/4-fix
**Navigation**: [← Step 3: Plan](3-plan.md) | [Main Workflow](../workflow-steps.md) | [Step 5: Validate →](5-validate.md)
$ npx -y skills add athola/claude-night-market --agent claude-codeHow it fires
How this command gets triggered: by you, by Claude, or both.
- Fires itselfClaude auto-loads it when your prompt matches the work.
- You can call itInvoke it directly when you want it.
- Slash command
/4-fix
Context preview
What this command does when you run it.
**Navigation**: [← Step 3: Plan](3-plan.md) | [Main Workflow](../workflow-steps.md) | [Step 5: Validate →](5-validate.md)
Command definition
4-fix.mdStep 4: Fix (Apply Changes)
> **Navigation**: [← Step 3: Plan](3-plan.md) | [Main Workflow](../workflow-steps.md) | [Step 5: Validate →](5-validate.md)
**Purpose**: Apply code changes systematically.
**Skip when**: Just need validation (already made changes manually).
4.1 Apply Fixes Systematically
# For each approved fix:
1. Read code context (±20 lines)
2. Apply fix with Edit tool
3. Verify no new issues introduced
4. Mark as completed
4.2 Commit Changes
- **Single**: "Address PR review feedback"
- **Separate**: One commit per fix category
- **Manual**: Stage changes, user commits
Commit message hygiene (MANDATORY)
Load `../../shared/output-hygiene.md` before writing the message. Inline fallback if that module is absent:
- **Contract A (characters)**: no `"+"` used as a conjunction (use
`and`; keep `+` in versions and code), no em-dash `—`, no prose `--`, no arrows `->` / `→` as connectors, no smart quotes `“ ” ‘ ’`. Replace with plain punctuation.
- **Contract B (subject matter)**: if a fix removed AI slop, describe
the change by its reader-facing effect. Name neither the AI origin nor the specific marker removed. Do NOT write `remove AI slop`, `de-slop`, `AI-generated content`, `AI phrasing`, `replace em-dashes`, or `remove smart quotes`. For example `docs: clarify wording`, not `style: replace em-dashes with colons`.
**Step 4 Output**: Applied fixes, commits created
---
> **Next**: [Step 5: Validate (Test & Verify) →](5-validate.md)
Read more
Step 4: Fix (Apply Changes)
> **Navigation**: [← Step 3: Plan](3-plan.md) | [Main Workflow](../workflow-steps.md) | [Step 5: Validate →](5-validate.md)
**Purpose**: Apply code changes systematically.
**Skip when**: Just need validation (already made changes manually).
4.1 Apply Fixes Systematically
# For each approved fix: 1. Read code context (±20 lines) 2. Apply fix with Edit tool 3. Verify no new issues introduced 4. Mark as completed
4.2 Commit Changes
- **Single**: "Address PR review feedback"
- **Separate**: One commit per fix category
- **Manual**: Stage changes, user commits
Commit message hygiene (MANDATORY)
Load `../../shared/output-hygiene.md` before writing the message. Inline fallback if that module is absent:
- **Contract A (characters)**: no `"+"` used as a conjunction (use
`and`; keep `+` in versions and code), no em-dash `—`, no prose `--`, no arrows `->` / `→` as connectors, no smart quotes `“ ” ‘ ’`. Replace with plain punctuation.
- **Contract B (subject matter)**: if a fix removed AI slop, describe
the change by its reader-facing effect. Name neither the AI origin nor the specific marker removed. Do NOT write `remove AI slop`, `de-slop`, `AI-generated content`, `AI phrasing`, `replace em-dashes`, or `remove smart quotes`. For example `docs: clarify wording`, not `style: replace em-dashes with colons`.
**Step 4 Output**: Applied fixes, commits created
---
> **Next**: [Step 5: Validate (Test & Verify) →](5-validate.md)
A plugin marketplace for Claude Code. Install only the plugins you need to run git workflows, code review, spec-driven development, and autonomous agents from inside your Claude Code session.
Other commands on claude-night-market.
- /aggregate-logs
Generate LEARNINGS.md from skill execution logs.
Open command - /analyze-skill
Analyze skill file complexity metrics and generate modularization recommendations for splitting or progressive loading.
Open command - /bulletproof-skill
Harden skills against rationalization and bypass behaviors
Open command - /context-report
Generate context optimization report for skill directories
Open command - /create-command
Create slash commands with brainstorming and best practices
Open command - /create-hook
Create hooks with brainstorming and security-first design
Open command

