agentsclimarketplace

File analysis

Skill athola/claude-night-market/plugins/sanctum/skills/file-analysis

23 Claude Code plugins: TDD enforcement hooks, git/PR workflows, spec-driven development, code review, project lifecycle, fix-from-error, maintenance automation, context optimization, research, and multi-LLM delegation. 186 skills, 128 commands, 54 agents.

Install
npx -y skills add athola/claude-night-market --skill file-analysis

Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.

What its author says it does

Copied from the file, not written here

Maps file structure and module organization of a codebase. Use before architecture reviews, refactoring planning, or migration scope estimation.

SKILL.md

2.7 KB, 583 tokens by cl100k_base, as published. Nobody here has run it

File Analysis

When To Use

  • Before architecture reviews to understand module boundaries and file organization.
  • When exploring unfamiliar codebases to map structure before making changes.
  • As input to scope estimation for refactoring or migration work.

When NOT To Use

  • General code exploration - use the Explore agent
  • Searching for specific patterns - use Grep directly

Required TodoWrite Items

  1. file-analysis:root-identified
  2. file-analysis:structure-mapped
  3. file-analysis:patterns-detected
  4. file-analysis:hotspots-noted

Mark each item as complete as you finish the corresponding step.

Step 1: Identify Root (file-analysis:root-identified)

  • Confirm the analysis root directory with pwd.
  • Note any monorepo boundaries, workspace roots, or subproject paths.
  • Capture the project type (language, framework) from manifest files (package.json, Cargo.toml, pyproject.toml, etc.).

Step 2: Map Structure (file-analysis:structure-mapped)

  • Run tree -L 2 -d or find . -type d -maxdepth 2 to capture the top-level directory layout.
  • Identify standard directories: src/, lib/, tests/, docs/, scripts/, configs/.
  • Note any non-standard organization patterns that may affect downstream analysis.

Step 3: Detect Patterns (file-analysis:patterns-detected)

  • Use find . -name "*.ext" -not -path "*/.venv/*" -not -path "*/__pycache__/*" -not -path "*/node_modules/*" -not -path "*/.git/*" | wc -l to count files by extension.
  • Identify dominant languages and their file distributions.
  • Note configuration files, generated files, and vendored dependencies.
  • Run wc -l $(find . -not -path "*/.venv/*" -not -path "*/__pycache__/*" -not -path "*/node_modules/*" -not -path "*/.git/*" -name "*.py" -o -name "*.rs" | head -20) to sample file sizes.

Step 4: Note Hotspots (file-analysis:hotspots-noted)

  • Identify large files (potential "god objects"): find . -type f -exec wc -l {} + | sort -rn | head -10.
  • Flag deeply nested directories that may indicate complexity.
  • Note files with unusual naming conventions or placement.

Exit Criteria

  • TodoWrite items are completed with concrete observations.
  • Downstream workflows (architecture review, refactoring) have structural context.
  • File counts, directory layout, and hotspots are documented for reference.

Gives 0 of the 12 instructions most research analysis skills give in 583 tokens

Counted across 1,063 of the 1,754 authors here whose files we hold, read 2026-08-06

  • generate a markdown reportin 32 of 1063, across 17 files
  • cite each claim's sourcein 31 of 1063, across 14 files
  • define the ideal customer profilein 20 of 1063, across 2 files
  • search for companies matching the criteriain 20 of 1063, across 2 files
  • assign a fit score from one to tenin 20 of 1063, across 2 files
  • format results in a scannable markdown templatein 20 of 1063, across 2 files
  • analyze the codebase to understand the productin 19 of 1063, across 1 file
  • ask clarifying questions about the value propositionin 19 of 1063, across 1 file
  • look for signals of immediate needin 19 of 1063, across 1 file
  • identify the target decision maker rolein 19 of 1063, across 1 file
  • suggest a personalized contact strategyin 19 of 1063, across 1 file
  • provide conversation starters for outreachin 19 of 1063, across 1 file

Said here and by no other author read

  • confirm analysis root directory with pwd
  • capture project type from manifest files
  • run tree or find to capture directory layout
  • note non-standard organization patterns
  • count files by extension excluding dependencies
  • identify dominant languages and file distributions

Grouped from the skills themselves: near-identical wordings counted once, and counted by distinct author, so one author publishing three of these counts once. Length counted with cl100k_base; the agent that loads this file may tokenize it differently.

Keep looking

Skills are one crate of 328,083. Ordering is by how many stacks a row turns up in, so the top of any crate is what has actually been picked rather than what has the most stars.