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 instructions/study8677/agent_view_controller-avc/agents-mdgit clone --depth 1 https://github.com/study8677/Agent_View_Controller-AVCWhat 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 | $0.01044 | $0.01044 |
| Opus 5 | $0.00522 | $0.00522 |
| Sonnet 5 | $0.00209 | $0.00209 |
| Haiku 4.5 | $0.00104 | $0.00104 |
Grade A, and why
Agent_View_Controller-AVC AGENTS.md 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 yesterday.
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 — 129 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AVC Integration Guide for AI Agents
What is AVC?
AVC (Agent View Controller) is a visual interaction tool installed on this system. It transforms JSON data into interactive visual UIs for human decision-making.
Binary location: avc (in PATH) or ./avc (project root)
When to Use AVC
Use AVC instead of printing plain text when you need human approval for:
- Execution plans with more than 3 steps
- Architecture changes involving multiple modules
- Multi-file refactoring plans
- Deployment sequences that need human ordering
How to Use
Construct a JSON object following the schema below, then pipe it to avc:
echo '{"view":"plan","title":"Your Plan Title","editable":true,"data":{"steps":[{"id":1,"label":"Step description","status":"pending"}]}}' | avc
Important Behavior
- The
avccommand blocks until the human clicks Confirm or Cancel - stdout contains the modified JSON (human may have reordered, edited, or removed steps)
- Exit code
0= confirmed, exit code130= cancelled - Parse the returned JSON to get the human-approved plan
- Token threshold: If the input token count ≤ 3000 (default), AVC will pass-through — it outputs the original JSON to stdout and exits with code
0without opening a window. This avoids interrupting the human for short content.
Token Threshold
AVC has a built-in token threshold (default: 3000 tokens). When the content is short, AVC skips the WebView and passes through directly.
How it works:
- If the JSON contains a
token_countfield, AVC uses that value - Otherwise, AVC estimates tokens from the JSON byte length (
bytes / 3) - If the token count ≤ threshold, AVC passes through without opening a window
To always show the WebView (bypass threshold), use --no-threshold:
echo '<json>' | avc --no-threshold
To set a custom threshold:
echo '<json>' | avc --threshold=5000
To include token count in JSON (recommended for accuracy):
{
"view": "plan",
"title": "Your Plan",
"token_count": 4500,
"data": { "steps": [...] }
}
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.
- yesterday First seen · 129 lines · 1,044 tokens per session scan A 201b89f0ab72
Agent_View_Controller-AVC AGENTS.md is an instructions file published in the GitHub repository study8677/Agent_View_Controller-AVC (68 stars, last pushed 3mo ago), licensed Apache-2.0. It adds 1,044 tokens to every session, about $0.0052 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 instructions, from other repositories
ui-components AGENTS.md
Instructions for starc007/ui-components, covering beui v2 — agent guide, commands, layout, component catalog and components (motion category — primitives).
open-agent-hub AGENTS.md
AGENTS.md instructions for guanyang/open-agent-hub, covering agents.md, 1. think before coding, 2. simplicity first, 3. surgical changes and 4. goal-driven execution.
core AGENTS.md
Instructions for ReactUnity/core, covering release workflow, write changelog files, example, fix button hover state and package references.
gmgn-skills CLAUDE.md
Instructions for GMGNAI/gmgn-skills, covering claude.md, critical rule — read this first, project overview, available skills and quick decision guide.
OneJS AGENTS.md
Instructions for Singtaa/OneJS, covering onejs v3: agent guide, requirements, install, project setup and build and live reload.
nim_duilib CLAUDE.md
Instructions for rhett-lee/nim_duilib, covering nimduilib - 跨平台 c++ ui 库, 项目概述, 项目结构, 开发模式(xml + c++) and xml 布局文件.