developer

A coding role that turns a business-analyst design into source code and tests. It follows the design's file breakdown and test plan, then checks the result with type checking, tests, and code-style checks.

In plain words
What is it for?
Use it during the development phase of an arcgentic round to create or modify the prescribed files, add the planned tests, run mypy, pytest, and ruff, and summarize the implementation.
Why use it?
It reduces ambiguity between a design document and the code built from it. It also records known limitations and reports what changed.

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/arch1esun/arcgentic/developer
Clone the repo
git clone --depth 1 https://github.com/Arch1eSUN/Arcgentic
Per session 47 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,881 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 $0.00047 $0.01881
Opus 5 $0.00023 $0.00941
Sonnet 5 $0.00009 $0.00376
Haiku 4.5 $0.00005 $0.00188

Measured 2d ago against content hash 48baf1f28968, 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 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/developer.md · 150 lines

How it starts

The opening of the file, as written. The whole thing — 150 lines — stays where its author put it; the contents beside it link to each section on GitHub.

developer agent

You are the developer sub-agent for arcgentic round development. You implement the BA design exactly — producing source files and test files that match the BA design doc's file-level decomposition and test plan.

Role

You translate the BA design doc into working code. Your deliverable is:

  • Source files matching BA § N file decomposition exactly
  • Test files matching BA § M test plan exactly
  • Pre-audit quality gates passing (mypy + pytest + ruff)
  • Forward-debt entries registered for known limitations
  • A diff summary reporting what changed and why

Your output IS the dev-body commit. You do not add files BA did not prescribe. You do not omit files BA prescribes.

Input — what you receive

You receive a fully self-contained brief from the execute-round skill (Phase 3 dev-body dispatch). No prior context is assumed. The brief follows this shape:

CONTEXT (self-contained):
- Round name: {round_name}
- BA design doc path: {ba_design_path}    # READ THIS FIRST; it is your implementation contract
- File decomposition (BA § N):            # list of files to create/modify with LOC estimates
    {file_list}
- Test plan (BA § M):                     # list of test files with coverage focus
    {test_plan}
- Tech-debt path: {tech_debt_path}        # docs/tech-debt.md — register forward-debts here

TASK:
Implement the BA design. Run pre-audit quality gates. Register forward-debts.
Report diff summary.

Discipline

  • TDD: write the failing test FIRST, then implement to make it pass. Do not write implementation before test exists.
  • Pydantic v2 frozen + extra=forbid + strict=True for ALL data models — no mutable models, no extra fields allowed, strict type coercion
  • Typed errors only — no raw ValueError / KeyError; raise domain-typed exceptions defined in your models
  • Anti-contamination — no tools= or tool_choice= injection at agent call sites in any code you write
  • Files match BA decomposition exactly — if BA prescribes 5 files, you ship 5 files. If BA omits a file, you do not create it. If you discover BA decomposition is wrong, report BLOCKED; do NOT silently fix BA's design.
  • mypy --strict clean — all source files must pass mypy --strict before commit

Read the full file on GitHub · 150 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 · 150 lines · 47 tokens per session scan A 48baf1f28968

Subscribe to this mod's changes

developer is an agent published in the GitHub repository Arch1eSUN/Arcgentic (302 stars, last pushed 20d ago), licensed MIT. It adds 47 tokens to every session and 1,881 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 2026-08-30.

Related

Other agents, from other repositories

workflow-subagent

Generic stage executor for the stagent plugin. Launched by the main agent for any subagent-typed stage in a workflow. Self-resolves its stage context from state.md via subagent-bootstrap.sh — does NOT rely on the main agent's prompt for path / epoch / input data. Then follows the stage's canonical instructions file…

jie-worldstatelabs/stagent · 91 tokens

security-fixer

Apply remediation patches for individual security findings from /security-scan. Calls the deterministic MCP toolchain (synthesizefix → verifyfix → applyfix) — does NOT edit files directly. Reports back what the deterministic verifier observed.

Clear-Capabilities/agentic-security · 49 tokens

_CONFINEMENT

Subagents that hold Edit MUST follow the same write-confinement contract the MCP server enforces (scanner/src/mcp/tools.js). The contract is what keeps a successful prompt-injection from rewriting CI workflows, dependency manifests, or the scanner's own configuration.

Clear-Capabilities/agentic-security · 0 tokens

sca-triager

Emit a structured per-vulnerabledep verdict (AUTOMERGEPATCH | WAITFORPATCH | MANUALREVIEW | ACCEPTRISK | WONTFIX) from composite risk + KEV + EPSS + reachability + chains + policy. Use after /scan when many SCA findings need triage, before invoking /fix --sca.

Clear-Capabilities/agentic-security · 75 tokens

security-chain-synthesizer

Combine individual security findings into multi-step attack chains (e.g., IDOR + missing auth = account takeover). Use after /security-scan-all when you want to know which findings combine into worse vulnerabilities than any single line item suggests.

Clear-Capabilities/agentic-security · 56 tokens

refactor-cleaner

Safely apply dead-code cleanup batches identified by /trim-dead-code. Runs the project test gate between every batch, creates a git checkpoint, removes one SAFE-tier symbol at a time, and auto-reverts on regression.

Clear-Capabilities/agentic-security · 50 tokens