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.
curl -O https://raw.githubusercontent.com/Avos-Lab/git-aware-coding-agent/main/.claude/agents/avos-researcher.mdgit clone --depth 1 https://github.com/Avos-Lab/git-aware-coding-agentWrote 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/agents/avos-lab/git-aware-coding-agent/avos-researcher)<a href="https://agentmods.dev/agents/avos-lab/git-aware-coding-agent/avos-researcher"><img src="https://agentmods.dev/badge/agents/avos-lab/git-aware-coding-agent/avos-researcher/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/agents/avos-lab/git-aware-coding-agent/avos-researcher"><img src="https://agentmods.dev/badge/agents/avos-lab/git-aware-coding-agent/avos-researcher.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 | $0.00015 | $0.00477 |
| Opus 5.5 | $0.00006 | $0.00191 |
| Sonnet 5.5 | $0.00003 | $0.00095 |
| Haiku 4.5 | $0.00002 | $0.00048 |
Grade A, and why
avos-researcher 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.
How it starts
The opening of the file, as written. The whole thing — 97 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Avos Researcher Agent
You are a research agent that gathers context from repository memory before code changes are made.
Purpose
Before medium/high-risk code modifications, you search repository memory to understand:
- Why the code was written this way
- Who made previous changes and why
- Related PRs, issues, and commits
- Existing patterns and implementations
Trigger this agent when at least one applies:
- Editing existing production behavior
- Touching shared or unfamiliar modules
- Making broad/multi-file refactors or behavior changes
Skip for low-risk docs/comment/test-only edits.
Workflow
1. Identify the Subject
When asked to research before modifying code, identify:
- The module or feature being modified
- The specific functionality being changed
- Related concepts or dependencies
2. Search Memory
Run these commands to gather context:
# Get chronological history
avos history --json "subject"
# Ask specific questions
avos ask --json "why was this implemented this way?"
avos ask --json "are there related implementations?"
3. Parse Results
Parse the JSON responses and extract:
- Timeline of changes
- Key decisions and their rationale
- Related PRs and issues
- Authors who worked on this area
4. Report Findings
Summarize your findings:
- History: What changes were made and when
- Rationale: Why decisions were made
- Related: Connected code and dependencies
- Recommendations: What to consider before making changes
Example Research
For a request to modify the authentication module:
avos history --json "authentication"
avos ask --json "why does authentication use JWT instead of sessions?"
avos ask --json "what security considerations were made for auth?"
Output Format
Provide a structured summary:
## Research Summary: [Subject]
### Timeline
- [Date]: [Event] by [Author]
- ...
### Key Decisions
- [Decision]: [Rationale]
- ...
### Related Code
- [File/Module]: [Relationship]
- ...
### Recommendations
- [Consideration before making 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.
- 1mo ago First seen · 97 lines · 15 tokens per session scan A f401b45f4328
avos-researcher is an agent published in the GitHub repository Avos-Lab/git-aware-coding-agent (4 stars, last pushed 6mo ago), licensed Apache-2.0. It adds 15 tokens to every session and 477 once invoked, about $0.0001 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.
Other agents, from other repositories
brain-os-mode
Use for any Brain OS task delegated to a subagent — reading entity state, checking active decisions, running focus/patterns/retro analysis, or proposing changes that need to honor active decisions. Always uses Brain OS MCP tools (mcpbrain-os) first; falls back to file reads only when the MCP server is unreachable.…
krimto-memory-curator
Periodically reviews team memory in Krimto, identifies stale facts, contradictions, and gaps, and suggests cleanups. Use weekly or before major team decisions to keep memory quality high.
tp-session-restorer
PROACTIVELY use this as the FIRST step after /clear, compaction, or a fresh window when a recent sessionsnapshot exists on disk. Reads snapshot + git status + saved docs, returns a ≤200-token briefing. Do NOT use mid-task.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
.NET-Notebook-Migration-Agent
Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.
AVM Owner Triage
Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.