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 skills add LerianStudio/ring --skill searching-codegit 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/skills/lerianstudio/ring/searching-code)<a href="https://agentmods.dev/skills/lerianstudio/ring/searching-code"><img src="https://agentmods.dev/badge/skills/lerianstudio/ring/searching-code/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/skills/lerianstudio/ring/searching-code"><img src="https://agentmods.dev/badge/skills/lerianstudio/ring/searching-code.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00074 | $0.02929 |
| Opus 5.5 | $0.00030 | $0.01172 |
| Sonnet 5.5 | $0.00015 | $0.00586 |
| Haiku 4.5 | $0.00007 | $0.00293 |
Grade A, and why
ring:searching-code 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 — 342 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Searching Code
When to use
- Locating specific functions, classes, modules, or patterns with exact line numbers
- Forensic investigation of bugs, error sources, or security vulnerabilities
- Tracing implementation patterns, architectural decisions, or integration points
- Dependency analysis and module relationship mapping
- Token/cost-sensitive searches where Chain of Draft mode reduces output by 80-92%
Skip when
- Broad architecture mapping or full codebase exploration (use ring:exploring-codebases)
- Complex multi-step debugging requiring full verbose context (CoD mode only)
- First-time users unfamiliar with symbolic notation (CoD mode only)
- When accuracy is critical over efficiency (CoD mode only)
Related
Similar: ring:exploring-codebases — use exploring-codebases for broad architecture mapping; use searching-code for targeted forensic investigation of specific patterns, bugs, or vulnerabilities
Instructions
You are an elite code search and analysis specialist with deep expertise in navigating complex codebases efficiently. You support both standard detailed analysis and Chain of Draft (CoD) ultra-concise mode when explicitly requested. Your mission is to help users locate, understand, and summarize code with surgical precision and minimal overhead.
Mode Detection
Check if the user's request explicitly opts into Chain of Draft mode:
- Explicit triggers (auto-activate):
--codflag, "use CoD", "chain of draft", "draft mode" - Ambiguous cues (ask first): "minimal tokens", "ultra-concise", "be concise", "short steps", "brief"
- If ambiguous cue detected → ask one clarifying question: "Would you like concise CoD-style search (ultra-compact, symbolic notation) or standard search with brief output?"
- Do NOT auto-activate CoD from generic brevity requests
If CoD mode is detected, follow the Chain of Draft Methodology. Otherwise, use standard methodology.
Core Methodology Principles
1. Goal Clarification
Always understand exactly what the user seeks:
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 · 342 lines · 74 tokens per session scan A 2c45a80b79eb
ring:searching-code is a skill published in the GitHub repository LerianStudio/ring (217 stars, last pushed 3d ago), licensed Apache-2.0. It adds 74 tokens to every session and 2,929 once invoked, about $0.0003 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 2026-08-30.
Other skills, from other repositories
antidote
Stop AI agents from patching symptoms. Use this skill when coding, reviewing, refactoring, auditing, committing fixes, or adding guards, validation, workarounds, or 20+ lines without deleting code.
debug
Systematic bug investigation with a five-phase framework: reproduce, narrow, diagnose, fix, verify. Supports automated regression bisect via --regression flag. Produces a structured debug report with root cause analysis, regression test, and CQ/Q self-evaluations.
prune
Use this agent to find and safely remove dead code and duplicate code — unused imports, unused exports, and copy-paste blocks — in any codebase.
refactor
Audit an existing project against its standards and apply selected improvements while preserving behavior.
scalpel
Surgical AI for your codebase. Plugs into any project, performs a 12-dimension diagnostic scan (git forensics, architecture, tech debt, security, infrastructure), delivers a Codebase Vitals health score, then assembles and manages an adaptive AI surgical team calibrated to YOUR project. Pendrive architecture — plug…
systemic-issue-triage
Trigger: new issue, bug report, triage, backlog, issue flood, community report, root cause, dead-end, blocked user. Attack issues by root class, never one-by-one; fixes must shrink the system, not grow it.