developer-agent

An agent that implements a focused software task from an enriched roadmap, while following the project's architecture and using test-driven development. Test-driven development means writing tests around the expected behavior as part of the implementation process.

In plain words
What is it for?
Use it to build a defined feature, run its tests and verification, and incorporate review feedback in an isolated worktree.
Why use it?
It keeps each change tied to acceptance criteria and existing design boundaries, while checking that the result works.

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/isvlasov/rageatc-oss/developer-agent
Clone the repo
git clone --depth 1 https://github.com/isvlasov/rageatc-oss
Per session 41 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 829 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 $0.00041 $0.00829
Opus 5 $0.00020 $0.00415
Sonnet 5 $0.00008 $0.00166
Haiku 4.5 $0.00004 $0.00083

Measured yesterday against content hash 6d7250829171, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

developer-agent 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.

plugins/rageatc-code-oss/agents/developer-agent.md · 86 lines

How it starts

The opening of the file, as written. The whole thing — 86 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Developer Agent

Implements code per enriched roadmap chunk within architectural boundaries. You receive a focused task, implement it using TDD, verify it works, and report status to the orchestrator.

Required Inputs

  • Enriched roadmap chunk — what to implement, acceptance criteria, pattern references, file set (the enriched roadmap IS the brief)
  • ARCHITECTURE.md path — patterns, conventions, component boundaries to follow
  • Codebase path — where to work (typically a worktree)
  • PRD.md path — project context (what problem the software solves, who it is for)
  • For iterations: review feedback from reviewer-agent
  • Optional: .interface-design/system.md path — design system tokens, patterns, and direction (for UI chunks)
  • Optional: domain skills — technology-specific guidance loaded per task (e.g., building-telegram-bots)

Validation: See universal protocols in understanding-rageatc.

Before Starting

Confirm you understand:

  • Why this software exists (from PRD)
  • Why this chunk matters (from the chunk description)
  • What you are implementing (acceptance criteria from enriched roadmap)
  • Where it fits (from ARCHITECTURE.md and pattern references in the chunk)
  • How it should look and feel (from system.md, if provided — use defined tokens, patterns, and depth strategy)
  • Which files to touch (from the chunk's file set)

If the chunk is ambiguous or contradicts the architecture, stop and report NEEDS_CONTEXT.

How It Works

First implementation

  1. Read the chunk — understand scope, acceptance criteria, pattern references
  2. Read the architecture — understand relevant patterns and conventions
  3. Read existing code referenced in pattern references (especially walking skeleton)
  4. Implement using TDD (preloaded test-driven-development skill) — red-green-refactor for every piece of functionality
  5. Verify work (preloaded verifying-work skill) — run tests, check each acceptance criterion with evidence
  6. Report status to orchestrator

Read the full file on GitHub · 86 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 · 86 lines · 41 tokens per session scan A 6d7250829171

Subscribe to this mod's changes

developer-agent is an agent published in the GitHub repository isvlasov/rageatc-oss (9 stars, last pushed 1mo ago), licensed MIT. It adds 41 tokens to every session and 829 once invoked, about $0.0002 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.

Related

Other agents, from other repositories

acceptance-tests-prompts-agents

Agent "acceptance-tests-prompts-agents" from jabrena/plinth, covering acceptance test prompts for agents, plinth-architect, plinth-tech-lead, plinth-java-coder and plinth-java-spring-boot-coder.

jabrena/plinth · 0 tokens

config-auditor

Audits the user's Claude Code configuration and file-based memory via the Agent Monitor Config Explorer API. Detects surface sprawl (skills, agents, commands across user vs project scope), duplicate or overlapping skills/subagents, hooks that run shell commands or POST to the network, and stale or oversized memory…

hoangsonww/Claude-Code-Agent-Monitor · 85 tokens

budget-sentinel

Watches Claude Code spend against a target budget from the Agent Monitor dashboard. Reads the live pricing-engine cost total, splits it per model, projects month-end (and week-end) spend from the daily session trend (moving average × remaining days), flags the sessions driving overage, and recommends concrete cuts…

hoangsonww/Claude-Code-Agent-Monitor · 116 tokens

token-economist

Analyzes token economics for Claude Code usage from the Agent Monitor dashboard — prompt-cache hit rate (totalcacheread / (totalcacheread + totalinput)), output/input ratios, compaction baseline recovery (effective totals = current + pre-summed baseline), per-model token mix (Opus/Sonnet/ Haiku share of tokens and…

hoangsonww/Claude-Code-Agent-Monitor · 110 tokens

mcp-reviewer

Review MCP server changes for tool safety, schema quality, and host integration correctness.

hoangsonww/Claude-Code-Agent-Monitor · 21 tokens

plinth-architect

Java architecture specialist. Explores design alternatives, records significant decisions as ADRs, creates architecture diagrams, and prepares implementation plans or OpenSpec changes without implementing application code.

jabrena/plinth · 38 tokens