supervisor

supervisor is an agent for coding agents from iamironz/ai-config-bundle. It costs 16 tokens per session (131 once invoked), scanned A, original, MIT.

A hidden supervisor agent for cases where normal autonomous work is unsafe or unclear. It recommends a branch, explains the reason, says whether a question is needed, and identifies the smallest safe next action.

In plain words
What is it for?
Use it when multiple materially different paths remain possible, an action could delete data or change security, or an implementation has failed repeatedly.
Why use it?
It helps recover from repeated failures and prevents ambiguous or destructive actions from being taken without enough evidence.

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/iamironz/ai-config-bundle/supervisor
Clone the repo
git clone --depth 1 https://github.com/iamironz/ai-config-bundle

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

README.md
[![agentmods](https://agentmods.dev/badge/agents/iamironz/ai-config-bundle/supervisor.svg)](https://agentmods.dev/agents/iamironz/ai-config-bundle/supervisor)
Your own site
<a href="https://agentmods.dev/agents/iamironz/ai-config-bundle/supervisor"><img src="https://agentmods.dev/badge/agents/iamironz/ai-config-bundle/supervisor.svg" alt="Measured on agentmods" height="20"></a>
Per session 16 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 131 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 $0.00016 $0.00131
Opus 5 $0.00008 $0.00066
Sonnet 5 $0.00003 $0.00026
Haiku 4.5 $0.00002 $0.00013

Measured 3d ago against content hash 3ba25660eed6, 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 3d 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.

.opencode/agents/supervisor.md · 23 lines

What it actually says

You are the hidden supervisor lane.

Use this lane only when the normal autonomy-first path is insufficient because one of these is true:

  • the repository supports multiple materially different branches and evidence does not disambiguate them,
  • the next action is destructive or changes security posture,
  • the implementation loop has failed repeatedly and needs a recovery recommendation.

Return:

  • recommended branch,
  • exact reason,
  • whether a question tool escalation is necessary,
  • the smallest safe next action.
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. 3d ago First seen · 23 lines · 16 tokens per session scan A 3ba25660eed6

Subscribe to this mod's changes

supervisor is an agent published in the GitHub repository iamironz/ai-config-bundle (2 stars, last pushed 5mo ago), licensed MIT. It adds 16 tokens to every session and 131 once invoked, about $0.0001 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 agents, from other repositories

director

Turn a request into a shot-plan.json for a short (3–30s) design-led motion graphic. You run in two parts around the asset-sourcing step: Part 1 (plan) before sourcing, Part 2 (design) after. You do NOT write composition code — that's the Builder. Schema: references/shot-plan-ir.md.

calesthio/OpenMontage · 0 tokens

builder

Turn shot-plan.json into one renderable HyperFrames composition (compositions/index.html). Everything stays in the HF ecosystem — HTML is the source of truth; a single paused GSAP timeline carries all motion; the engine seeks it. Category-specific build rules live in categories/ /module.md; this file is the shared…

calesthio/OpenMontage · 0 tokens

finalize

Snapshot visual QA + one in-place fix pass + render. Dispatched only when Step 6 lint/inspect reports issues, or to do the final render.

calesthio/OpenMontage · 0 tokens

clawteam-rnd-backend

Backend R&D task agent — layered abstraction, defensive coding, consistency-first data, built-in observability, evolvable design, perf/resource awareness; architecture layers, quality trade-offs, error taxonomy, distributed consistency patterns.

deepelementlab/jupyter-studio · 52 tokens

clawteam-rnd-frontend

Frontend R&D task agent — component model, declarative UI, data-driven flow, progressive enhancement, perf-first, a11y built-in; layered architecture, CSR/SSR/SSG/ISR, state taxonomy, RAIL-style optimization.

deepelementlab/jupyter-studio · 57 tokens

clawteam-rnd-mobile

Mobile R&D task agent — platform-first adaptation, resource constraints, offline-first, lifecycle-aware, privacy/security, store-safe delivery & hotfix; layered architecture, perf model, stack trade-offs, release pipeline.

deepelementlab/jupyter-studio · 49 tokens