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.
git clone --depth 1 https://github.com/fabiolalli/aits-agentsWrote 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.
[](https://agentmods.dev/commands/fabiolalli/aits-agents/diverge)<a href="https://agentmods.dev/commands/fabiolalli/aits-agents/diverge"><img src="https://agentmods.dev/badge/commands/fabiolalli/aits-agents/diverge/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/commands/fabiolalli/aits-agents/diverge"><img src="https://agentmods.dev/badge/commands/fabiolalli/aits-agents/diverge.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00081 | $0.00943 |
| Opus 5.5 | $0.00032 | $0.00377 |
| Sonnet 5.5 | $0.00016 | $0.00189 |
| Haiku 4.5 | $0.00008 | $0.00094 |
Grade A, and why
diverge 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.
How it starts
The opening of the file, as written. The whole thing — 92 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Engine: this command starts an AITS run with
aits_start_run(graphdiverge, modereview) and closes it only throughaits_synthesize.
/aits:diverge — Divergent AITS (Review Mode)
This command activates the Meta-Orchestrator in review mode — full generative sequence runs uninterrupted, then everything is presented for structured review at the end.
When to use
- Idea generation and option exploration
- When the problem is "we need more alternatives"
- Breaking out of false binaries
- Innovation sprints and creative strategy sessions
- When you want creative flow without premature critique
What happens
- Intake — Meta-Orchestrator reads the problem; notes if this is a deadlock-reframing call (Critical or Optimizer couldn't find a path with existing options)
- Execution — uninterrupted — the creative-first sequence runs without voluntary checkpoints:
- 🟢 Creative-Generative — generates options, novelty-labeled, with cross-domain analogies and micro-tests
- 🔴 Emotional-Intuitive — maps stakeholder reception for the generated options (adoption profile hints)
- 🔭 Foresight (if ≥ 4 viable options, triggered by inviolable rule #5) — options-scenarios matrix and robustness ranking
- 🎯 Synthesis — integrated view of the option space
- Review interface — full analysis presented at once:
═══════════════════════════════════════════════════
AITS ANALYSIS COMPLETE — Review Mode
═══════════════════════════════════════════════════
▶ DECISION LOG
▶ OPTION SPACE (labeled by novelty: incremental/adjacent/novel/radical)
▶ DISSOLVED BINARIES (options that reframe the original question)
▶ ROBUSTNESS RANKING (if Foresight ran)
▶ STRATEGIC RECOMMENDATION
▶ REVIEW OPTIONS
[1] ✅ ACCEPT and generate action plan
[2] 🔍 DRILL DOWN on specific option
[3] 🔁 RE-RUN Creative with new constraint
[4] ➕ ADD Critical-Validator for stress-testing the options
[5] 🔄 RECALCULATE with modified problem framing
═══════════════════════════════════════════════════
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.
- 3d ago First seen · 92 lines · 81 tokens per session scan A 5b5e477ae3ad
diverge is a command published in the GitHub repository fabiolalli/aits-agents (10 stars, last pushed 3d ago), licensed MIT. It adds 81 tokens to every session and 943 once invoked, about $0.0003 per session on Opus 5.5. 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 2026-11-07.
diverge compared with commands from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| divergefabiolalli/aits-agents | Command | 10 | 3d ago | MIT | A | 81 | Claude Code |
| reviewfabioc-aloha/Alex_Skill_Mall | Command | 5 | yesterday | MIT | A | 2 | Claude Code |
| prune-sourcefabioc-aloha/Alex_Skill_Mall | Command | 5 | yesterday | MIT | A | 27 | GitHub Copilot |
| add-sourcefabioc-aloha/Alex_Skill_Mall | Command | 5 | yesterday | MIT | A | 25 | GitHub Copilot |
| setup-ai-operationsfabioc-aloha/Alex_Skill_Mall | Command | 5 | yesterday | MIT | A | 27 | Claude Code |
| choose-modelfabioc-aloha/Alex_Skill_Mall | Command | 5 | yesterday | MIT | A | 31 | Claude Code |
| execute-model-taskfabioc-aloha/Alex_Skill_Mall | Command | 5 | yesterday | MIT | A | 35 | Claude Code |