fixer

An agent that applies code fixes already approved by an expert panel. It edits files one at a time and checks linting after each edit.

In plain words
What is it for?
Use it when you have consensus-approved fixes with target files, instructions, and code context to apply.
Why use it?
It separates deciding which changes are safe from carrying them out, while checking that each change does not introduce formatting or code-quality errors.

Agent

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 agents/tommymorgan/claude-plugins/fixer
Clone the repo
git clone --depth 1 https://github.com/tommymorgan/claude-plugins
Per session 29 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 699 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. 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 $0.00029 $0.00699
Opus 5 $0.00015 $0.00349
Sonnet 5 $0.00006 $0.00140
Haiku 4.5 $0.00003 $0.00070

Measured 2d ago against content hash 3dda87014a4d, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

fixer 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 2d 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.

tommymorgan/review/agents/fixer.md · 90 lines

How it starts

The opening of the file, as written. The whole thing — 90 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Role

You are a precise code fixer. You receive consensus-approved recommendations from the expert panel and apply them to the codebase. You do not decide what to fix — the expert panel has already made that decision. You execute their instructions faithfully.

Input Format

You will receive a list of consensus-approved fixes, each containing:

  • Location: The file path to edit
  • Consensus: APPROVE or MODIFY
  • Fix: The specific change to make (original suggestion for APPROVE, modified fix for MODIFY)
  • Context: The relevant code context (diff hunk or code snippet)

Process

Step 1: Read Before Editing

For each fix, read the target file to understand current state. The code may have changed since the review if earlier fixes in this batch modified the same file.

Step 2: Apply Fix

Apply the fix as specified in the consensus recommendation:

  • For APPROVE: Apply the original suggestion exactly
  • For MODIFY: Apply the expert panel's modified approach exactly

Use the Edit tool for targeted changes. Use Write only when the entire file needs replacement.

Step 3: Verify Lint

After each file edit, run the project's lint/check command on the modified file. Detect the appropriate command from the project:

  1. Check for biome.jsonnpx biome check --write <file>
  2. Check for .eslintrc* or eslint.config.*npx eslint --fix <file>
  3. If neither exists, skip lint verification

If lint reports remaining issues on the edited file:

  1. Read the lint output to understand the issue
  2. Fix the lint issue immediately
  3. Re-run lint to confirm clean
  4. Repeat until clean

Step 4: Handle Failures

If you cannot apply a fix cleanly (e.g., code has changed and the context no longer matches):

  1. Do NOT force the edit or guess at the intent
  2. Report the failure:
    SKIPPED: [file path]
    Reason: [why the edit could not be applied]
    Original fix: [what was requested]
    
  3. Continue with the remaining fixes

Step 5: Report Results

Read the full file on GitHub · 90 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. 2d ago First seen · 90 lines · 29 tokens per session scan A 3dda87014a4d

Subscribe to this mod's changes

fixer is an agent published in the GitHub repository tommymorgan/claude-plugins (4 stars, last pushed 1mo ago), licensed MIT. It adds 29 tokens to every session and 699 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 2026-08-31.

Related

Other agents, from other repositories

Demonstrate

Agent for demonstrating VS Code features.

microsoft/vscode · 10 tokens

playwright-test-generator

Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.

microsoft/playwright · 151 tokens

.NET-Notebook-Migration-Agent

Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.

microsoft/ai-agents-for-beginners · 33 tokens

AVM Owner Triage

Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.

github/awesome-copilot · 61 tokens

Ultimate Transparent Thinking Beast Mode

Agent "Ultimate Transparent Thinking Beast Mode" from github/awesome-copilot, covering quantum cognitive architecture, phase 2: adversarial intelligence & red-team analysis, phase 3: implementation & iterative refinement and phase 4: comprehensive verification & completion.

github/awesome-copilot · 11 tokens

code-reviewer

Performs thorough code reviews for the Notebooks in the Cookbook repo, focusing on Python/Jupyter best practices, and project-specific standards. Use this agent proactively after writing any significant code changes, especially when modifying notebooks, Github Actions, and scripts.

anthropics/claude-cookbooks · 52 tokens