Run any Skill in Manus with one click

harness-fix-durability

Stars27

Forks5

UpdatedJune 21, 2026 at 22:59

Use when /harness is invoked or fixing a harness rule violation. Matches fix durability to severity (nit=memory, wrong=CLAUDE.md, silent-sub=hook+commitment).

Installation

Install with Codex or Claude Copy this prompt, paste it into Codex, Claude, or another assistant, and let it review the skill page and install it for you.

Run Skill in Manus

Source

jleechanorg

jleechanorg/claude-commands

View GitHub Repository View Creator Repositories

Download

Run Skill in Manus

SKILL.md

readonly

name	harness-fix-durability
description	Use when /harness is invoked or fixing a harness rule violation. Matches fix durability to severity (nit=memory, wrong=CLAUDE.md, silent-sub=hook+commitment).

Harness fix durability must match violation severity

Violation severity	Minimum fix durability
Nitpick/style	Memory
Wrong approach	CLAUDE.md instruction
Commitment integrity	Hook (PreToolUse/PostToolUse)
Silent substitution	Hook + commitment file
Data loss / security	Hook + CI gate

When running /harness, match the fix to the severity. Instructions alone cannot prevent commitment violations — they need hooks.

More from this repository

same repository

advice

jleechanorg/claude-commands

Token-efficient second opinion slash command /advice. Extracts decision point + artifact (≤150 lines), then fans out in parallel: (1) Opus subagent reviewer with fallback chain codex→agy→cursor, (2) /research on the decision topic, (3) /secondo multi-model opinion. Use instead of advisor() which ships the full conversation uncached.

2026-06-2427

ponytail

jleechanorg/claude-commands

Lazy senior-dev mode — the seven-rung ladder that decides whether to write code at all, whether to reuse code that already exists, and whether to prefer stdlib/platform/installed deps over a new dependency. Use before writing any code, every PR diff, every fix, every feature. Source attribution included.

2026-06-2427

runtime-activation-claim

jleechanorg/claude-commands

Use when making any "X is enabled" / "feature X works" / "cache works" claim in a running session — requires runtime probe output from the standard harness startup path, NOT a launchd/cron test that explicitly sets the activation env var.

2026-06-2427

self-hosted-runner-preflight

jleechanorg/claude-commands

Pre-flight checklist for self-hosted runner failures. Use when investigating low disk, missing runner, or stuck Green Gate on the jleechanorg/worldarchitect.ai fleet. Always verifies host-level container state, not just GitHub API.

2026-06-2427

test-tui-claude-feature-via-cmux

jleechanorg/claude-commands

When asked to verify whether a Claude Code feature works (especially slash commands, dialogs, pickers, status indicators), spawn a real interactive TUI session in cmux — never use `claude --print "/feature"` as a test, because --print is non-interactive and will always return "isn't available in this environment" regardless of whether the feature actually works.

2026-06-2427

ao-agent-shorthands

jleechanorg/claude-commands

Read ~/.hermes/agent-orchestrator.yaml BEFORE declaring an --agent <X> value unsupported. Lists plugin shorthands (wafer, minimax, agy).

2026-06-2127

Run any Skill with one click