test-first-development

test-first-development is a skill for Claude Code, Codex from bostonaholic/team. It costs 24 tokens per session (442 once invoked), scanned A, original, MIT.

A development rule that requires all acceptance tests to be written before implementation and kept unchanged. Acceptance tests are checks that define the required behavior and completion boundary.

In plain words
What is it for?
Use it to turn a plan into a fixed set of tests, enforce test-before-code work, and verify that every planned requirement passes.
Why use it?
It prevents implementation from drifting beyond the approved scope and gives a clear answer about whether the work is complete.

Skill for Claude CodeCodex

Written for Claude Code and Codex: user-invocable in frontmatter, but also agents/openai.yaml present.

Part of the team plugin — 89 skills, 13 agents, 2 hooks shipped together

Good fit Use it to turn a plan into a fixed set of tests, enforce test-before-code work, and verify that every planned requirement passes.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/bostonaholic/team/test-first-development
Install

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.

Any agent
npx skills add bostonaholic/team --skill test-first-development
Clone the repo
git clone --depth 1 https://github.com/bostonaholic/team

Made for: Claude Code, Codex.

Or install team, the plugin that ships this one along with the rest of its 89 skills, 13 agents, 2 hooks.

Wrote 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.

agentmods badge for test-first-development

README.md
[![agentmods](https://agentmods.dev/badge/skills/bostonaholic/team/test-first-development.svg)](https://agentmods.dev/skills/bostonaholic/team/test-first-development)
Your own site
<a href="https://agentmods.dev/skills/bostonaholic/team/test-first-development"><img src="https://agentmods.dev/badge/skills/bostonaholic/team/test-first-development.svg" alt="Measured on agentmods" height="20"></a>
Per session 24 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 442 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00024 $0.00442
Opus 5 $0.00012 $0.00221
Sonnet 5 $0.00005 $0.00088
Haiku 4.5 $0.00002 $0.00044

Measured 3d ago against content hash d536b4d6ab74, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

test-first-development 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 3d 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.

skills/test-first-development/SKILL.md · 59 lines

What it actually says

Test-First Development

Acceptance tests are the immutable scope fence (principle-scope-fence). Read references/procedure.md for complete error handling, stub limits, and the acceptance-versus-step-level distinction.

Core Rule

Write ALL acceptance tests from the plan BEFORE any implementation code. Use the plan's exact names; add, omit, or rename none. If boundary, invalid-input, failure, concurrency, auth, or resource-limit cases are missing, return to PLAN.

1. Write every planned test

Tests assert observable outcomes and follow skills/test-style/SKILL.md. Audit each against that skill's named checklist before reporting results.

2. Make Sure That Tests Fail Correctly

Run the full suite. Every new test must FAIL through its assertion, never ERROR; every existing test must pass. This is a deterministic gate (principle-mechanical-gates). Then run the project's static checks, including typecheck, and make them pass. Report both results.

3. Fix errors, not failures

For missing imports, fixtures, types, or runner config, add only the minimum placeholder module, fixture, type stub, or configuration required to execute. Stubs remain visibly incomplete. Never add implementation to make a test run.

4. Lock the test list

After correct Red state, acceptance tests are immutable during IMPLEMENT:

  • add none;
  • remove none;
  • change no assertions;
  • rename none.

A needed change returns to PLAN; the structure regenerates the plan. There is no approval step.

Two test levels

  • Feature acceptance: immutable, coarse observable behavior; defines what.
  • Step-level TDD: Red, Green, Refactor unit tests; freely changed during implementation; helps build how.

Completion Contract

Proceed to VERIFY only when all acceptance tests pass unchanged, none were added or removed, and the full prior suite has no regression.

Files

What ships with it

2 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.

Changes

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.

  1. 3d ago Changed · -78 lines · -5 tokens per session d536b4d6ab74
  2. 4d ago First seen · 137 lines · 29 tokens per session scan A 458f5c13b7f0

Subscribe to this mod's changes

test-first-development is a skill published in the GitHub repository bostonaholic/team (11 stars, last pushed today), licensed MIT. It adds 24 tokens to every session and 442 once invoked, about $0.0001 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 2026-09-03.