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 commands/avos-lab/git-aware-coding-agent/avos-askgit clone --depth 1 https://github.com/Avos-Lab/git-aware-coding-agentWhat 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 | $0.00006 | $0.00179 |
| Opus 5 | $0.00003 | $0.00089 |
| Sonnet 5 | $0.00001 | $0.00036 |
| Haiku 4.5 | $0.00001 | $0.00018 |
Grade A, and why
avos-ask scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured yesterday.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
What it actually says
Avos Ask
Search the repository memory for answers to your question.
Usage
Run this command and parse the JSON output:
avos ask --json "$ARGUMENTS"
Response Handling
Parse the JSON response:
{
"success": true,
"data": {
"format": "avos.ask.v1",
"answer": { "text": "..." },
"evidence": { "items": [...] }
}
}
If success is false, check error.code and error.hint for guidance.
Examples
- "why does authentication use JWT?"
- "how do other endpoints handle pagination?"
- "is there existing error handling middleware?"
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 · 41 lines · 6 tokens per session scan A 0e8ed1a3f64b
avos-ask is a command published in the GitHub repository Avos-Lab/git-aware-coding-agent (2 stars, last pushed 4mo ago), licensed Apache-2.0. It adds 6 tokens to every session and 179 once invoked, about $0.0000 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 2026-08-31.
Other commands, from other repositories
add-agent
引导新增一个 Agent 适配器。用法 /add-agent.
backfill-auto
.opensunstar/wiki/candidates/rd-backfill-auto- / ├── candidate.json # engine: "rd-backfill-auto", sourcecommit, createdat └── wiki/ ├── index.md └── runbooks/ .md # wiki schema frontmatter.
extract-routing
Command "extract-routing" from alisunstar/OpenSunstar, covering /rd:extract-routing — 源码锚点提取适配器（外置）, 先读规则, 执行, 产物 and 何时停止.
verify-prd
Command "verify-prd" from alisunstar/OpenSunstar, covering /rd:verify-prd — 输入质量门禁, 先读规则, 执行, 何时澄清 and 何时停止.
wrap
Close the session cleanly. Update entity state. Capture decisions. Detect momentum shifts.
code-review
Command "code-review" from alisunstar/OpenSunstar, covering /rd:code-review — 代码审查, 先读, 执行, 产物 and 人工确认.