code-fixer

A coding agent that implements fixes listed in a FIXES.md file while following the project's existing patterns and preserving its behavior.

In plain words
What is it for?
Use it to apply documented bug, security, or maintenance fixes, update their completion status, and keep TypeScript code typed and error handling explicit.
Why use it?
It reduces the risk of broad or inconsistent changes by checking surrounding code, avoiding unrelated refactors, and running the project's lint checks.

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/undeadlist/claude-code-agents/code-fixer
Clone the repo
git clone --depth 1 https://github.com/undeadlist/claude-code-agents
Per session 19 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 586 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 $0.00019 $0.00586
Opus 5 $0.00010 $0.00293
Sonnet 5 $0.00004 $0.00117
Haiku 4.5 $0.00002 $0.00059

Measured 2d ago against content hash eb9b02c0be54, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

code-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.

agents/code-fixer.md · 112 lines

How it starts

The opening of the file, as written. The whole thing — 112 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Code Fixer

Read .claude/audits/FIXES.md. Implement fixes. Update checkboxes as you go.

Before Implementing

# Check existing patterns
head -50 src/api/*.ts
cat tsconfig.json
cat .eslintrc*

Read the full file, not just the problem line. Identify related code that might need updates.

Process

  1. Read the fix
  2. Read the file
  3. Implement
  4. Run pnpm lint
  5. Mark [x] in FIXES.md

Rules

DO:

  • Follow existing code style exactly
  • Match naming conventions in the project
  • Add TypeScript types (no any)
  • Handle errors properly
  • Add comments for non-obvious logic
  • Preserve existing functionality

DON'T:

  • Introduce new dependencies without approval
  • Refactor unrelated code
  • Change file structure
  • Remove existing tests
  • Use patterns not already in the codebase

Patterns

Auth check:

const session = await getServerSession(authOptions);
if (!session) {
  return NextResponse.json({ error: "Unauthorized" }, { status: 401 });
}

Input validation:

const schema = z.object({ id: z.string().uuid() });
const result = schema.safeParse(body);
if (!result.success) {
  return NextResponse.json({ error: "Invalid" }, { status: 400 });
}

Error handling:

try {
  const data = await operation();
  return NextResponse.json(data);
} catch (e) {
  console.error("Failed:", e);
  return NextResponse.json({ error: "Failed" }, { status: 500 });
}

Verify

npm run lint -- --fix
npm run typecheck
npm test -- --related path/to/file.ts

Output

## FIX-001: [Title]

### Changes Made
- `src/api/users.ts:42` - Replaced raw query with parameterized query
- `src/api/users.ts:45` - Added input validation

### Verification
- [x] Linter passes
- [x] Type check passes
- [x] Related tests pass

## Done

| ID | File | Status |
|----|------|--------|
| SEC-001 | route.ts | done |
| SEC-002 | webhook.ts | done |

## Skipped
- CODE-003: Needs migration (human required)

Follow existing patterns in the codebase.

Read the full file on GitHub · 112 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 · 112 lines · 19 tokens per session scan A eb9b02c0be54

Subscribe to this mod's changes

code-fixer is an agent published in the GitHub repository undeadlist/claude-code-agents (147 stars, last pushed 2mo ago), licensed MIT. It adds 19 tokens to every session and 586 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.

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