git-aware-coding-agent: Skill for Cursor

.cursor/skills/avos-search/SKILL.md

avos-search is a skill for Cursor from Avos-Lab/git-aware-coding-agent. It costs 10 tokens per session (671 once invoked), scanned A, original, Apache-2.0.

A command-line search tool for finding engineering context stored in repository memory. It answers questions about existing code decisions, patterns, and functionality.

In plain words
What is it for?
Use it to investigate architecture and design rationale, locate established implementation patterns, and check whether a capability already exists.
Why use it?
It helps developers understand an unfamiliar codebase before making changes, reducing the risk of duplicating or contradicting existing work.

Skill for Cursor

Written for Cursor: installed under .cursor/.

This is Avos-Lab/git-aware-coding-agent's own configuration. It tells Cursor how to work on git-aware-coding-agent itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything git-aware-coding-agent configures →

Reuse

Borrowing it

Nothing to install: this file belongs to Avos-Lab/git-aware-coding-agent. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/Avos-Lab/git-aware-coding-agent/main/.cursor/skills/avos-search/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/Avos-Lab/git-aware-coding-agent

Made for: Cursor.

Wrote 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.

agentmods badge for avos-search

README.md
[![agentmods](https://agentmods.dev/badge/skills/avos-lab/git-aware-coding-agent/avos-search/github.svg)](https://agentmods.dev/skills/avos-lab/git-aware-coding-agent/avos-search)
Your own site
<a href="https://agentmods.dev/skills/avos-lab/git-aware-coding-agent/avos-search"><img src="https://agentmods.dev/badge/skills/avos-lab/git-aware-coding-agent/avos-search/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.

agentmods 80×15 button for avos-search

Your own site · 80×15
<a href="https://agentmods.dev/skills/avos-lab/git-aware-coding-agent/avos-search"><img src="https://agentmods.dev/badge/skills/avos-lab/git-aware-coding-agent/avos-search.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 10 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 671 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00010 $0.00671
Opus 5.5 $0.00004 $0.00268
Sonnet 5.5 $0.00002 $0.00134
Haiku 4.5 $0.00001 $0.00067

Measured 1mo ago against content hash 1d69a9baf595, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

avos-search 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 1mo 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.

.cursor/skills/avos-search/SKILL.md · 121 lines

How it starts

The opening of the file, as written. The whole thing — 121 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Avos Search (Ask)

Use this skill when you need to search repository memory for engineering context.

When to Use

Use this skill when at least one trigger applies:

  • You are editing existing production code in an unfamiliar/shared module
  • You expect a medium/large change (multi-file, refactor, behavior change)
  • You need design rationale before changing architecture/API/auth/data flow
  • You need to avoid duplicating an existing pattern

You can skip this skill for low-risk tasks:

  • Docs/comments/typo-only changes
  • New isolated file creation without touching existing behavior
  • Test-only updates that do not alter production logic

Command

avos ask --json "your question about the codebase"

Examples

Understanding Code Decisions

avos ask --json "why does the authentication module use JWT instead of sessions?"

Finding Existing Patterns

avos ask --json "how do other API endpoints handle pagination?"

Checking for Existing Functionality

avos ask --json "is there existing error handling middleware?"

Response Format

Success with answer:

{
  "success": true,
  "data": {
    "format": "avos.ask.v1",
    "raw_text": "...",
    "answer": {
      "text": "The authentication module uses JWT because..."
    },
    "evidence": {
      "is_none": false,
      "items": [
        {
          "type": "pr",
          "ref": "123",
          "title": "Implement JWT auth",
          "author": "developer"
        }
      ],
      "unparsed_lines": []
    },
    "parse_warnings": []
  }
}

No matching evidence:

{
  "success": true,
  "data": {
    "format": "avos.ask.v1",
    "answer": {
      "text": "No matching evidence found in repository memory."
    },
    "evidence": {
      "is_none": true,
      "items": []
    }
  }
}

Best Practices

  1. Be specific: "how does user authentication work?" is better than "auth?"
  2. Include context: "why does the login API return 401 instead of 403?" is better than "login error"
  3. Use for high-risk edits: Trigger this before substantial or unfamiliar code edits
  4. Skip for trivial edits: Avoid unnecessary memory calls for low-risk cosmetic changes

Read the full file on GitHub · 121 lines

Changes

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.

  1. 1mo ago First seen · 121 lines · 10 tokens per session scan A 1d69a9baf595

Subscribe to this mod's changes

avos-search is a skill published in the GitHub repository Avos-Lab/git-aware-coding-agent (4 stars, last pushed 6mo ago), licensed Apache-2.0. It adds 10 tokens to every session and 671 once invoked, about $0.0000 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 2026-08-31.

Related

Other skills, from other repositories

agent-state-bar

A design guide for an agent status bar: a short, automatically updated summary of progress, remaining tasks, tool counts, errors, and system state placed near the latest model input.

bojieli/ai-agent-book · 105 tokens

knowledge-org

A guide to organising large bodies of knowledge so an AI system can navigate relationships, summaries, and layers instead of searching only flat text chunks. It covers tree indexes, knowledge graphs, file-like structures, incremental updates, and long-term memory layouts.

bojieli/ai-agent-book · 96 tokens

context-compression

A guide to shortening the information an agent carries between steps. It explains how to replace large tool outputs and old conversation details with compact, useful summaries while preserving important decisions and constraints.

bojieli/ai-agent-book · 92 tokens

memory-system

A guide to giving an AI agent persistent, user-specific memory across conversations. It covers what to remember, how to store it, how to update or compress it, and when to use memory instead of a shared knowledge base.

bojieli/ai-agent-book · 95 tokens

memory

Persist and retrieve agent memory across sessions — recall via the three-stage protocol (structure route → semantic search → navigation fallback), read via memoryload, see the wiki structure via memorybrowse, write well-placed pages via memorywrite (including section-level append/rewrite), maintain via memorycurate.…

Prismer-AI/PrismerCloud · 122 tokens

memory-dream

Curate the workspace memory wiki as its appointed orchestrator. Trigger on a Cloud-scheduled Dream task or a user's direct curation request. Inspect candidates for orphan leaves, near-duplicates, stale pages, remote conflicts and oversized hubs; browse the graph, cluster leaves into INDEX/hub/leaf structure, maintain…

Prismer-AI/PrismerCloud · 133 tokens