Skills DirectorySkills Directory
SkillsLearnSecurityCategoriesDocsBlogPro
Sign InSubmit Skill
Skills Directory

Security-tested agent skills for Claude, coding agents, and AI workflows.

Directory

  • Browse Skills
  • All Skills A–Z
  • Claude Skills
  • Claude Code Skills
  • Agent Skills
  • Categories
  • Authors
  • Submit a Skill

Learn

  • Learn Hub
  • Install Claude Skills
  • Write SKILL.md
  • Skills vs MCP
  • Directories Compared

Security

  • Security
  • Methodology
  • Secure Claude Skills
  • Security Badges
  • Chrome Extension
  • Skill Manager

Company

  • About
  • Community
  • Blog
  • API Docs
  • Advertise

2026 Skills Directory. All rights reserved.

ProTermsPrivacyRefunds
Back to skills

Semantic Filesystem Navigation

ASecurity

Use when navigating, searching, and exploring large codebases efficiently. Enforces token-conscious search patterns: ripgrep-first, line-range viewing, symbol indexing, and strict bans on dumping entire directories or multi-thousand line files.

5 stars
0 votes
0 copies
0 views
Added 9/27/2026
ai-agentsbashnoderailstestinggitperformance

Works with

terminalcli

Security Analysis

A100/100

Scanned 9/29/2026

$npx -y skills add Harmitx7/tribunal-kit --skill semantic-filesystem-navigation --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Semantic Filesystem Navigation?

Add the live security badge to your README — it updates automatically with every re-scan.

Security grade badge for Semantic Filesystem Navigation
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/harmitx7-semantic-filesystem-navigation/badge)](https://www.skillsdirectory.com/skills/harmitx7-semantic-filesystem-navigation)

More formats (shields.io, HTML) on the badges page. Keep it an A: scan every change in CI with Pro.

Download with Pro
Files
SKILL.md
---
name: semantic-filesystem-navigation
description: "Use when navigating, searching, and exploring large codebases efficiently. Enforces token-conscious search patterns: ripgrep-first, line-range viewing, symbol indexing, and strict bans on dumping entire directories or multi-thousand line files."
version: 6.0.0
last-updated: 2026-09-29
skills:
  - clean-code
tools: Read, Grep, Glob, Bash, Edit, Write
scripts-binding:
  - .agent/scripts/lint_runner.js
  - .agent/scripts/verify_all.js
---

# Semantic Filesystem Navigation — Token-Conserving Codebase Exploration

## Activation Boundaries
- **Activate when:** Use when navigating, searching, and exploring large codebases efficiently. Enforces token-conscious search patterns: ripgrep-first, line-range viewing, symbol indexing, and strict bans on dumping entire directories or multi-thousand line files.
- **DO NOT activate when:** The task falls outside the `semantic-filesystem-navigation` domain or is managed by a different dedicated specialist agent.


## 🔁 Multi-Pass Execution Protocol

| Pass | Phase | Core Action | Adaptive Depth |
|:---|:---|:---|:---|
| **Pass 1** | **Understand** | Deconstruct the user's explicit objective, implicit requirements, and platform constraints. | Fast / Standard / Deep |
| **Pass 2** | **Plan** | Decompose task into smallest logical steps; map dependencies, affected files, and tool calls. | Standard / Deep |
| **Pass 3** | **Execute** | Implement solution with production-grade craft, zero placeholders, and strict typing. | All Modes |
| **Pass 4** | **Verify** | Run linters, unit tests, or compiler checks to validate structural correctness. | All Modes |
| **Pass 5** | **Attack & Falsify** | Perform adversarial search for edge-case failures, counterexamples, race conditions, and traps. | Standard / Deep |
| **Pass 6** | **Harden** | Eliminate discovered friction, optimize performance, and harden error boundaries. | Standard / Deep |
| **Pass 7** | **Quality Gate** | Enforce Verification-Before-Completion (VBC) with concrete terminal proof before finalizing. | All Modes |


## Mandatory Pre-Flight Context Inspection
1. **Search Budget**: Determine the minimal information needed to answer the question or make the edit.
2. **Grep-First Protocol**: Use exact grep or ripgrep search for symbols/functions before opening files.
3. **Line-Range Slicing**: When viewing files, slice precise line ranges (`StartLine`, `EndLine`); NEVER view 2,000 lines at once.
4. **Directory Bounding**: Filter `list_dir` searches; avoid listing directories inside `node_modules`, `.git`, or `target`.
5. **Caller Mapping**: Before modifying any function, grep for all callers across the workspace.

