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 Justinmendezai/The-Adam-Repo --skill tests-firstgit clone --depth 1 https://github.com/Justinmendezai/The-Adam-RepoWrote 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/justinmendezai/the-adam-repo/tests-first)<a href="https://agentmods.dev/skills/justinmendezai/the-adam-repo/tests-first"><img src="https://agentmods.dev/badge/skills/justinmendezai/the-adam-repo/tests-first/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/justinmendezai/the-adam-repo/tests-first"><img src="https://agentmods.dev/badge/skills/justinmendezai/the-adam-repo/tests-first.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00062 | $0.01446 |
| Opus 5 | $0.00031 | $0.00723 |
| Sonnet 5 | $0.00012 | $0.00289 |
| Haiku 4.5 | $0.00006 | $0.00145 |
Grade A, and why
tests-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 12d 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 — 94 lines — stays where its author put it; the contents beside it link to each section on GitHub.
tests-first
Strict TDD ownership. The high-level agent writes every test. Composer 2 subagents only write implementation that turns the tests green. Subagents must not modify test files.
This is the lever that lets the orchestrator review without reading every diff: if the tests pass and the test files weren't touched, the slice is meeting its contract by construction.
When to use
- After
slice-to-tasksproducesslices/<id>/SPEC.mdfiles. - Or when adding a new slice mid-flight to an in-progress build.
Workflow
1. Discover the test framework
Read plan/CONTEXT.md and the project's existing test setup. If you can't tell, dispatch a one-shot explore subagent: "What test framework, where do tests live, what's the run command?"
2. Per slice, write the failing tests
For each slices/<id>/SPEC.md:
- Read
acceptanceandpaths_in_scope. - Write tests under
tests/<id>/(or wherever the project convention places them — match it). - Cover each AC. One AC may map to one or several tests.
- Include test fixtures, sample data, and types as needed.
- Tests must compile (or parse) but fail with a meaningful message — not crash on missing imports.
If a function/module the test calls doesn't exist yet, write a stub in paths_in_scope that throws new Error("not implemented"). The stub plus the test together produce a clean red.
2b. Playwright E2E (when packet/PACKET.md defines e2e)
If the packet includes an e2e block with spec_dir and commands.test:
- For web slices with user-visible ACs, add Playwright specs under
e2e.spec_dir(typicallye2e/) that assert the same outcomes as the ACs at the browser level — in addition to, not instead of,tests/<id>/unit/integration coverage. - Prefer one spec file per slice or per journey; align paths with
e2e.journeys[].spec_pathswhen the packet lists them. - Subagents must still not modify these files; if needed, list them under
paths_out_of_scopeinslices/<id>/SPEC.mdbeside the unit test paths.
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.
- 12d ago First seen · 94 lines · 62 tokens per session scan A 834033a3f8c2
tests-first is a skill published in the GitHub repository Justinmendezai/The-Adam-Repo (12 stars, last pushed 18d ago), licensed Apache-2.0. It adds 62 tokens to every session and 1,446 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
engram-testing-coverage
TDD and coverage standards for Engram. Trigger: When implementing behavior changes in any package.
iterative-development
TDD iteration loops using Claude Code Stop hooks - runs tests after each response, feeds failures back automatically.
python
Python development with ruff, mypy, pytest - TDD and type safety.
nw-fp-clojure
Clojure language-specific patterns, data-first modeling, REPL-driven development, and spec.
strict-tdd
Strict RED->GREEN->REFACTOR test-driven development with enforcement. Never write production code before a failing test. Atomic commits per TDD cycle.
mobiai-mobile-tdd
You MUST use this before writing any implementation code for a mobile feature, bug fix, refactor, or behavior change. Tests come before implementation — no exceptions.