opencode-ollama-steroids: Skill for OpenCode

.opencode/skills/test-first-agent-loop/SKILL.md

test-first-agent-loop is a skill for OpenCode from pillaiharish/opencode-ollama-steroids. It costs 31 tokens per session (276 once invoked), scanned A, original, Apache-2.0.

A development workflow that requires agents to validate their work and record the results honestly. It covers builders and reviewers, with checks such as tests, builds, route checks, browser checks, and security scans when relevant.

In plain words
What is it for?
Use it during implementation, code review, or approval to choose validation commands, stop when checks fail, repeat failed checks, and document exact results.
Why use it?
It prevents claims of success without evidence and makes skipped checks, failures, fixes, and remaining risks visible before signoff.

Skill for OpenCode

Written for OpenCode: installed under .opencode/.

This is pillaiharish/opencode-ollama-steroids's own configuration. It tells OpenCode how to work on opencode-ollama-steroids itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything opencode-ollama-steroids configures →

Reuse

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.

Copy the file
curl -O https://raw.githubusercontent.com/pillaiharish/opencode-ollama-steroids/main/.opencode/skills/test-first-agent-loop/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/pillaiharish/opencode-ollama-steroids

Made for: OpenCode.

Wrote 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.

agentmods badge for test-first-agent-loop

README.md
[![agentmods](https://agentmods.dev/badge/skills/pillaiharish/opencode-ollama-steroids/test-first-agent-loop.svg)](https://agentmods.dev/skills/pillaiharish/opencode-ollama-steroids/test-first-agent-loop)
Your own site
<a href="https://agentmods.dev/skills/pillaiharish/opencode-ollama-steroids/test-first-agent-loop"><img src="https://agentmods.dev/badge/skills/pillaiharish/opencode-ollama-steroids/test-first-agent-loop.svg" alt="Measured on agentmods" height="20"></a>
Per session 31 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 276 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.00031 $0.00276
Opus 5 $0.00015 $0.00138
Sonnet 5 $0.00006 $0.00055
Haiku 4.5 $0.00003 $0.00028

Measured 6d ago against content hash 02533552733e, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

test-first-agent-loop 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 6d 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/skills/test-first-agent-loop/SKILL.md · 42 lines

What it actually says

Test First Agent Loop

Use this skill when a prompt requires implementation, review, or signoff.

Builder Requirements

The builder must:

  • identify required validation commands before claiming completion;
  • run unit tests, build/static generation, smoke checks, domain checks, route checks, browser tests, and security scans when relevant;
  • stop feature work when validation fails;
  • fix failures only inside approved scope;
  • rerun failed commands and the full suite when practical;
  • document exact commands, results, failures, fixes, and remaining risks.

Reviewer Requirements

The reviewer must block signoff when:

  • validation commands are missing;
  • output is summarized without evidence;
  • tests are superficial or unrelated;
  • generated output changed without review;
  • screenshots are missing for UI work that needs browser evidence;
  • security/redaction checks were skipped before publication.

Honest Reporting

Use precise language:

  • passed only when the command completed successfully;
  • failed when the command returned non-zero or produced blocking errors;
  • not run when skipped, with a reason;
  • not applicable only when the category genuinely does not apply.

Never hide failures to make a prompt look complete.

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. 6d ago First seen · 42 lines · 31 tokens per session scan A 02533552733e

Subscribe to this mod's changes

test-first-agent-loop is a skill published in the GitHub repository pillaiharish/opencode-ollama-steroids (5 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 31 tokens to every session and 276 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.