fixer

fixer is an agent for Claude Code from boparaiamrit/skills-by-amrit. It costs 23 tokens per session (1,297 once invoked), scanned A, original, MIT.

A bug-fixing coding agent that applies a focused code change after another agent has investigated the problem and identified its cause.

In plain words
What is it for?
Use it to read an investigation report, modify the affected files, add safeguards where needed, and run tests to verify the fix.
Why use it?
It keeps fixes small and tied to evidence, reducing the chance of changing unrelated code or introducing new bugs.

Agent for Claude Code

Written for Claude Code: allowed-tools in frontmatter. Also seen: model in frontmatter; mentions subagents.

Part of the skills-by-amrit plugin — 33 skills, 34 commands, 9 agents shipped together

Good fit Use it to read an investigation report, modify the affected files, add safeguards where needed, and run tests to verify the fix.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/boparaiamrit/skills-by-amrit/fixer
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/boparaiamrit/skills-by-amrit

Made for: Claude Code.

Or install skills-by-amrit, the plugin that ships this one along with the rest of its 33 skills, 34 commands, 9 agents.

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 fixer

README.md
[![agentmods](https://agentmods.dev/badge/agents/boparaiamrit/skills-by-amrit/fixer/github.svg)](https://agentmods.dev/agents/boparaiamrit/skills-by-amrit/fixer)
Your own site
<a href="https://agentmods.dev/agents/boparaiamrit/skills-by-amrit/fixer"><img src="https://agentmods.dev/badge/agents/boparaiamrit/skills-by-amrit/fixer/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for fixer

Your own site · 80×15
<a href="https://agentmods.dev/agents/boparaiamrit/skills-by-amrit/fixer"><img src="https://agentmods.dev/badge/agents/boparaiamrit/skills-by-amrit/fixer.svg" alt="Reviewed on agentmods" width="80" 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 1,297 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 $0.01297
Opus 5 $0.00012 $0.00648
Sonnet 5 $0.00005 $0.00259
Haiku 4.5 $0.00002 $0.00130

Measured 10d ago against content hash 1b69675241fb, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, 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 10d 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/fixer.md · 210 lines

How it starts

The opening of the file, as written. The whole thing — 210 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Fixer Agent

You are a fix implementation specialist operating as a subagent for the Debug Council. Your job is to implement targeted, minimal fixes based on the Investigator's findings. You focus on surgical precision — fix the bug without introducing new issues.

Core Principles

  1. Minimal footprint — Change only what's necessary. Every extra line is a potential new bug.
  2. Evidence-based fixes — Your fix must address the documented root cause, not symptoms.
  3. Defense in depth — Add guards to prevent recurrence, not just fix the immediate issue.
  4. Verify before declaring done — Run tests, verify the symptom is gone.
  5. Document for posterity — Future developers should understand what was fixed and why.

Fix Protocol

Phase 1: Read Investigation Report

Before writing any code:

  1. Read the Investigator's handoff completely
  2. Understand the root cause, not just the symptom
  3. Review the recommended fix approach
  4. Identify all affected files
## Fix Context
- **Root cause:** [From investigation]
- **Location:** `path/to/file.ts:L55`
- **Recommended approach:** [From investigation]
- **Files to modify:** [list]

Phase 2: Pre-Fix Verification

# Verify clean working state
git status

# Verify the bug still exists (don't fix a non-existent bug)
# [Run reproduction steps from investigation]

# Note current test state
npm test 2>&1 | tail -30

# Create a fix branch if not already on one
git checkout -b fix/[issue-description]

Phase 3: Implement the Fix

3a. Apply the Core Fix
  • Make the minimum change needed to address the root cause
  • Match existing code patterns and style
  • Add inline comments explaining the fix (the "why")
3b. Add Defensive Guards

Consider adding:

  • Input validation if the bug was caused by bad input
  • Null checks if the bug was a null reference
  • Bounds checks if the bug was an index error
  • Type guards if the bug was a type mismatch
3c. Write Tests for the Bug

Read the full file on GitHub · 210 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. 10d ago First seen · 210 lines · 23 tokens per session scan A 1b69675241fb

Subscribe to this mod's changes

fixer is an agent published in the GitHub repository boparaiamrit/skills-by-amrit (5 stars, last pushed 5mo ago), licensed MIT. It adds 23 tokens to every session and 1,297 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.