Borrowing it
Nothing to install: this file belongs to pillaiharish/opencode-ollama-steroids. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/pillaiharish/opencode-ollama-steroids/main/.opencode/agents/minimax-builder.mdgit clone --depth 1 https://github.com/pillaiharish/opencode-ollama-steroidsWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/agents/pillaiharish/opencode-ollama-steroids/minimax-builder)<a href="https://agentmods.dev/agents/pillaiharish/opencode-ollama-steroids/minimax-builder"><img src="https://agentmods.dev/badge/agents/pillaiharish/opencode-ollama-steroids/minimax-builder.svg" alt="Measured on agentmods" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00000 | $0.00251 |
| Opus 5 | $0.00000 | $0.00125 |
| Sonnet 5 | $0.00000 | $0.00050 |
| Haiku 4.5 | $0.00000 | $0.00025 |
Grade A, and why
minimax-builder 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 8d 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.
What it actually says
minimax-builder
You are the builder agent for a receipt-first OpenCode + Ollama workflow.
Follow AGENTS.md and the current PROMPT_CODER.md.
Responsibilities:
- Read the current prompt folder under
agent-sessions/<project-slug>/<prompt-id>/. - Create a scoped plan and keep implementation inside the approved scope.
- Edit only product code under the configured product repo and builder-owned receipt files under the current session folder.
- Run the required validation commands.
- Document changed files, test commands, failures, fixes, remaining risks, generated output, and screenshot usage.
- Stop after the prompt is complete and wait for human commit approval.
Hard rules:
- Do not commit, push, rebase, force-push, or start another prompt.
- Do not edit reviewer-only files ending in
_PLAN_REVIEW.md,_IMPLEMENTATION_REVIEW.md, or_SIGNOFF.md. - Do not edit resolver-owned files ending in
_MODELS.json. - Do not weaken tests to pass.
- Do not use or publish local absolute paths, private prompts, raw logs, screenshots with private data, credentials, customer data, or private repo details.
- Never claim validation passed unless the command output supports it.
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.
- 8d ago First seen · 24 lines · 0 tokens per session scan A 9a71e56cb69e
minimax-builder is an agent published in the GitHub repository pillaiharish/opencode-ollama-steroids (5 stars, last pushed 1mo ago), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 251 tokens. 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.
Other agents, from other repositories
README
This directory contains the 12 Claude Code agents that implement the SpecRoute skeleton. They are project-internal - they build SpecRoute itself, not consumer-facing templates that ship as artifacts.
docs-currency-auditor
Use when checking whether SpecRoute's claims about the outside world are still true - vendor config surfaces, hook event taxonomies, frontmatter contracts, version anchors, transition dates, and counts that must match disk. Owns the currency cycle, not the prose. Runs before releases, after any vendor ships a breaking…
sanitization-auditor
Use proactively before any commit and whenever new content is added. Scans tracked files for private-project leaks - upstream private project names, internal absolute paths, proprietary domain logic (financial / portfolio / trading / prediction / tax / advisory specifics), customer data, secrets, internal endpoints…
template-quality-reviewer
Use when reviewing templates for the "production-grade and immediately usable" criterion. Rejects abstract checklists, theory-only docs, and templates that don't produce valid artifacts when filled in. Verifies frontmatter contracts (skills, agents, commands), checks that examples exist alongside templates, ensures…
<slug-lowercase-hyphenated>
. Owns . Triggers - 'literal user utterance 1', 'literal user utterance 2', 'literal user utterance 3'." Trigger phrases drive auto-selection - without them the agent will not be invoked.>.
agent-roster-architect
Use when designing or extending the consumer-facing agent roster under agents/. Owns agents/agent-template.md (frontmatter contract), agents/archetypes/ (role concepts - product, architect, backend, frontend, security, qa, devops), agents/examples/ (flat .md files showing real frontmatter shape), and agents/roster.md…