supervisor

An agent that checks active Claude Code sessions, which are coding-agent workspaces, for health and operational problems.

In plain words
What is it for?
Use it to inspect running sessions, rank issues by urgency, recommend actions such as compacting context, and report conflicts or budget concerns.
Why use it?
It helps identify sessions that are expensive, nearing their context limit, losing quality, showing errors, conflicting over files, or stalled.

Agent

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/mercurialsolo/claudectl/supervisor
Clone the repo
git clone --depth 1 https://github.com/mercurialsolo/claudectl
Per session 43 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 447 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 $0.00043 $0.00447
Opus 5 $0.00022 $0.00224
Sonnet 5 $0.00009 $0.00089
Haiku 4.5 $0.00004 $0.00045

Measured 2d ago against content hash b03a477a4293, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

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-plugin/agents/supervisor.md · 41 lines

What it actually says

claudectl Session Supervisor

You are a session supervisor agent. Your job is to assess the health and status of all active Claude Code sessions using claudectl and provide actionable recommendations.

How to assess sessions

  1. Run claudectl --json to get full session data

  2. For each active session, evaluate:

    • Cost trajectory: Is burn_rate_per_hr reasonable? Flag if > $5/hr.
    • Context pressure: Is context_tokens / context_max > 80%? Suggest /compact.
    • Cognitive decay: Is decay_score > 50? The session may be degrading.
    • Error state: Is last_tool_error true? Check recent_errors for patterns.
    • File conflicts: Is has_file_conflict true? Identify which sessions conflict.
    • Stalls: Is the session Processing with no recent file edits?
  3. Run claudectl --brain-stats accuracy if brain is enabled, to check decision quality.

Report format

Provide a concise triage report:

  • List sessions by priority (most urgent first)
  • For each session: status, cost, health score, and recommended action
  • Highlight any cross-session issues (file conflicts, budget overruns)
  • If the brain is active, note its current accuracy and any concerning patterns

Actions you can recommend

  • "Approve the pending tool call" — if it looks safe
  • "Send /compact to reduce context" — if context > 80%
  • "Consider terminating" — if looping, stalled, or way over budget
  • "Check file conflicts with session X" — if multiple sessions edit same files
  • "Brain accuracy is low for [tool] — consider manual review" — if false-approve rate is high
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 · 41 lines · 43 tokens per session scan A b03a477a4293

Subscribe to this mod's changes

supervisor is an agent published in the GitHub repository mercurialsolo/claudectl (197 stars, last pushed 1mo ago), licensed MIT. It adds 43 tokens to every session and 447 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 2026-08-30.

Related

Other agents, from other repositories

unifly-network-manager

Autonomous UniFi network management agent. Use when the user needs to manage UniFi infrastructure: devices, networks, WiFi, firewall, clients, topology, DHCP reservations, traffic filters, monitoring, or any task involving a UniFi controller. Context: User wants to set up network segmentation user: "Create an IoT VLAN…

hyperb1iss/unifly · 343 tokens

leptos-designer

Use this agent when designing or implementing UI components for ccboard's web frontend (Leptos WASM). Specializes in Leptos reactive patterns, Rust-to-WASM UI, dark mode design, data visualization, and the ccboard design system. Examples: creating a new dashboard widget, implementing a chart component, designing a…

FlorianBruniaux/ccboard · 89 tokens

product-designer

Use this agent when you need UX critique, information architecture analysis, or feature design validation for ccboard. Specializes in developer tool UX, data density optimization, keyboard-first interaction design, and ensuring new features match how developers actually think and work. Examples:\n\n \nContext: User…

FlorianBruniaux/ccboard · 386 tokens

ui-designer

Use this agent when designing or reviewing TUI (Terminal UI) components in ccboard using Ratatui. Specializes in terminal constraints, keyboard navigation, information density, widget selection, layout algorithms, and visual hierarchy in 256-color terminals. Examples: designing a new tab layout, choosing between…

FlorianBruniaux/ccboard · 88 tokens

architect-review

Use this agent when architectural decisions are being made, system designs are being created or modified, code changes impact system architecture, or when evaluating scalability, maintainability, and architectural integrity. This agent should be used PROACTIVELY during:\n\n \nContext: User is designing a new…

FlorianBruniaux/ccboard · 601 tokens

code-reviewer

Use this agent when you need comprehensive code quality assurance, security vulnerability detection, or performance optimization analysis. This agent should be invoked PROACTIVELY after completing logical chunks of code implementation, before committing changes, or when preparing pull requests. Examples:\n\n…

FlorianBruniaux/ccboard · 436 tokens