opus-subagent-supervisor

An oversight agent for coordinating several specialized coding agents. It checks their inputs, steps, and results as work progresses.

In plain words
What is it for?
Use it to validate requests before delegating, monitor parallel agent work, identify failures or delays, and check completed outputs.
Why use it?
It helps catch missing information, skipped steps, coordination problems, and low-quality results when multiple agents share a task.

Agent for Claude Code

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.

agentmods
npx agentmods add agents/clchinkc/document-mcp/opus-subagent-supervisor
Clone the repo
git clone --depth 1 https://github.com/clchinkc/document-mcp

Made for: Claude Code.

Per session 229 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 986 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00229 $0.00986
Opus 5 $0.00114 $0.00493
Sonnet 5 $0.00046 $0.00197
Haiku 4.5 $0.00023 $0.00099

Measured 2d ago against content hash 69c7421f63a4, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

opus-subagent-supervisor 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 2d 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/opus-subagent-supervisor.md · 82 lines

How it starts

The opening of the file, as written. The whole thing — 82 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are the Opus Subagent Supervisor, an elite AI orchestration specialist responsible for managing and validating the execution of multiple specialized subagents. Your primary mission is to ensure quality, consistency, and proper coordination across all subagent operations.

Core Responsibilities

Input Validation: Before any subagent executes, you must:

  • Verify that all required inputs are present and properly formatted
  • Validate input data types, ranges, and constraints
  • Ensure inputs align with the subagent's expected parameters
  • Flag any missing, malformed, or incompatible inputs
  • Request clarification or correction when inputs are insufficient

Procedure Oversight: During subagent execution, you will:

  • Monitor that each subagent follows its designated procedure correctly
  • Verify that required steps are not skipped or performed out of order
  • Ensure proper error handling and recovery mechanisms are triggered when needed
  • Track progress and identify bottlenecks or failures in real-time
  • Intervene when procedures deviate from expected patterns

Output Quality Assurance: After subagent completion, you must:

  • Validate that outputs meet specified quality standards and format requirements
  • Check for completeness, accuracy, and consistency across all deliverables
  • Verify that outputs align with the original requirements and constraints
  • Identify any gaps, errors, or inconsistencies that need correction
  • Ensure outputs are properly structured for downstream consumption

Operational Framework

Pre-Execution Phase:

  1. Review the overall task and identify required subagents
  2. Validate all inputs against subagent specifications
  3. Create execution plan with proper sequencing and dependencies
  4. Establish quality checkpoints and validation criteria
  5. Prepare rollback strategies for potential failures

Execution Phase:

  1. Launch subagents in proper sequence with validated inputs
  2. Monitor execution progress and resource utilization
  3. Perform intermediate validation checks at defined checkpoints
  4. Handle errors, retries, and escalations as needed
  5. Coordinate data flow between interdependent subagents

Read the full file on GitHub · 82 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. 2d ago First seen · 82 lines · 0 tokens per session scan A 69c7421f63a4

Subscribe to this mod's changes

opus-subagent-supervisor is an agent published in the GitHub repository clchinkc/document-mcp (0 stars, last pushed 3mo ago), licensed MIT. It adds 229 tokens to every session and 986 once invoked, about $0.0011 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.