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

Knowledge Graph

ASecurity

Use when Understands the architecture, risk blast radius, and dependencies of the codebase without token bloat. Now includes Context Snapshots for 27x token reduction.

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

Security Analysis

A100/100

Scanned 9/27/2026

$npx -y skills add Harmitx7/tribunal-kit --skill knowledge-graph --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Knowledge Graph?

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

Security grade badge for Knowledge Graph
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/harmitx7-knowledge-graph-tribunal-kit/badge)](https://www.skillsdirectory.com/skills/harmitx7-knowledge-graph-tribunal-kit)

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: knowledge-graph
description: "Use when Understands the architecture, risk blast radius, and dependencies of the codebase without token bloat. Now includes Context Snapshots for 27x token reduction."
version: 5.0.0
last-updated: 2026-09-13
skills:
  - codebase-design
  - architecture
  - fabel-protocol
tools: Read, Grep, Glob, Bash, Edit, Write
scripts-binding:
  - .agent/scripts/graph_builder.js
  - .agent/scripts/graph_zoom.js
  - .agent/scripts/verify_all.js
  - .agent/scripts/lint_runner.js
---

# /graph — Knowledge Graph Skill v3.0

---

## 🛠️ Technical Architecture & Reference Recipes

---

## The Token Reduction Protocol (Option C)

**DO NOT READ RAW SOURCE FILES IF A SNAPSHOT EXISTS.**
Reading raw project files wastes up to 50,000 tokens per edit. You must use the pre-computed Context Snapshots instead. These snapshots contain the file's content, resolved imports, dependent files, and risk scores all in one JSON blob.

## Pre-Flight Checklist

- [ ] Have I run the Macro Mapper to generate the latest Context Snapshots?
- [ ] Am I reading from `.agent/history/snapshots/` instead of directly grepping the project?
- [ ] Have I respected the `blastRadius` before modifying a file?

## Execution Protocol

1. **Step 1: The Macro Map (Blast Radius & Snapshot Engine)**
   Execute the graph builder to map module boundaries and compute downstream risk scores. This also automatically generates a Context Snapshot for every file.

   ```bash
   node .agent/scripts/graph_builder.js
   ```

2. **Step 2: Read Context Snapshots (MANDATORY)**
   Instead of using `cat` or `grep` to read a file, read its snapshot. Snapshots are stored in `.agent/history/snapshots/` with slashes replaced by `__`.
   _Example:_ To edit `src/middleware/auth.js`, read `.agent/history/snapshots/src__middleware__auth.js.json`.

   This gives you:
   - The full source code of the target file.
   - The exported symbols of every file it imports.
   - The list of files that depend on it.
   - Its exact `riskScore` and `blastRadius`.

3. **Step 3: Interactive Visualization (For Humans)**
   The user can view a sleek, zero-dependency visualizer of the codebase. You can prompt them to run:

   ```bash
   npx tribunal-kit graph
   ```

4. **Step 4: The Micro Zoom (Legacy Street View)**
   If a snapshot is unavailable or too large, you can fall back to the zoomer to get its structural skeleton:
   ```bash
   node .agent/scripts/graph_zoom.js --focus <path_to_file>
   ```

## VBC Protocol (Verification-Before-Completion)

You are explicitly forbidden from guessing or "hallucinating" what functions, props, or variables exist inside a file. You MUST read the Context Snapshot (or use `graph_zoom.js`) to verify a component's exact signature before you attempt to call it, mock it, or rewrite it. Always respect the Blast Radius Risk Score before deleting or mutating files.

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 →