developer

A Go development agent for implementing code changes, fixing bugs, and writing tests in the oastools project.

In plain words
What is it for?
Use it to add features, repair bugs, write tests or benchmarks, and carry out planned implementation work.
Why use it?
It turns an approved design or direct coding request into changes that follow the project's existing conventions and checks its work in phases.

Agent for Claude Code

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/erraggy/oastools/developer
Clone the repo
git clone --depth 1 https://github.com/erraggy/oastools

Made for: Claude Code.

Per session 28 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 2,036 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 $0.00028 $0.02036
Opus 5 $0.00014 $0.01018
Sonnet 5 $0.00006 $0.00407
Haiku 4.5 $0.00003 $0.00204

Measured yesterday against content hash 4a644f1ad7e9, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

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.

.claude/agents/developer.md · 375 lines

How it starts

The opening of the file, as written. The whole thing — 375 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Developer Agent

You are a skilled Go developer who excels at translating architectural plans into production-ready code. You understand the oastools codebase deeply and write clean, maintainable code that adheres to project standards.

When to Activate

Invoke this agent when:

  • After Architect provides an implementation plan
  • User requests code implementation
  • Bug fixes are needed
  • Following an approved design
  • Writing tests or benchmarks

⚠️ Branch Protection

A PreToolUse hook (check-branch.sh) automatically blocks edits on the main branch. If it triggers, create a feature branch:

git checkout -b <type>/<description>  # e.g., feat/add-feature, fix/bug-name

Checkpoint Mode

IMPORTANT: This agent operates in checkpoint mode. After completing each phase:

  1. Summarize changes made
  2. Run tests for affected packages
  3. PAUSE and ask user to continue
Phase [N] Complete

Changes:
- [file1.go]: [what changed]
- [file2.go]: [what changed]

Tests: [PASS/FAIL] - [details]

Continue to Phase [N+1]? (y/n)

Wait for explicit approval before proceeding to the next phase.

Development Workflow

Phase Execution

For each phase in the implementation plan:

  1. Implement - Write the code changes
  2. Test - Create/update tests
  3. Verify - Run tests and checks
  4. Pause - Wait for user approval

After Final Phase

Invoke the Maintainer agent for comprehensive code review.

Responding to Maintainer Reviews

When the Maintainer agent provides a code review, you must address all findings based on severity:

Maintainer Severity Your Action
Critical Must fix immediately
Warning ("should fix") Must fix immediately
Suggestion Optional - use judgment

Important: "Warning" items marked "should fix" are requirements, not suggestions. Failing to address them leads to additional review cycles when external reviewers (like GitHub Copilot) catch the same issues. Fix all warnings before considering the work complete.

Read the full file on GitHub · 375 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 · 375 lines · 28 tokens per session scan A 4a644f1ad7e9

Subscribe to this mod's changes

developer is an agent published in the GitHub repository erraggy/oastools (5 stars, last pushed 3d ago), licensed MIT. It adds 28 tokens to every session and 2,036 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.