fix-master-enhanced

A command for diagnosing and fixing broken software with small, targeted code changes.

In plain words
What is it for?
Use it for errors, broken forms, failing API endpoints, and other specific software problems.
Why use it?
It helps find the actual cause of a problem and avoid changing working parts of the code by mistake.

Command for Claude Code

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add commands/agentsea/flashbacker/fix-master-enhanced
Clone the repo
git clone --depth 1 https://github.com/agentsea/flashbacker

Made for: Claude Code.

Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,185 The whole file, excluding the scripts and references it only reads on demand.
Security scan B 1 finding. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5 $0.00000 $0.01185
Opus 5 $0.00000 $0.00593
Sonnet 5 $0.00000 $0.00237
Haiku 4.5 $0.00000 $0.00119

Measured 3d ago against content hash 697b4c83b5c2, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade B, and why

fix-master-enhanced scanned grade B with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 3d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Unrestricted tool accessmediumExcessive agency

A wildcard tool grant or "run any command" leaves no least-privilege boundary at all.

allowed-tools: "*"
templates/.claude/commands/fb/fix-master-enhanced.md · 155 lines

How it starts

The opening of the file, as written. The whole thing — 155 lines — stays where its author put it; the contents beside it link to each section on GitHub.

🔧 Surgical Fix Master Protocol

Master software engineer specializing in surgical, precise fixes for broken software. This protocol enforces proven methodologies for fixing code systematically and efficiently.

Usage

/fb:fix-master <problem description or error details>

Examples:

  • /fb:fix-master TypeError: Cannot read property 'id' of undefined in user.service.ts:42
  • /fb:fix-master Login form validation not working on mobile devices
  • /fb:fix-master API endpoint returns 500 error when processing large files

Core Principles (READ FIRST - Apply Rigorously)

🎯 Surgical Precision: Zero in on exact root cause. Make minimal, targeted changes that fix only what is broken while preserving all working functionality.

📖 READ Before Write: Always search existing codebase for similar functionality. Never assume functions don't exist - use Grep, Read, and Glob tools extensively.

✋ Manual Validation First: Prove functionality works through hands-on validation. Do NOT write e2e test for functionality that is still in progress.

🚫 No Placeholders: Never create empty/placeholder files or "TODO" implementations. Only implement complete, working solutions within established architecture.

🔄 One Problem, One Fix: Avoid scope creep. Don't refactor unrelated code while fixing specific issues.


Surgical Fix Workflow

Phase 1-5: Core Fix Implementation

1. Problem Isolation

  • Read error/issue completely, locate failure point, map code path, identify root cause

2. Code Analysis

  • Read surrounding code, check for existing solutions, validate assumptions, plan minimal change

3. Surgical Implementation

  • Make targeted changes, maintain consistency, preserve interfaces, test incrementally

4. Manual Validation

  • Test fix manually

5. Initial Testing

  • Create focused tests only after proven functionality, avoid broad test suites

Phase 6: Agent Validation (For Complex/Large Fixes Only)

When to Use Agents:

  • Fix touches multiple files (3+ files)
  • Complex logic changes or architectural impact
  • TypeScript/type system modifications
  • Performance-critical code changes

Read the full file on GitHub · 155 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 3d ago First seen · 155 lines · 0 tokens per session scan B 697b4c83b5c2

Subscribe to this mod's changes

fix-master-enhanced is a command published in the GitHub repository agentsea/flashbacker (57 stars, last pushed 7mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,185 tokens. A static security scan graded it B with 1 finding (unrestricted tool access). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.