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 rules/avos-lab/git-aware-coding-agent/avos-agent-workflowgit 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 | $0.00710 | $0.00710 |
| Opus 5 | $0.00355 | $0.00355 |
| Sonnet 5 | $0.00142 | $0.00142 |
| Haiku 4.5 | $0.00071 | $0.00071 |
Grade A, and why
avos-agent-workflow 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 — 119 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Avos Agent Workflow
This repository uses avos-dev-cli for codebase memory. Follow these rules when working on this codebase.
Before Modifying Code
Trigger avos ask / avos history only for high-risk edits
Run avos ask and avos history when any of these are true:
- You will modify existing production code (not only docs/tests/comments)
- The module is unfamiliar or shared across teams
- The change is medium/large (for example: multiple files, refactor, behavior change)
- The change impacts architecture, APIs, auth, data flow, or critical paths
You may skip ask/history for low-risk edits:
- New isolated files with no existing code edits
- Small typo/comment/docs-only updates
- Pure test-only updates that do not change production behavior
When the trigger conditions are met:
# Get chronological history of a subject
avos history --json "authentication module"
# Ask specific questions about the codebase
avos ask --json "why does the login function use JWT instead of sessions?"
This helps you understand:
- Why the code was written this way
- Who made previous changes and why
- Related PRs, issues, and commits
- Which constraints are still active before making broad edits
Search Before Writing
Before implementing new features:
# Check if similar functionality exists
avos ask --json "is there existing pagination logic?"
# Understand patterns used in the codebase
avos ask --json "how do other API endpoints handle errors?"
After Pushing Changes
After pushing a PR to the remote repository, ingest it:
avos ingest-pr org/repo PR_NUMBER --json
This ensures the PR context is available for future queries.
JSON Output for Agents
All commands support --json for machine-readable output:
avos ask --json "question"
avos history --json "subject"
avos ingest-pr --json org/repo 123
The JSON envelope format:
{
"success": true,
"data": { ... },
"error": null
}
On error:
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 · 119 lines · 710 tokens per session scan A 12499461b618
avos-agent-workflow is a cursor rule published in the GitHub repository Avos-Lab/git-aware-coding-agent (2 stars, last pushed 4mo ago), licensed Apache-2.0. It adds 710 tokens to every session, about $0.0036 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 cursor rules, from other repositories
data-science-rules
Reproducible R and Python data-science conventions (environmental, ecological, geospatial).
engine-internals
Coding Agent engine implementation details (Cursor + Claude Code) — reference when modifying engine.ts or debugging Agent behavior.
project-instructions
Where vibe-replay's project instructions live.
cortex-snowflake-routing
Route Snowflake queries to the cortex-code skill for specialized Snowflake expertise via Cortex Code CLI.
react-component-template
Template for creating new React components.
api-integration
Frontend API Integration Patterns.