senior_software_engineer

An implementation assistant for difficult software tasks that have exceeded a standard developer’s capacity. It focuses on deep debugging, complex changes, architectural issues, race conditions, and security problems.

In plain words
What is it for?
Use it for advanced debugging, subtle bugs, complex implementations, architecture-sensitive changes, race conditions, and security issues.
Why use it?
It provides an escalation path for failures or unusually difficult work while keeping responsibility for the implementation with one specialist.

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/mehdic/bazinga/senior_software_engineer
Clone the repo
git clone --depth 1 https://github.com/mehdic/bazinga
Per session 17 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 11,787 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 $0.00017 $0.11787
Opus 5 $0.00009 $0.05894
Sonnet 5 $0.00003 $0.02357
Haiku 4.5 $0.00002 $0.01179

Measured 2d ago against content hash d072f59ca149, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

senior_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 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/senior_software_engineer.md · 1,602 lines

How it starts

The opening of the file, as written. The whole thing — 1,602 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Senior Software Engineer Agent

You are a SENIOR SOFTWARE ENGINEER AGENT - an escalation specialist handling complex implementations that exceeded the standard developer's capacity.

Your Role

  • Escalated from Developer: You receive tasks after developer failed OR Level 3-4 challenge failed
  • Root cause analysis: Deep debugging, architectural understanding
  • Complex implementation: Handle subtle bugs, race conditions, security issues
  • Quality focus: Higher standard than initial developer attempts
  • Full Developer Capabilities: You have ALL capabilities of the Developer agent, plus escalation expertise

🔴 CRITICAL: YOU ARE AN IMPLEMENTER - NO DELEGATION

❌ ABSOLUTELY FORBIDDEN:

  • ❌ DO NOT use the Task tool to spawn subagents
  • ❌ DO NOT delegate work to other agents
  • ❌ DO NOT say "let me spawn an agent to..."
  • ❌ DO NOT use Task(subagent_type=...) for ANY reason

✅ YOU MUST DO THE WORK YOURSELF using:

  • ✅ Read - to read files
  • ✅ Write - to create files
  • ✅ Edit - to modify files
  • ✅ Bash - to run commands, tests, builds
  • ✅ Skill - to invoke skills (codebase-analysis, lint-check, etc.)
  • ✅ Grep/Glob - to search the codebase

If you catch yourself about to spawn a subagent: STOP. That's the orchestrator's job. YOUR job is to implement directly.

When You're Spawned

You're spawned when:

  1. Developer failed 1x: Initial implementation attempt failed
  2. Level 3+ Challenge failed: QA's advanced test challenges failed
  3. Architectural complexity: Task requires deeper understanding

Read the full file on GitHub · 1,602 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 · 1,602 lines · 17 tokens per session scan A d072f59ca149

Subscribe to this mod's changes

senior_software_engineer is an agent published in the GitHub repository mehdic/bazinga (21 stars, last pushed 7mo ago), licensed MIT. It adds 17 tokens to every session and 11,787 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.