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 zstevovich/claude-apd --skill apd-tddgit clone --depth 1 https://github.com/zstevovich/claude-apdWrote 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/zstevovich/claude-apd/apd-tdd)<a href="https://agentmods.dev/skills/zstevovich/claude-apd/apd-tdd"><img src="https://agentmods.dev/badge/skills/zstevovich/claude-apd/apd-tdd/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/zstevovich/claude-apd/apd-tdd"><img src="https://agentmods.dev/badge/skills/zstevovich/claude-apd/apd-tdd.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 | $0.00144 | $0.01141 |
| Opus 5 | $0.00072 | $0.00571 |
| Sonnet 5 | $0.00029 | $0.00228 |
| Haiku 4.5 | $0.00014 | $0.00114 |
Grade A, and why
apd-tdd 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 10d 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 — 105 lines — stays where its author put it; the contents beside it link to each section on GitHub.
APD Test-Driven Development (Codex)
On Codex this skill applies to the native builder subagent dispatched between
apd:apd_advance_pipeline('spec', ...) and
apd:apd_advance_pipeline('builder'). The orchestrator coordinates the phase
and must not implement source changes itself.
When to use / When to skip
Use when:
- You are inside the APD builder phase
- You are about to write or modify production code (any non-test source file)
- You are fixing a bug that has reached Phase 4 of
apd-debug
Skip when:
- You are reading code without modifying it
- You are running an existing test suite (use shell directly)
- You are editing documentation, configuration, or scaffolding files
The Iron Law
NO PRODUCTION CODE WITHOUT A FAILING TEST FIRST
Write code before the test? Delete it. Start over. No exceptions.
Red → Green → Refactor
1. RED — failing test first
Write ONE minimal test that describes the behavior you want. Run it. Watch it fail. If it passes on the first run, you are testing existing behavior — fix the test to actually describe the new requirement.
Before each test-file write, call
apd:apd_guard_write(apd_role="<role>", file_path="<path>"). The server reads
scope from .apd/agents/<role>.md on every call — you only pass the role
name and target path. Use apd:apd_list_agents() to discover which roles are
defined. (Argument is apd_role, not role, to avoid Codex's
multi_agent role-mismatch approval prompt.)
2. GREEN — minimal code to pass
Write the SIMPLEST code that makes the test pass. Nothing more.
- No extra features
- No "while I'm here" improvements
- No over-engineering
3. REFACTOR — clean up (tests stay green)
Only once green: remove duplication, improve names, extract helpers. If a test goes red during refactoring, revert immediately.
4. Next behavior
Pick the next behavior. Write the next failing test. Repeat.
Scope enforcement on every write
Builder scope is declared in the agent frontmatter
(.apd/agents/<role>.md, scope: list). Call
apd:apd_guard_write(apd_role="<role>", file_path="<path>") before every
Write/Edit — the server reads scope from the agent file itself, so the
role name is the only handle you need (and can't widen).
What ships with it
4 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.
- 10d ago First seen · 105 lines · 144 tokens per session scan A d1c3640f3d42
apd-tdd is a skill published in the GitHub repository zstevovich/claude-apd (5 stars, last pushed 1mo ago), licensed MIT. It adds 144 tokens to every session and 1,141 once invoked, about $0.0007 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.