Agent skill

the-honoured-one

Forces the AI to fully load context and read relevant files before performing complex, multi-file tasks, architectural changes, or debugging. Prevents acting on assumptions.

Nick44,414★ · +328/wk · 1 repos on radarProfile →
claude-codecodexcursorMIT
Install
npx skills add sickn33/agentic-awesome-skills --skill the-honoured-one --agent claude-code

Same command for any agent — swap --agent for codex, cursor, copilot.

Facts
Files in the skill folder: 1
SKILL.md size: 8 KB
Bundled scripts: none
Path: skills/the-honoured-one/SKILL.md
Open the folder on GitHub →
Where it comes from
Stars: 44,414 · +328 this week
Language: Python
Read our review of the source →

Weekly change comes from our own snapshots, not the repository page — it measures attention, not adoption.

From the SKILL.md

# the-honoured-one — Full Context Load Protocol ## Overview > Gojo at full power means all six eyes open — everything visible, nothing assumed, no blind spots. The Honoured One doesn't act on guesses. This skill enforces the same: the AI must earn the right to act by reading and understanding first. The most common AI coding failure is **confident wrongness** — the AI proposes or implements something based on how it assumes the code is structured, not how it actually is. It gets the architecture wrong, uses a pattern inconsistent with the rest of the codebase, or integrates with a module it never actually opened. This skill eliminates that failure mode by making context-loading mandatory before any action. --- ## When to Use This Skill - Use when modifying multiple files in an existing codebase - Use when designing or modifying a system component - Use when adding a feature that integrates with existing code - Use when debugging a system or component the AI has not yet read - Use when the AI would need to assume how existing code is structured - **DO NOT** use for isolated single-file tasks where the file has already been read --- ## How It Works ### PHASE 1 — Context Audit When gi

What's inside
Steps it walks through
  1. Overview
  2. When to Use This Skill
  3. How It Works
  4. PHASE 1 — Context Audit
  5. PHASE 2 — Mandatory Read Pass
  6. PHASE 3 — Orientation Statement
  7. PHASE 4 — Confidence Gate
  8. Self-Ask Before Acting
  9. Hard Rules (Never Violated)
  10. What This Skill Prevents
  11. Quick Reference
  12. Trigger Phrases
  13. Examples
  14. Best Practices
More from agentic-awesome-skills
All skills →
About this skill
What does the the-honoured-one skill do?

Forces the AI to fully load context and read relevant files before performing complex, multi-file tasks, architectural changes, or debugging. Prevents acting on assumptions.

How do I install it?

Run `npx skills add sickn33/agentic-awesome-skills --skill the-honoured-one --agent claude-code` — it drops the skill into your project so the agent can pick it up. Swap the --agent value for codex, cursor or copilot if you use one of those.

Where does this skill come from?

From sickn33/agentic-awesome-skills, a repository with 44,414 stars. We read it straight from the repository tree rather than a submitted listing, so what you see here is what is actually published.

Is a popular skill a good skill?

Not necessarily. Stars measure attention, not adoption — a repository can trend for a week and be abandoned. That is why we show the weekly change from our own snapshots next to the total, instead of a single flattering number.

Keep going