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/blushyes/reef/testing-reefnpx skills add Blushyes/reef --skill testing-reefgit clone --depth 1 https://github.com/Blushyes/reefWhat 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 | $0.00188 | $0.02869 |
| Opus 5 | $0.00094 | $0.01435 |
| Sonnet 5 | $0.00038 | $0.00574 |
| Haiku 4.5 | $0.00019 | $0.00287 |
Grade A, and why
testing-reef 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 — 208 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Testing in the reef workspace
A project-specific test playbook. Follow this when adding any test. The goal is that tests are deterministic across Linux/macOS CI and every dev's laptop, and that no test becomes that one flaky thing everyone reruns.
Workspace layout
Reef is a single-process binary plus shared internal crates. There is no plugin subsystem.
crates/reef-app— renderer-neutral app engine, task orchestration, command dispatch, snapshots, and app-state tests.crates/reef-tui(reefcrate) — terminal adapter, TUI rendering, input/mouse decoding, terminal image protocol,tests/(terminal adapter / UI integration),benches/(criterion).crates/reef-core— UI-independent git, diff, preview, markdown, highlight, nav/LSP, file-op, host parsing, and history logic.crates/reef-agent/crates/reef-proto/crates/reef-sqlite-preview— remote agent/protocol and SQLite preview support.crates/test-support— shared fixtures (tempdir_repo,commit_file,write_file,HomeGuard).fuzz/— fuzz targets. Separate package, not in the workspace; run viacargo +nightly fuzz run <target>.
Quick decision table
| Scenario | Test type | Where it goes |
|---|---|---|
| Pure function, no I/O | Unit test | #[cfg(test)] mod tests inline at bottom of the source file |
| Renderer-neutral app engine / worker contract | Integration test | crates/reef-app/tests/<name>_integration.rs |
| Backend / agent / Local-vs-Remote IO contract | Integration test | crates/reef-io/tests/<name>_loopback.rs |
| TUI adapter behavior with real fs/git | Integration test | crates/reef-tui/tests/<name>_integration.rs |
| Algorithmic invariant over random inputs | Property test | crates/reef-tui/tests/<name>_properties.rs (uses proptest) |
| Full UI rendered to terminal buffer | Snapshot | crates/reef-tui/tests/<name>_snapshots.rs (uses insta + ratatui::TestBackend) |
| Hot-path performance | Benchmark | crates/reef-tui/benches/<name>.rs (uses criterion) |
| Parser / deserializer robustness | Fuzz target | fuzz/fuzz_targets/<name>.rs |
What ships with it
5 files 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.
- 2d ago First seen · 208 lines · 188 tokens per session scan A 01e8afd068c8
testing-reef is a skill published in the GitHub repository Blushyes/reef (82 stars, last pushed 7d ago), licensed Apache-2.0. It adds 188 tokens to every session and 2,869 once invoked, about $0.0009 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
om-implement-spec
Implement a specification (or specific phases) using coordinated subagents with unit tests, integration tests, docs, and code-review compliance. Tracks progress by updating the spec. Triggers on "implement spec", "implement phases", "build from spec", "code the spec".
writing-tests
Write unit tests, component tests, and integration tests for AiderDesk using Vitest and React Testing Library. Use when creating new tests, adding test coverage, configuring mocks, setting up test files, or debugging failing tests.
running-julia-test
Before running tests for a new package, make sure the test environment is already set up. If the package does not have tests yet, follow creating-julia-test-env first. Tests that use using Test must have Test available from the package or test project.
memstack-development-test-writer
Use this skill when the user says 'write tests', 'add tests', 'test coverage', 'unit tests', 'integration tests', 'component tests', 'mocking', 'edge cases', or needs to generate tests with proper mocking and edge case coverage. Do NOT use for refactoring plans or database migrations.
verify-changes
How to test and verify work in the dev-3.0 repo — which vitest config covers what, how to write a test that fits the house style, mocking Electrobun RPC and i18n providers, what coverage is actually expected, and the browser QA hand-off. Use when writing or fixing tests, deciding what a change needs covered, hitting a…
verify
Self-healing verification loop (test → clippy → fmt).