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 skills add ZaxbyHub/opencode-swarm --skill writing-testsgit clone --depth 1 https://github.com/ZaxbyHub/opencode-swarmWrote 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/skills/zaxbyhub/opencode-swarm/writing-tests)<a href="https://agentmods.dev/skills/zaxbyhub/opencode-swarm/writing-tests"><img src="https://agentmods.dev/badge/skills/zaxbyhub/opencode-swarm/writing-tests.svg" alt="Measured on agentmods" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 2 findings, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Agent Snooping · line 14 Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.Fix: Remove all code or instructions that list or read other skills' files or directories. Skills should operate independently; cross-skill access is a privilege escalation.
- medium Agent Snooping · line 16 Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.Fix: Remove all code or instructions that list or read other skills' files or directories. Skills should operate independently; cross-skill access is a privilege escalation.
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 | $0.00055 | $0.00359 |
| Opus 5 | $0.00028 | $0.00179 |
| Sonnet 5 | $0.00011 | $0.00072 |
| Haiku 4.5 | $0.00006 | $0.00036 |
Grade A, and why
writing-tests 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
Writing Tests
Use this Codex-facing adapter before touching tests in opencode-swarm.
Read, in order:
AGENTS.md.opencode/skills/writing-tests/SKILL.md
If the task also touches architecture, plugin initialization, subprocesses, tool registration, plan durability, .swarm storage, runtime portability, session/global state, guardrails/retry, chat/system hooks, or release/cache behavior, also load .agents/skills/engineering-conventions/SKILL.md.
Codex-specific execution notes:
- Use
apply_patchfor manual test/source edits. - Use the available shell execution tool for
bun --smol test, per-file loops,rg, and validation commands. - Prefer shell test commands for repo validation. Do not use broad OpenCode
test_runnerscopes. - Preserve unrelated user changes in the worktree.
Carry forward the source skill's core rules: bun:test only, dependency injection or _internals over mock.module where possible, real module spreading when mocking Node built-ins, os.tmpdir() plus path.join(...) for temp paths, and per-file isolation for mock-heavy directories.
Regression tests must also be falsifiable: remove or bypass the fix, confirm the test fails for the expected reason, restore the fix, and confirm the test passes; record the evidence or document why an equivalent mutation was required.
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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 · 30 lines · 55 tokens per session scan A 5c30428b1a98
writing-tests is a skill published in the GitHub repository ZaxbyHub/opencode-swarm (463 stars, last pushed today), licensed MIT. It adds 55 tokens to every session and 359 once invoked, about $0.0003 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 2026-08-30.
Other skills, from other repositories
cpp-testing
A guide for testing C++17/20 code with GoogleTest, GoogleMock, CMake, and CTest. It covers unit and integration tests, test discovery, coverage, and sanitizers.
perl-testing
Perl testing patterns using Test2::V0, Test::More, prove runner, mocking, coverage with Devel::Cover, and TDD methodology.
armada-verification
Mandatory pre-completion verification and evidence checklist before reporting done.
armada-tdd
Test-driven development for armada workers. Use before writing any implementation. Triggers on: TDD, failing test, test first, write a test.
debugging
Use when debugging bugs, test failures, or unexpected behavior. Triggers: 'why isn't this working', 'this doesn't work', 'X is broken', 'something's wrong', 'getting an error', 'exception in', 'stopped working', 'regression', 'crash', 'hang', 'flaky test', 'intermittent failure', or when user pastes a stack…
vc:autoresearch
Autonomous iterative optimization loop for measurable metrics like coverage, performance, or bundle size. Use when repeated experiments can be judged by a mechanical score.