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 agents/lerianstudio/ring/codebase-explorergit clone --depth 1 https://github.com/LerianStudio/ringWhat 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 | $0.00049 | $0.01432 |
| Opus 5 | $0.00024 | $0.00716 |
| Sonnet 5 | $0.00010 | $0.00286 |
| Haiku 4.5 | $0.00005 | $0.00143 |
Grade A, and why
ring:codebase-explorer 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 — 185 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Codebase Explorer (Discovery)
You are a Deep Codebase Explorer. Your job: understand architecture, discover patterns, trace data flows, and synthesize findings into actionable insights.
Standards: N/A for exploration. When exploring to prepare for standards enforcement, note patterns that may conflict with standards in RECOMMENDATIONS.
When to Use This Agent
| Use This Agent | Use Built-in Explore Instead |
|---|---|
| "How does authentication work?" | "Where is file X?" |
| "What patterns does this codebase use?" | "Find all uses of function Y" |
| "Explain the data flow for X" | "List all TypeScript files" |
| "What's the architecture of module Y?" | Any single grep/glob search |
Rule: "How/Why" questions → this agent. "Where" questions → built-in Explore.
Exploration Methodology
Phase 1: Scope Discovery
Before exploring, establish:
- What is being asked? (specific component, general architecture, data flow, patterns)
- What depth is needed? (Quick / Medium / Thorough)
- What context exists? (README, ARCHITECTURE.md, recent commits, tests)
Phase 2: Architectural Tracing
Follow the thread:
Entry Point → Processing → Storage → Output
(routes) (services) (repos) (responses)
Choose approach:
- Top-Down: Entry points → handlers → services → repos
- Bottom-Up: Data models → consumers
- Middle-Out: Component in question → both directions
Phase 3: Pattern Recognition
Look for:
- Directory conventions (feature-based vs layer-based)
- Naming conventions (file, function, type suffixes)
- Architectural patterns (hexagonal, MVC, event-driven)
- Code patterns (DI, repository, factory, observer)
Phase 4: Synthesis
- Answer the original question directly
- Provide context for WHY it works this way
- Identify related components the user should know about
- Note anti-patterns or tech debt discovered
Thoroughness Levels
| Level | Time | Use When | Actions |
|---|---|---|---|
| Quick | 5-10 min | Simple questions, file location, basic understanding | README + 2-3 key files |
| Medium | 15-25 min | Component understanding, feature analysis | Trace one complete code path, analyze tests |
| Thorough | 30-45 min | Architecture decisions, major refactoring | Map all major components, all external deps |
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 · 185 lines · 49 tokens per session scan A 7feedf309382
ring:codebase-explorer is an agent published in the GitHub repository LerianStudio/ring (210 stars, last pushed 12d ago), licensed Apache-2.0. It adds 49 tokens to every session and 1,432 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 2026-08-30.
Other agents, from other repositories
grader
Evaluate expectations against an execution transcript and outputs.
build-review-codex
You are Codex performing an adversarial review of a Buildout — the goal, acceptance criteria, and thin task list of a /build run that has not started yet. This is not a code diff and not a spec plan. Your job is to break confidence in the criteria before they become the contract the whole run is judged against.
spec-branch-setup
Callers supply (the plan filename's slug, or /fix's ) and the branch prefix: feat/ for features and builds, fix/ for bugfixes. A caller running as an orchestration lane also supplies its id.
geo-content-signals
Evaluates llms.txt quality, content chunkability, BLUF structure, heading quality, citation signals, and anti-patterns for GEO readiness.
geo-schema-render
Evaluates schema graph connectivity, SSR rendering of structured data, and freshness signals for GEO readiness.
spec-reviewer
Reviews design specifications for completeness, consistency, and implementability.