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 skills/robinfaraj/one-context/test-wavenpx skills add robinfaraj/one-context --skill test-wavegit clone --depth 1 https://github.com/robinfaraj/one-contextWhat 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 | $0.00032 | $0.00866 |
| Opus 5 | $0.00016 | $0.00433 |
| Sonnet 5 | $0.00006 | $0.00173 |
| Haiku 4.5 | $0.00003 | $0.00087 |
Grade A, and why
test-wave 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.
How it starts
The opening of the file, as written. The whole thing — 90 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Test Wave
You are orchestrating a parallel test-writing team. Your job is to:
- Analyze what was recently implemented — look at git diff, recent changes, and the existing test suite
- Split work into parallel streams — each stream covers a different package or route group
- Spawn agents that write and run tests — each agent extends the existing test suite
Steps
1. Discover what needs testing
Run these commands to understand what changed:
git diff --name-only HEAD~5 # or whatever range covers recent work
git diff --stat
Read the existing test suite at packages/api/src/__tests__/routes.test.ts to understand the current coverage and patterns.
2. Identify test streams
Group the changes into 2-4 parallel streams. Examples:
- Stream A: API route tests (auth guards, authenticated endpoints, error cases)
- Stream B: Package unit tests (ai-chat, mem0, integrations)
- Stream C: Edge cases and validation tests
3. Create the team and spawn agents
Create a team called test-wave and spawn one agent per stream. Each agent should:
- Read the existing test patterns and follow the same conventions
- Use
vitestwith Hono'sapp.request()for API tests - Use
describe.runIf(!!DEV_API_KEY)for tests that need auth/DB - Add tests to the existing file or create new test files in
packages/<pkg>/src/__tests__/ - Run the tests to verify they pass before finishing
4. Test conventions
// Unauthenticated tests (always run)
it("should return 401 for GET /api/endpoint without auth", async () => {
const res = await app.request("/api/endpoint");
expect(res.status).toBe(401);
});
// Authenticated tests (only with DEV_API_KEY + test DB)
describe.runIf(!!DEV_API_KEY)("Authenticated", () => {
it("should return data with auth", async () => {
const res = await app.request("/api/endpoint", { headers: authHeaders! });
expect(res.status).toBe(200);
});
});
5. Verify and report
After all agents complete:
- Run
pnpm --filter @onecontext/api testto verify all tests pass - Report the total test count and what was covered
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 · 90 lines · 32 tokens per session scan A 34bbc13ff2ea
test-wave is a skill published in the GitHub repository robinfaraj/one-context (43 stars, last pushed 6mo ago), licensed Apache-2.0. It adds 32 tokens to every session and 866 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 2026-08-30.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
brainstorming
You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
agent-host-chat-contributions
Build and review cross-cutting agent-host chat behavior through lifecycle contributions. Use when adding turn lifecycle side effects, prompt or context injection, restored-history transformation, protocol-action observation, or when reviewing changes that add code to AgentSideEffects or AgentService.
auto-perf-optimize
Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.