supervisor-agent

supervisor-agent is an agent for coding agents from akashkedian26/claude-code-workspace. It costs 0 tokens per session (79 once invoked), scanned A, original, MIT.

A lightweight session-recovery agent that reads a session index when work starts and asks whether to continue the latest session. It also signals when a response should continue because of token limits.

In plain words
What is it for?
Use it to offer continuation of the latest recorded session and to mark work for automatic continuation when needed.
Why use it?
It helps recover unfinished work after a session ends or a response becomes too long.

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/akashkedian26/claude-code-workspace/supervisor-agent
Clone the repo
git clone --depth 1 https://github.com/akashkedian26/claude-code-workspace

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 supervisor-agent

README.md
[![agentmods](https://agentmods.dev/badge/agents/akashkedian26/claude-code-workspace/supervisor-agent.svg)](https://agentmods.dev/agents/akashkedian26/claude-code-workspace/supervisor-agent)
Your own site
<a href="https://agentmods.dev/agents/akashkedian26/claude-code-workspace/supervisor-agent"><img src="https://agentmods.dev/badge/agents/akashkedian26/claude-code-workspace/supervisor-agent.svg" alt="Measured on agentmods" height="20"></a>
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 79 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 $0.00000 $0.00079
Opus 5 $0.00000 $0.00039
Sonnet 5 $0.00000 $0.00016
Haiku 4.5 $0.00000 $0.00008

Measured 4d ago against content hash 4e02e5682e0b, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

supervisor-agent 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 4d 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.

examples/agents/supervisor-agent.md · 20 lines

What it actually says

Supervisor

Purpose: Provide lightweight session recovery.

On session start:

  1. Read ~/ai/sessions/index.md
  2. Ask user if they want to continue the latest session.

Token Limit Continuity

If a response approaches token limits:

  1. End the message with "CONTINUE".
  2. Automatically continue in the next message.
  3. Repeat until the task is complete.
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. 4d ago First seen · 20 lines · 0 tokens per session scan A 4e02e5682e0b

Subscribe to this mod's changes

supervisor-agent is an agent published in the GitHub repository akashkedian26/claude-code-workspace (2 stars, last pushed 4mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 79 tokens. 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.