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/inclusionAI/AvernetWrote 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/inclusionai/avernet/ai-branch)<a href="https://agentmods.dev/commands/inclusionai/avernet/ai-branch"><img src="https://agentmods.dev/badge/commands/inclusionai/avernet/ai-branch/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/inclusionai/avernet/ai-branch"><img src="https://agentmods.dev/badge/commands/inclusionai/avernet/ai-branch.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 | $0.00030 | $0.00166 |
| Opus 5 | $0.00015 | $0.00083 |
| Sonnet 5 | $0.00006 | $0.00033 |
| Haiku 4.5 | $0.00003 | $0.00017 |
Grade A, and why
ai-branch 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 10d 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.
Copies of this mod
8 near-identical copies found in the catalogue:
- nl-branch — 88% identical, 8 lines differ
- workflow-dispatcher — 86% identical, 9 lines differ
- kf — 84% identical, 11 lines differ
- teamclaw-support — 84% identical, 11 lines differ
- kf-support — 84% identical, 11 lines differ
- approval-web — 83% identical, 9 lines differ
- aw — 83% identical, 9 lines differ
- ap — 81% identical, 9 lines differ
What it actually says
The user invoked the /ai-branch facade command from the nl-branching-demo pack.
Call the mcp__clawmind__workflow_engine_dispatch tool with:
- action: "run"
- workflowId: "ai-interpreted-branch"
- Pass the user's full query as the
inputparameter
If the MCP tool is not available, tell the user the ClawMind plugin MCP server is not running and suggest restarting Claude Code.
Examples
- /ai-branch 审核目标
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.
- 10d ago First seen · 19 lines · 30 tokens per session scan A 289e531cebfc
ai-branch is a command published in the GitHub repository inclusionAI/Avernet (536 stars, last pushed yesterday), licensed Apache-2.0. It adds 30 tokens to every session and 166 once invoked, about $0.0002 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 2026-08-30.
Other commands, from other repositories
tokenless-stats
Show Tokenless compression statistics.
discover
Run a full product discovery cycle — from outcome definition through opportunity mapping, prioritisation, and experiment design. Use when the team isn't sure what to build next, or before writing a PRD for a complex feature space.
music-suno-prompt
Grounded Suno prompt synthesis from local knowledge corpus + persona canon + label canon. No vibes-prompting.
hello-stranger
Say hello stranger.
audit-plugin
Audit plugin skills, commands, and agents for structure, size, and naming issues.
triage
Triage review findings one by one — present pending TODOs for user decision (approve, skip, modify).