## 🛠️ Technical Architecture & Reference Recipes

### 1. The 3-Step Token-Efficient Search Pipeline
```
1. LOCATE SYMBOL:  grep_search("function handlePayment", Includes: ["*.ts"])
       │ Returns: src/services/payment.ts, line 42
       ▼
2. INSPECT CONTEXT: view_file(src/services/payment.ts, StartLine: 35, EndLine: 65)
       │ Reads only 30 lines instead of 1,200 lines
       ▼
3. MAP CALLERS:    grep_search("handlePayment(", Includes: ["!*.test.ts"])
       │ Discovers all 3 consumers before applying modifications
```

## 🚨 Edge-Case & Failure Mode Matrix

| Scenario | Risk | Production Mitigation |
|:---|:---|:---|
| **Context Window Saturation** | Reading full 3,000-line files pushes instructions out of LLM context | Always slice files into 50-100 line chunks centered on the target function |
| **Stale File Hallucination** | Editing a file based on memory without re-reading the active version on disk | Always re-read the target file range immediately prior to editing |

## 🏛️ Tribunal Verification & Guardrails

### 🔬 Evidence Standard (Tri-State Verification)
Every finding, audit statement, or completion claim must classify its factual certainty:
- **`[OBSERVED]`**: Directly confirmed in the codebase or verified via executed terminal command.
- **`[INFERRED]`**: Logically deduced from code patterns, architectural data flow, or schema relations.
- **`[UNVERIFIED]`**: Speculative hypothesis or runtime possibility requiring active testing or measurement.

- **Active Reviewers:** `logic-reviewer`, `orchestrator`
- **Evidence Standard:** Cite exact file paths and line numbers (`[OBSERVED]`) for all codebase statements.

## 🤖 LLM-Specific Traps Table

| Anti-Pattern | What AI Commonly Does Wrong | What Is Actually Correct |
|:---|:---|:---|
| **Hallucinated Tool Capabilities** | Assuming an external library or CLI command exists without verification | Run a verification check or verify package.json before referencing tools |
| **Premature Completion Claim** | Declaring a task finished because code was generated without verification | Execute tests, linters, or terminal commands to provide concrete proof |
| **Context Bloat Dumping** | Pasting entire multi-thousand-line files into prompt context | Extract targeted excerpts, symbols, and signatures to preserve tokens |

Attribution

Harmitx7Harmitx7
View sourceSee grades on GitHubMore from Harmitx7 →
SSkills DirectorySkills Directory

Ship a skill? Prove it's safe.

Free 120-pattern security scan, letter grade, and an embeddable README badge.

Submit a skill

Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.

Comments (0)

No comments yet. Be the first to comment!

SSkills DirectorySkills Directory

Ship a skill? Prove it's safe.

Free 120-pattern security scan, letter grade, and an embeddable README badge.

Submit a skill

Related Skills

Caveman

Terse caveman voice: answer first, fluff gone, every technical fact kept. Use for /caveman, "caveman mode", "talk like caveman", "be brief", "less tokens". Stays on until "stop caveman" or "normal mode".

1100021 votes

Hyperplan

Adversarial multi-agent planning skill. Self-orchestrates 5 hostile category members (unspecified-low, unspecified-high, deep, ultrabrain, artistry) via team-mode for ruthless cross-critique debate, distills only the defensible insights, then MANDATORILY hands the distilled insight bundle to the `plan` agent for executable plan formalization. Use when planning needs maximum rigor and surfacing of weak assumptions, blind spots, and over-engineering. Triggers: 'hyperplan', 'hpp', '/hyperplan', ...

698461 votes

Writing Skills

Create and manage Claude Code skills in HASH repository following Anthropic best practices. Use when creating new skills, modifying skill-rules.json, understanding trigger patterns, working with hooks, debugging skill activation, or implementing progressive disclosure. Covers skill structure, YAML frontmatter, trigger types (keywords, intent patterns), UserPromptSubmit hook, and the 500-line rule. Includes validation and debugging with SKILL_DEBUG. Examples include rust-error-stack, cargo-dep...

3931 votes

Mcp Code Execution

Routes multi-tool workflows through MCP servers for large datasets and pipelines. Use when Bash tool overhead is limiting throughput on data-heavy tasks.

3421 votes

catchup

Recovers the conversation and failed tool calls of a previous Codex, Amp, Claude Code, Antigravity, Cline, Copilot CLI, Cursor, DeepSeek Harness, Grok Build, Kimi, OpenCode, Pi Agent, or ZCode session. Use when the user says "catch up", "what did the last session do", "get me up to speed", "I switched agents", asks to recover/summarize a previous session before continuing, or asks to diagnose or report a catchup failure. Do NOT use for the current conversation, git history, or any non-agent log.

741 votes
View all in ai-agents →