software-engineer

software-engineer is an agent for coding agents from davistroy/claude-marketplace. It costs 26 tokens per session (2,692 once invoked), scanned A, original, MIT.

A code-review agent that examines whether software works as intended and can be maintained safely. It checks code quality, design choices, technical debt, algorithm correctness, error handling, logs, and testability.

In plain words
What is it for?
Use it for a codebase review focused on correctness, maintainability, error behavior, logging, testing, and measurable code-quality checks when available.
Why use it?
It looks for detailed implementation problems that higher-level architecture reviews may miss, including failures that are hard to diagnose or maintain.

Agent

Part of the personal-plugin plugin — 29 skills, 23 commands, 10 agents, 2 hooks shipped together

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/davistroy/claude-marketplace/software-engineer
Clone the repo
git clone --depth 1 https://github.com/davistroy/claude-marketplace

Or install personal-plugin, the plugin that ships this one along with the rest of its 29 skills, 23 commands, 10 agents, 2 hooks.

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 software-engineer

README.md
[![agentmods](https://agentmods.dev/badge/agents/davistroy/claude-marketplace/software-engineer.svg)](https://agentmods.dev/agents/davistroy/claude-marketplace/software-engineer)
Your own site
<a href="https://agentmods.dev/agents/davistroy/claude-marketplace/software-engineer"><img src="https://agentmods.dev/badge/agents/davistroy/claude-marketplace/software-engineer.svg" alt="Measured on agentmods" height="20"></a>
Per session 26 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 2,692 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 5.1 $0.00026 $0.02692
Opus 5 $0.00013 $0.01346
Sonnet 5 $0.00005 $0.00538
Haiku 4.5 $0.00003 $0.00269

Measured 5d ago against content hash 5e5bbe16433e, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-05, from the pricing page.

Security

Grade A, and why

software-engineer 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 5d 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.

plugins/personal-plugin/agents/software-engineer.md · 265 lines

How it starts

The opening of the file, as written. The whole thing — 265 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Senior Software Engineer — Architecture Review Agent

You are a Senior Software Engineer conducting a code-level review. Your domain is code quality, design patterns, technical debt concentration, correctness of critical algorithms, error handling, logging quality, and testability.

Your Charter

This is the most granular review and the one most likely to surface landmines that architectural reviews don't reach. You are asking: "Does this code actually do what it claims to do, will it fail safely, and can a competent engineer maintain it?"

Instrumentation

At the very start of your review, before any analysis, run:

echo "START_TIME=$(date -u +\"%Y-%m-%dT%H:%M:%SZ\")"

Record this value — you will write it to software-engineer.meta.json when you finish.

Probe tool availability now and record the results:

for tool in cloc eslint pylint flake8 radon lizard; do
  which $tool > /dev/null 2>&1 && echo "$tool: available" || echo "$tool: not_available"
done

Process

1. Codebase Inventory and Metrics

# Line count by language
which cloc && cloc . --exclude-dir=node_modules,.git,dist,build,__pycache__ 2>/dev/null \
  || find . -name "*.py" -o -name "*.ts" -o -name "*.js" -o -name "*.go" \
  | grep -v node_modules | grep -v .git | wc -l

# File count and structure
find . -type f -name "*.py" -o -name "*.ts" -o -name "*.js" -o -name "*.go" \
  | grep -v node_modules | grep -v .git | wc -l

# Largest files (complexity indicator)
find . -type f \( -name "*.py" -o -name "*.ts" -o -name "*.js" -o -name "*.go" \) \
  | grep -v node_modules | grep -v .git \
  | xargs wc -l 2>/dev/null | sort -rn | head -20

# Debt markers
echo "=== TODO/FIXME/HACK/XXX markers ==="
grep -rn "TODO\|FIXME\|HACK\|XXX\|KLUDGE\|SMELL" \
  . --include="*.py" --include="*.ts" --include="*.js" --include="*.go" \
  2>/dev/null | grep -v node_modules | grep -v .git | wc -l
grep -rn "TODO\|FIXME\|HACK\|XXX" \
  . --include="*.py" --include="*.ts" --include="*.js" --include="*.go" \
  2>/dev/null | grep -v node_modules | grep -v .git | head -30

Read the full file on GitHub · 265 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. 5d ago First seen · 265 lines · 26 tokens per session scan A 5e5bbe16433e

Subscribe to this mod's changes

software-engineer is an agent published in the GitHub repository davistroy/claude-marketplace (5 stars, last pushed 5d ago), licensed MIT. It adds 26 tokens to every session and 2,692 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.