code-search-navigation

code-search-navigation is a skill for Claude Code, Codex from joinwell52-AI/CodeFlowMu-open. It costs 34 tokens per session (290 once invoked), scanned A, original, MIT.

A set of instructions for finding the right parts of a codebase before making changes or explaining how the code works. It focuses on files, named code elements, routes, tests, configuration, and which part of the project owns each responsibility.

In plain words
What is it for?
Use it to locate entry points, symbols, call sites, routes, tests, configuration, and project boundaries, then report the files inspected and the chosen edit area.
Why use it?
It helps avoid editing the wrong file or changing code before understanding how it fits together. It also keeps code searches focused and evidence-based.

Skill for Claude CodeCodex

Install

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.

agentmods
npx agentmods add skills/joinwell52-ai/codeflowmu-open/code-search-navigation
Any agent
npx skills add joinwell52-AI/CodeFlowMu-open --skill code-search-navigation
Clone the repo
git clone --depth 1 https://github.com/joinwell52-AI/CodeFlowMu-open

Made for: Claude Code, Codex.

Wrote 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.

agentmods badge for code-search-navigation

README.md
[![agentmods](https://agentmods.dev/badge/skills/joinwell52-ai/codeflowmu-open/code-search-navigation.svg)](https://agentmods.dev/skills/joinwell52-ai/codeflowmu-open/code-search-navigation)
Your own site
<a href="https://agentmods.dev/skills/joinwell52-ai/codeflowmu-open/code-search-navigation"><img src="https://agentmods.dev/badge/skills/joinwell52-ai/codeflowmu-open/code-search-navigation.svg" alt="Measured on agentmods" height="20"></a>
Per session 34 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 290 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00034 $0.00290
Opus 5 $0.00017 $0.00145
Sonnet 5 $0.00007 $0.00058
Haiku 4.5 $0.00003 $0.00029

Measured 3d ago against content hash 3f88b1407125, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

code-search-navigation 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 3d 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.

skills/code-search-navigation/SKILL.md · 44 lines

What it actually says

Code Search Navigation

When to use

Use before changing or explaining code when the relevant entry point, module, test, route, or ownership boundary is not already known.

Rules

  • Prefer rg and rg --files for text and file discovery.
  • Search for exact identifiers, route paths, filenames, error text, and user-visible labels.
  • Read nearby code before editing.
  • Follow existing patterns before adding new abstractions.
  • Keep the discovered evidence narrow: file paths, line numbers, and why they matter.
  • Stop searching once the implementation boundary is clear.

Required output

When reporting, include:

  • Search terms or discovery method.
  • Key files inspected.
  • Chosen edit boundary.
  • Any relevant files intentionally left untouched.

Forbidden actions

  • Do not edit before locating the owning module unless the task is trivial and file ownership is explicit.
  • Do not perform broad refactors just because search found related code.
  • Do not cite files you did not inspect.

Minimal example

Search: rg "resolveAndInject" packages/codeflowmu-runtime/src
Found: TaskDispatcher.ts builds the agent prompt prefix
Boundary: route skill injection there, not in Panel rendering
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.

  1. 3d ago First seen · 44 lines · 34 tokens per session scan A 3f88b1407125

Subscribe to this mod's changes

code-search-navigation is a skill published in the GitHub repository joinwell52-AI/CodeFlowMu-open (2 stars, last pushed 9d ago), licensed MIT. It adds 34 tokens to every session and 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 2026-08-31.