.agents/skills/abf/SKILL.md
Use AgentsBestFriend (ABF) MCP tools for codebase navigation, search, and analysis instead of native file-reading tools. USE WHEN: exploring unfamiliar code, understanding architecture, searching across files, tracing imports/dependencies, analyzing change impact, reading large files, or needing project context. Prefer ABF tools over read_file, grep_search, semantic_search, and list_dir for multi-file workflows — they return pre-structured, token-efficient results in a single call.
npx skillsauth add TheRealFloatDev/AgentsBestFriend abfInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
ABF is a local MCP server that provides AI-optimized tools for navigating, searching, and analyzing code repositories. These tools return structured, compact results that save 50–80% of tokens compared to manually reading files.
Always prefer ABF tools when you need to:
Use native tools only when:
| Task | ABF Tool | Instead of |
|------|----------|------------|
| Orient in a new project | abf_project_overview | Reading README + listing directories + checking package.json |
| Find where something is defined | abf_search (exact mode) | grep_search |
| Find files related to a concept | abf_search (keyword mode) | Multiple semantic_search + grep_search calls |
| Read a specific function from a large file | abf_chunk with symbol name | read_file (which loads entire file or requires guessing line ranges) |
| List all exports of a file | abf_symbols | read_file and scanning manually |
| Understand what a file imports and who imports it | abf_dependencies | Multiple grep_search calls for import statements |
| Get multi-file context around one entry point | abf_context_bundle | 5–10 calls to read_file + abf_symbols + abf_dependencies |
| Find all usages of a function/class | abf_impact | grep_search with manual filtering |
| Understand project conventions | abf_conventions | Reading multiple config files manually |
| Search by file purpose/description | abf_file_summary | No native equivalent |
| Check git history or blame | abf_git | run_in_terminal with git commands |
1. abf_project_overview → architecture, tech stack, entry points
2. abf_conventions → coding style, patterns, naming
3. abf_search (keyword: "main topic") → find relevant files
1. abf_symbols (file) → see all exports/functions at a glance
2. abf_chunk (file, symbol: "name") → read just the function you care about
3. abf_dependencies (file) → see what it imports and who imports it
1. abf_context_bundle (entry file, depth: 2, include: "smart")
→ full source of entry + signatures of all dependencies in ONE call
2. If needed: abf_chunk to read specific dependency functions
1. abf_impact (symbol: "functionName") → all files and lines referencing it
2. abf_context_bundle (entry, focus_symbol: "functionName", reverse: true)
→ focused view of the function + its callers
- Know the exact name? → abf_search mode: "exact"
- Exploring a concept? → abf_search mode: "keyword"
- Describe what you need? → abf_file_summary (searches LLM-generated descriptions)
- Semantic similarity? → abf_search mode: "semantic" (requires Ollama)
When: Starting work on a project, or when asked "what does this project do?" Saves: Reading README + package.json + listing directories manually (3–5 calls → 1)
When: Looking for code, files, or patterns across the project Saves: Multiple grep_search or semantic_search calls
mode: "exact" — ripgrep-powered, supports regex, returns matching lines with contextmode: "keyword" — scores every file by keyword density, best for explorationmode: "semantic" — embedding similarity (requires Ollama + index with embeddings)path_filter to narrow scope (e.g. "src/**/*.ts")When: You need to understand a file in the context of its dependencies Saves: 5–10 calls to read_file + abf_symbols + abf_dependencies (biggest saver)
include: "smart" (default) — full source for entry, signatures for depsinclude: "signatures" — compact type signatures only (minimal tokens)include: "full" — full source code for all files up to depthfocus_symbol — only follows imports relevant to one function/classreverse: true — also shows who imports this filedepth: 0–4 — how far to follow the import graphWhen: You need to read a specific function/class from a file without loading the entire file Saves: read_file loading hundreds of irrelevant lines
symbol: "functionName" to get its full source code directlychunk_index to retrieve specific sectionsWhen: You need to see what a file exports without reading its full content Saves: read_file + mentally parsing the file structure
When: Tracing what a file imports or finding who depends on it Saves: Multiple grep_search calls for import statements
When: Assessing how widely a symbol is used before changing it Saves: grep_search + manual filtering of false positives
When: Searching by file purpose rather than exact code text Saves: No native equivalent — unique capability
abf_index action: summarize)When: Understanding project style before making changes Saves: Reading eslint, tsconfig, prettier, and other config files manually
When: Checking history, blame, or diffs Saves: Running git commands in terminal and parsing output
When: Managing the ABF index
status — check index healthrebuild — full re-indexupdate — incremental updatesummarize — generate LLM summaries (requires Ollama)When: Verifying ABF is running
tools
MANDATORY: AgentsBestFriend (ABF) MCP tools are connected and MUST be used for ALL code navigation, search, and analysis. NEVER use read_file, grep_search, semantic_search, or list_dir for exploring code — ABF tools are faster, return structured results, and use 50–80% fewer tokens. USE FOR: any file reading, code search, symbol lookup, dependency tracing, impact analysis, git history, or architecture questions. Load this skill IMMEDIATELY whenever working in a codebase.
tools
Use AgentsBestFriend (ABF) MCP tools for codebase navigation, search, and analysis instead of native file-reading tools. USE WHEN: exploring unfamiliar code, understanding architecture, searching across files, tracing imports/dependencies, analyzing change impact, reading large files, or needing project context. Prefer ABF tools over read_file, grep_search, semantic_search, and list_dir for multi-file workflows — they return pre-structured, token-efficient results in a single call.
tools
Use when work should span one or more detached tasks but still behave like one job with a single owner context. TaskFlow is the durable flow substrate under authoring layers like Lobster, ACPX, plugins, or plain code. Keep conditional logic in the caller; use TaskFlow for flow identity, child-task linkage, waiting state, revision-checked mutations, and user-facing emergence.
tools
# Lobster Lobster executes multi-step workflows with approval checkpoints. Use it when: - User wants a repeatable automation (triage, monitor, sync) - Actions need human approval before executing (send, post, delete) - Multiple tool calls should run as one deterministic operation ## When to use Lobster | User intent | Use Lobster? | | ------------------------------------------------------ | --------------------------