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/buildmoonshot/skillpacks/test-firstnpx skills add buildmoonshot/skillpacks --skill test-firstgit clone --depth 1 https://github.com/buildmoonshot/skillpacksWhat 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 | $0.00065 | $0.00396 |
| Opus 5 | $0.00032 | $0.00198 |
| Sonnet 5 | $0.00013 | $0.00079 |
| Haiku 4.5 | $0.00006 | $0.00040 |
Grade A, and why
test-first 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
Test First
When the change can be tested, write the test before the implementation.
For a bug fix
- Reproduce it with a failing test. Write a test that asserts the correct behavior — it should fail against the current buggy code. This proves you understand the bug.
- Run it and watch it fail for the expected reason. A test that passes before you've fixed anything is testing the wrong thing.
- Write the minimal fix that makes it pass.
- Run the full suite to confirm the fix works and breaks nothing else.
For a new feature
- Write a test describing the behavior you want (it fails — the feature doesn't exist yet).
- Implement until it passes.
- Add tests for the obvious edge cases (empty input, boundaries, error paths).
Keep it honest
- The test must actually fail first. "I wrote a test and it passes" on unwritten code means the test is hollow.
- Test behavior, not implementation details — assert what the code does, not how, so the test survives refactors.
- If something genuinely can't be tested (UI nuance, external service), say so and fall back to a concrete manual check instead of pretending.
Why this matters
A bug with a failing-then-passing test around it is a bug that won't silently come back — the test stands guard forever. Writing the test first also forces you to define "done" before you write code, which is exactly when it's cheapest to get the definition right.
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.
- 2d ago First seen · 32 lines · 65 tokens per session scan A 4a8a4cfccb7f
test-first is a skill published in the GitHub repository buildmoonshot/skillpacks (2 stars, last pushed 2mo ago), licensed MIT. It adds 65 tokens to every session and 396 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 2026-08-31.
Other skills, from other repositories
bridge
Use when the user wants hyperflow's behavioral rules to apply outside the terminal CLI — in Claude Code Desktop, claude.ai web, or IDE extensions that don't load CLI plugins. Writes a managed doctrine block into the project's CLAUDE.md so autonomy + intent-routing + commit cadence + role separation + file-first rules…
fable-method
A step-by-step problem-solving loop (classify the ask, define done, gather evidence, decide, act surgically, verify by observation, report outcome-first). Use when the user says "/fable-method", "use the fable method", or "approach this like Fable", or proactively when starting any multi-step task that no…
fable-domain
Discuss a domain with the user, research it from real sources, then generate a trusted skill bundle for it - a step-by-step workflow with a flowchart, a domain adapter, a trap fixture, and a smoke eval. Use when the user says "/fable-domain ", "make a skill for ", "add a domain to the fable method", or "give a lesser…
caliber-testing
Writes Vitest tests following project patterns: tests/ directories, vi.mock() for module mocking with vi.hoisted() for test-time factories, global LLM mock from src/test/setup.ts, environment variable save/restore in beforeEach/afterEach, vi.clearAllMocks() lifecycle, and test file organization. Use when user says…
writers-pattern
Add a new platform writer module in src/writers/ that generates and writes agent config files for a supported platform. Each writer exports a function that accepts a config interface, creates directories (rules/, skills/, mcp configs), writes files with proper formatting and frontmatter, and returns string[] of…
llm-provider
Adds a new LLM provider implementing LLMProvider interface with call() and stream() methods. Integrates with provider factory in src/llm/index.ts, config detection in src/llm/config.ts, and error handling via tracking and recovery. Use when adding a new model backend, integrating a third-party LLM API, or extending…