focused-fix

focused-fix is a command for Claude Code from alirezarezvani/claude-skills. It costs 23 tokens per session (234 once invoked), scanned A, original, MIT.

A structured repair process for fixing an entire software feature or module. It first maps the code and its connections, finds confirmed causes, then applies and tests fixes in order.

In plain words
What is it for?
Use it when a feature is broken or needs a broad repair across code, configuration, tests, logs, and integrations.
Why use it?
It prevents quick changes from missing related files, dependencies, tests, or users of the code. The investigation must be completed before repairs begin.

Command for Claude Code

Written for Claude Code: $ARGUMENTS substitution.

Good fit Use it when a feature is broken or needs a broad repair across code, configuration, tests, logs, and integrations.

Compare 6 commands from other repositories ↓
Install with agentmods
npx agentmods add commands/alirezarezvani/claude-skills/focused-fix
About the project

claude-skills is a large collection of reusable skills, commands, plugins, and supporting resources for coding agents across engineering, business, research, compliance, and productivity work. It is used by people who want agents such as Claude Code, Codex, Gemini CLI, or Cursor to follow specialized workflows. The catalogue contains selected skills and settings from the collection.

alirezarezvani/claude-skills · 25,635 stars · on GitHub · alirezarezvani.medium.com

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.

Clone the repo
git clone --depth 1 https://github.com/alirezarezvani/claude-skills

Made for: Claude Code.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for focused-fix

README.md
[![agentmods](https://agentmods.dev/badge/commands/alirezarezvani/claude-skills/focused-fix.svg)](https://agentmods.dev/commands/alirezarezvani/claude-skills/focused-fix)
Your own site
<a href="https://agentmods.dev/commands/alirezarezvani/claude-skills/focused-fix"><img src="https://agentmods.dev/badge/commands/alirezarezvani/claude-skills/focused-fix.svg" alt="Measured on agentmods" height="20"></a>
Per session 23 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 234 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.00023 $0.00234
Opus 5 $0.00012 $0.00117
Sonnet 5 $0.00005 $0.00047
Haiku 4.5 $0.00002 $0.00023

Measured 8d ago against content hash 382d54f8cd28, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

focused-fix scanned grade A with 0 findings 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 8d 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.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

Origin

Copies of this mod

1 near-identical copy found in the catalogue:

.claude/commands/focused-fix.md · 18 lines

What it actually says

Systematically repair the feature/module at $ARGUMENTS using the focused-fix 5-phase protocol.

If $ARGUMENTS is empty, ask which feature/module to fix.

Read engineering/focused-fix/SKILL.md and execute ALL 5 phases IN ORDER:

  1. SCOPE — Map the feature boundary (all files, entry points, internal files)
  2. TRACE — Map inbound + outbound dependencies across the entire codebase
  3. DIAGNOSE — Check code, runtime, tests, logs, config. Assign risk labels (HIGH/MED/LOW). Confirm root causes with evidence.
  4. FIX — Repair in order: deps → types → logic → tests → integration. One fix at a time, test after each. 3-strike escalation if fixes cascade.
  5. VERIFY — Run all feature tests + consumer tests. Summarize changes.

Iron Law: No fixes before completing Phase 3. No exceptions.

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. 8d ago First seen · 18 lines · 23 tokens per session scan A 382d54f8cd28

Subscribe to this mod's changes

focused-fix is a command published in the GitHub repository alirezarezvani/claude-skills (25,635 stars, last pushed 8d ago), licensed MIT. It adds 23 tokens to every session and 234 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.