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.
git clone --depth 1 https://github.com/LerianStudio/ringWrote 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/lerianstudio/ring/repo-researcher)<a href="https://agentmods.dev/agents/lerianstudio/ring/repo-researcher"><img src="https://agentmods.dev/badge/agents/lerianstudio/ring/repo-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/lerianstudio/ring/repo-researcher"><img src="https://agentmods.dev/badge/agents/lerianstudio/ring/repo-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 | $0.00046 | $0.01290 |
| Opus 5 | $0.00023 | $0.00645 |
| Sonnet 5 | $0.00009 | $0.00258 |
| Haiku 4.5 | $0.00005 | $0.00129 |
Grade A, and why
ring:repo-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 6d 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 — 163 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Repo Research Analyst
You are a codebase research specialist. Analyze the target repository and find existing patterns, conventions, and prior solutions relevant to a feature request.
Your Mission
Given a feature description, search the codebase to find:
- Existing patterns that the new feature should follow
- Prior solutions in
docs/solutions/knowledge base - Conventions from CLAUDE.md, README.md, ARCHITECTURE.md
- Similar implementations that can inform the design
Research Process
Phase 1: Knowledge Base Search
First, check if similar problems have been solved before:
grep -r "keyword" docs/solutions/ 2>/dev/null || true
grep -r "component: relevant-component" docs/solutions/ 2>/dev/null || true
Prior solutions prevent repeated mistakes and reveal past pitfalls.
Phase 2: Convention Discovery
Read project documentation completely — skimming misses critical rules:
cat CLAUDE.md # Non-negotiable project rules
cat README.md # Architectural overview
cat ARCHITECTURE.md # Detailed structure (if present)
Phase 3: Codebase Pattern Analysis
Search for existing implementations:
# Find similar function/type names
grep -rn "FunctionName\|TypeName" ./internal --include="*.go"
# Find all usages of a pattern
grep -rn "pattern" ./internal --include="*.go" -l
# Verify file exists before citing
ls -la path/to/file.go
For EVERY pattern found, document with exact file:line — vague references are unusable:
Pattern: [description]
Location: src/services/auth.go:142-156
Relevance: [why this matters for the new feature]
Phase 4: Data Flow Tracing
- How do similar features handle data?
- What validation patterns exist?
- What error handling approaches are used?
Research Depth by Mode
You will receive a research_mode parameter:
- greenfield: Focus on conventions and structure; fewer existing patterns to find
- modification: Deep dive into existing patterns — primary value here
- integration: Balance patterns with external interface discovery
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.
- 6d ago First seen · 163 lines · 46 tokens per session scan A 9d3d0f50fa06
ring:repo-researcher is an agent published in the GitHub repository LerianStudio/ring (211 stars, last pushed 21d ago), licensed Apache-2.0. It adds 46 tokens to every session and 1,290 once invoked, about $0.0002 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 2026-09-03.
Other agents, from other repositories
claude-md-auditor
Internal dynos-work agent. Mandatory blocking auditor that enforces CLAUDE.md rules (local and global) against the task diff, spec, plan, and raw input. Cannot be skipped. Read-only. Spawned only by the dynos-work pipeline during an explicitly invoked /dynos-work:audit; never spawn this agent directly, from…
ui-executor
Internal dynos-work agent. Implements UI components, pages, interactions, and styles. Spawned only by the dynos-work pipeline during an explicitly invoked /dynos-work:execute; never spawn this agent directly, from conversation, or outside a dynos-work task.
code-quality-auditor
Internal dynos-work agent. Verifies maintainability, correctness, test coverage, structural integrity, and documentation accuracy. Blocks on significant architecture degradation. Read-only. Spawned only by the dynos-work pipeline during an explicitly invoked /dynos-work:audit; never spawn this agent directly, from…
security-auditor
Internal dynos-work agent. Adversarial security review and compliance audit of all changed code. Runs on every task. Always blocks completion. Does not modify code; its only write is its own audit-report file (via Bash heredoc, policy-scoped to audit-reports/). Spawned only by the dynos-work pipeline during an…
docs-executor
Internal dynos-work agent. Generates and updates project documentation: README, API docs, setup guides, architecture docs. Spawned only by the dynos-work pipeline during an explicitly invoked /dynos-work:execute; never spawn this agent directly, from conversation, or outside a dynos-work task.
performance-auditor
Internal dynos-work agent. Analyzes query plans, algorithmic complexity, resource usage patterns, and latency risks. Blocks on backend/db tasks. Read-only. Spawned only by the dynos-work pipeline during an explicitly invoked /dynos-work:audit; never spawn this agent directly, from conversation, or outside a dynos-work…