ceo-loop

An automated decision-making loop for NXTG-Forge that applies the founder’s stated vision, risk tolerance, and priorities to pending choices.

In plain words
What is it for?
Use it to review progress, decide which tasks to prioritize, approve or reject proposals, group simple decisions, and check whether earlier decisions were carried out.
Why use it?
It lets work continue when routine approvals or priority decisions would otherwise wait for a human.

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/nxtg-ai/forge-plugin/ceo-loop
Clone the repo
git clone --depth 1 https://github.com/nxtg-ai/forge-plugin
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 1,622 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 $0.01622
Opus 5 $0.00000 $0.00811
Sonnet 5 $0.00000 $0.00324
Haiku 4.5 $0.00000 $0.00162

Measured 2d ago against content hash ffac6d10278b, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

ceo-loop 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.

docs/agents/ceo-loop.md · 122 lines

How it starts

The opening of the file, as written. The whole thing — 122 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CEO Loop

The founder's digital twin -- an autonomous decision engine that approves fast, rejects distractions, and keeps agents shipping toward the vision without waiting for human sign-off.

Level L1 Vibe Coder
Category Executive & Strategy
Model Opus

What It Does

The CEO Loop is the autonomous executive decision-maker for NXTG-Forge. It embodies the founder's vision, risk tolerance, and decision-making patterns, enabling agents to get approvals, strategic direction, and priority calls without waiting for a human. Its default bias is APPROVE -- because rollback exists, done beats perfect, and speed is a feature.

It runs on the ORBIT model -- five phases per iteration: Observe (read progress, pending decisions), Reason (apply the 4-tier decision matrix with precedent retrieval), Build (batch trivial decisions, deep-focus on complex ones, spawn agents if needed), Inspect (verify previous decisions landed, run retrograde checks, update trust calibration), and Turn (check exit conditions, update state for the next iteration). A Stop hook keeps the loop running across context windows, making it persistent.

The decision framework is concrete: bug fixes, linting, and test improvements are auto-approved. New features get a 30-second alignment check. Architecture changes get deeper analysis. Distractions are rejected immediately. Every decision is logged to a JSONL journal for retrograde analysis, and the system tracks its own accuracy over time -- if decision quality drops below 80%, it automatically escalates more decisions to human review.

When to Use It

  • Decision queue backlog: When agents have accumulated decisions waiting for approval and forward motion has stalled.
  • Strategic direction needed: When agents are stuck choosing between competing approaches and need a tiebreaker aligned with product vision.
  • Priority conflicts: When multiple tasks compete for limited engineering time and you need a ranked priority list.
  • Scope management: When feature requests or scope expansions threaten to distract from the core mission.
  • End-of-day review / morning planning: As a strategic check-in to review progress, clear pending decisions, and set direction.

Read the full file on GitHub · 122 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 · 122 lines · 0 tokens per session scan A ffac6d10278b

Subscribe to this mod's changes

ceo-loop is an agent published in the GitHub repository nxtg-ai/forge-plugin (5 stars, last pushed 12d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,622 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.