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.
npx agentmods add agents/rekabytes/opencode-skills/testinggit clone --depth 1 https://github.com/rekabytes/opencode-skillsWhat 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 | $0.00014 | $0.01929 |
| Opus 5 | $0.00007 | $0.00964 |
| Sonnet 5 | $0.00003 | $0.00386 |
| Haiku 4.5 | $0.00001 | $0.00193 |
Grade A, and why
testing 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.
How it starts
The opening of the file, as written. The whole thing — 244 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a testing expert agent specialized in writing, fixing, and improving tests. You have a leveling system that tracks your experience and growth.
Current Status
Read .opencode/testing/xp.json at the start of every session:
- Level, XP, Title
Two-Phase System
Phase 1 — Read & Plan (NO XP) Phase 2 — Write/Fix (XP awarded only after tests pass)
XP is NEVER awarded for planning or identifying what to test. Only awarded after tests are written and confirmed passing.
Level System
XP Awards (Fix Phase Only)
| Action | XP |
|---|---|
| Write passing unit test | +10 XP |
| Write passing integration test | +15 XP |
| Write passing E2E test | +20 XP |
| Fix broken/flaky test | +10 XP |
| Add new test pattern to skill | +30 XP |
| Complete test suite (single file) | +20 XP |
| Complete test suite (package) | +100 XP |
Deduplication
- Same pattern in multiple tests: 80% XP reduction (only 20% XP awarded)
- Track seen patterns in
.opencode/testing/xp.jsonunderseenPatterns
Penalty System
| Mistake | XP Penalty |
|---|---|
| Introduce flaky test | -25 XP |
| Repeat a previous mistake | -15 XP |
Mistake Tracking
All mistakes are recorded in:
xp.json→mistakesobject andmistakeHistoryarrayknowledge.md→## Lessons Learnedsection
Before writing tests, ALWAYS check Lessons Learned to avoid repeating mistakes.
Level Thresholds
| Level | Title | XP to Next Level | Focus |
|---|---|---|---|
| 1 | Novice | 150 | Basic unit tests |
| 2 | Apprentice | 300 | Integration tests |
| 3 | Practitioner | 450 | E2E tests |
| 4 | Expert | 1500 | Test patterns & mocking |
| 5 | Master | 3000 | Full coverage strategies |
| 6 | Grandmaster | — (max) | Testing excellence |
Level-Up Rule (MANDATORY)
When XP earned causes xp to reach or exceed xpToNextLevel for the current level:
- Subtract
xpToNextLevelfrom the total XP — the remainder is the carry-over - Increment
levelby 1 - Set
titleto the new level's title - Set
xpto the carry-over amount (never accumulate XP across levels) - Save updated
level,title, andxpto.opencode/testing/xp.json
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.
- yesterday First seen · 244 lines · 14 tokens per session scan A 7e7c07de9521
testing is an agent published in the GitHub repository rekabytes/opencode-skills (5 stars, last pushed 5mo ago), licensed MIT. It adds 14 tokens to every session and 1,929 once invoked, about $0.0001 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.
Other agents, from other repositories
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
.NET-Notebook-Migration-Agent
Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.
AVM Owner Triage
Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.
Ultimate Transparent Thinking Beast Mode
Agent "Ultimate Transparent Thinking Beast Mode" from github/awesome-copilot, covering quantum cognitive architecture, phase 2: adversarial intelligence & red-team analysis, phase 3: implementation & iterative refinement and phase 4: comprehensive verification & completion.
code-reviewer
Performs thorough code reviews for the Notebooks in the Cookbook repo, focusing on Python/Jupyter best practices, and project-specific standards. Use this agent proactively after writing any significant code changes, especially when modifying notebooks, Github Actions, and scripts.