellowship · 54 tokens