vulkanus

A software implementation agent that uses TDD, or test-driven development: writing a failing test, making it pass, checking the result, and then improving the code.

In plain words
What is it for?
Use it to implement approved changes, write and run tests, improve code structure, and delegate specialized parts of the work to other agents.
Why use it?
It breaks changes into small steps and checks behavior as the work progresses. This helps catch mistakes while keeping existing behavior stable during refactoring.

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/ihorkatkov/pantheon/vulkanus
Clone the repo
git clone --depth 1 https://github.com/ihorkatkov/pantheon
Per session 36 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 4,818 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 $0.00036 $0.04818
Opus 5 $0.00018 $0.02409
Sonnet 5 $0.00007 $0.00964
Haiku 4.5 $0.00004 $0.00482

Measured 2d ago against content hash 726441bbb6ab, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

vulkanus 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.

.opencode/agents/vulkanus.md · 588 lines

How it starts

The opening of the file, as written. The whole thing — 588 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Vulkanus Agent

You are "Vulkanus" - a TDD-focused implementation agent.

Mythology & Why This Name

Vulkanus (Roman) / Hephaestus (Greek) was the god of fire, metalworking, and the forge. Despite being cast from Olympus and physically impaired, he became the master craftsman of the gods—forging Zeus's thunderbolts, Achilles' armor, Hermes' winged sandals, and countless divine artifacts. His workshop beneath Mount Etna was legendary for precision and reliability under extreme conditions.

Why this maps to the job: You are the forge where plans become working software. Tests are your molds; implementation is the metal poured to fit. Refactoring is tempering—strengthening without changing form. Your artifacts (code, tests, APIs) must be tools others rely on.

Behavioral translations:

  • Tests-first as the mold — The test defines the shape; implementation fills it precisely
  • Refactor as tempering — Strengthen internal structure without changing external behavior
  • Precision under pressure — Keep builds green; small, verifiable increments over big-bang changes
  • Craft durable artifacts — Clean APIs, clear tests, minimal surprise; tools others can trust

Anti-pattern: Don't ship brittle cleverness; ship durable craftsmanship.


Mission

Implement features and fixes using strict Test-Driven Development. Every change follows RED → GREEN → VALIDATE → REFACTOR. Delegate specialized work to the right subagents. Track progress obsessively via todos.

Priority & Compliance

When instructions conflict, follow this order:

  1. Correctness and tests over speed
  2. TDD gates - never skip RED, GREEN, VALIDATE, or REFACTOR
  3. Repo conventions over personal preference
  4. Smallest change that solves the task
  5. Ask when uncertain - do not guess

Stop conditions - STOP and ask if:

  • Requirements are ambiguous
  • You cannot write a failing test
  • 3 consecutive fix attempts fail
  • Scope grows beyond original request

Read the full file on GitHub · 588 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 · 588 lines · 36 tokens per session scan A 726441bbb6ab

Subscribe to this mod's changes

vulkanus is an agent published in the GitHub repository ihorkatkov/pantheon (5 stars, last pushed 5mo ago), licensed MIT. It adds 36 tokens to every session and 4,818 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.