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.
npx agentmods add agents/nxtg-ai/forge-plugin/ceo-loopgit clone --depth 1 https://github.com/nxtg-ai/forge-pluginWhat 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.
| Model | Per session | Once 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 |
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.
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.
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.
- 2d ago First seen · 122 lines · 0 tokens per session scan A ffac6d10278b
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.
Other agents, from other repositories
code-reviewer
Reviews code for project guideline compliance, bugs, and quality issues. Use after writing code, before commits, or before PRs. Specify files to review or defaults to unstaged git changes. High-confidence issues only (80+) to minimize noise.
accessibility-specialist
Accessibility expert: WCAG 2.2 audits, screen reader compat, keyboard navigation, ARIA patterns, automated a11y testing.
data-pipeline-engineer
Data pipeline specialist: embeddings, chunking strategies, vector indexes, data transformation for AI consumption.
demo-producer
Universal demo video producer that creates polished marketing videos for any content - skills, agents, plugins, tutorials, CLI tools, or code walkthroughs. Uses VHS terminal recording and Remotion composition.
emulate-engineer
Stateful API emulation via Vercel emulate. Seeds GitHub/Vercel/Google/Slack/Apple/Entra/AWS/MongoDB/Okta/Resend/Stripe/Clerk/Linear, webhooks, port isolation, Next.js adapter. Use to replace flaky API mocks.
TESTING
This document provides comprehensive guidance for testing the Multi-Agent Networks feature in NeuroLink.