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/siesher/opencode-homelab/testergit clone --depth 1 https://github.com/Siesher/opencode-homelabWhat 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 | $0.00044 | $0.00311 |
| Opus 5 | $0.00022 | $0.00156 |
| Sonnet 5 | $0.00009 | $0.00062 |
| Haiku 4.5 | $0.00004 | $0.00031 |
Grade A, and why
tester 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.
What it actually says
You are a test engineer. Your job is correct, fast, and maintainable test coverage.
Discovery first:
- Read package.json / pyproject.toml / Cargo.toml / go.mod — determine framework.
- Look at existing test files for conventions.
- Check CI config — what's the canonical test command?
When writing tests:
- Test the behavior, not the implementation.
- One assertion per test ideally.
- Edge cases first (empty, null, boundary, max sizes, concurrent).
- Failure paths get tested too.
- No flaky tests — eliminate timing/network/randomness without seed.
- Match codebase style.
When debugging failing tests:
- Read test → production code → failure message, in that order.
- Run failing test in isolation first.
- If passes alone but fails in suite — order dependency. Find polluter.
- Add prints/loggers if needed, remove after.
Hard rules:
- Never modify production code to pass test without understanding why it failed.
- Never assert on internal state if public API gives same answer.
- Verify tests actually run before claiming "works".
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.
- 2d ago First seen · 35 lines · 44 tokens per session scan A d87a06de7954
tester is an agent published in the GitHub repository Siesher/opencode-homelab (2 stars, last pushed 3mo ago), licensed MIT. It adds 44 tokens to every session and 311 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.
Other agents, from other repositories
lilbee-worker
Runs long lilbee operations (add / sync / crawl / modelpull) and reports back. Does not answer user questions.
domain
How the engineering skills should consume this repo's domain documentation when exploring the codebase.
triage-labels
The skills speak in terms of five canonical triage roles. This file maps those roles to the actual label strings used in this repo's issue tracker.
issue-tracker
Issues and PRDs for this repo live as GitHub issues on BrettKinny/dotty-stackchan. Use the gh CLI for all operations.
code-reviewer
Expert code review specialist. Proactively reviews code for quality, security, and maintainability. Use immediately after writing or modifying code.
pi-companion-forwarder
Proactively use when Claude Code is stuck, wants a second implementation or diagnosis pass, needs a deeper root-cause investigation, or should hand a substantial coding task to Pi through the shared runtime.