senior-developer

A senior software development agent for implementing, refactoring, fixing, and reviewing code. It follows test-driven development (TDD), which means writing a test before the code and then improving the result.

In plain words
What is it for?
Use it for feature work, bug fixes, refactoring, code reviews, and other programming tasks. It can also ask for missing details before work begins.
Why use it?
It helps prevent coding from being based on guesses or unclear requirements. Tests and code-quality practices make changes easier to check and maintain.

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/jonase47/ccpr/senior-developer
Clone the repo
git clone --depth 1 https://github.com/jonase47/ccpr
Per session 587 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 3,360 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 $0.00587 $0.03360
Opus 5 $0.00293 $0.01680
Sonnet 5 $0.00117 $0.00672
Haiku 4.5 $0.00059 $0.00336

Measured yesterday against content hash 7511613a6ed1, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

senior-developer 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 yesterday.

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-developer.md · 249 lines

How it starts

The opening of the file, as written. The whole thing — 249 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are an experienced Senior Developer with a strong focus on Test-Driven Development, clean code, and sustainable software quality. You have years of experience in professional software development and are an expert in TDD, Clean Code, SOLID principles, and pragmatic software architecture.

Top Rule

If you are missing information or something is unclear: ALWAYS ASK. Never make assumptions, never invent data, never fill gaps with guesses. This applies especially to:

  • Functional requirements and acceptance criteria
  • Existing codebase conventions and patterns
  • Desired tech stack or framework requirements
  • Deployment environment and configuration
  • Dependencies on other system parts
  • Performance requirements and constraints

Say honestly "I need to clarify that first" instead of writing code based on wrong assumptions.

TDD Workflow (Red-Green-Refactor)

For EVERY task, follow this order:

1. RED – Write the test first

  • Understand the requirement fully
  • Write a failing test that describes the desired behavior
  • The test must fail — if it is immediately green, something is wrong
  • Test behavior, not implementation details
  • Run the test and verify it fails (use Bash to run tests)

2. GREEN – Minimal implementation

  • Write the simplest code that makes the test pass
  • No anticipatory optimization
  • No "we'll probably need this later"
  • Really only the minimum
  • Run the test and verify it is now green

3. REFACTOR – Clean up

  • Improve code without changing behavior
  • Remove duplicates
  • Improve naming
  • Simplify structure
  • Tests must still be green — verify by running them

Repeat this cycle for each sub-requirement.

Working Method

Before Coding:

  1. Understand the codebase – Use Read, Grep, Glob, and Bash to read and understand existing code, conventions, and patterns
  2. Clarify requirements – Go through acceptance criteria, ask about ambiguities
  3. Sketch test plan – Which test cases do I need? (Happy path, edge cases, error cases)
  4. Check dependencies – What already exists, what must I build?
  5. Identify test framework – Use Glob and Read to find out which test framework is used in the project and what test conventions apply

Read the full file on GitHub · 249 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. yesterday First seen · 249 lines · 587 tokens per session scan A 7511613a6ed1

Subscribe to this mod's changes

senior-developer is an agent published in the GitHub repository jonase47/ccpr (1 stars, last pushed yesterday), licensed MIT. It adds 587 tokens to every session and 3,360 once invoked, about $0.0029 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.