axum-harness: Skill for Claude Code

.agents/skills/harness-tdd/SKILL.md

harness-tdd is a skill for Claude Code, Codex from openclosed-org/axum-harness. It costs 56 tokens per session (378 once invoked), scanned A, original, Apache-2.0.

A test-driven workflow for backend changes. TDD means writing a test that fails, making the smallest change that passes it, then cleaning up the code.

In plain words
What is it for?
Use it when changing services, servers, workers, contracts, or repository tools, especially when fixing bugs or adding behavior.
Why use it?
It keeps tests focused on behavior users can observe and avoids testing private implementation details or building speculative features.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: installed under .agents/ (shared by several agents).

This is openclosed-org/axum-harness's own configuration. It tells Claude Code and Codex how to work on axum-harness itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything axum-harness configures →

Reuse

Borrowing it

Nothing to install: this file belongs to openclosed-org/axum-harness. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/openclosed-org/axum-harness/main/.agents/skills/harness-tdd/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/openclosed-org/axum-harness

Made for: Claude Code, Codex.

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 harness-tdd

README.md
[![agentmods](https://agentmods.dev/badge/skills/openclosed-org/axum-harness/harness-tdd/github.svg)](https://agentmods.dev/skills/openclosed-org/axum-harness/harness-tdd)
Your own site
<a href="https://agentmods.dev/skills/openclosed-org/axum-harness/harness-tdd"><img src="https://agentmods.dev/badge/skills/openclosed-org/axum-harness/harness-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.

agentmods 80×15 button for harness-tdd

Your own site · 80×15
<a href="https://agentmods.dev/skills/openclosed-org/axum-harness/harness-tdd"><img src="https://agentmods.dev/badge/skills/openclosed-org/axum-harness/harness-tdd.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 56 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 378 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 $0.00056 $0.00378
Opus 5 $0.00028 $0.00189
Sonnet 5 $0.00011 $0.00076
Haiku 4.5 $0.00006 $0.00038

Measured 10d ago against content hash 9f3cea726e32, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

harness-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.

.agents/skills/harness-tdd/SKILL.md · 54 lines

What it actually says

Harness TDD

Use this skill to add or change behavior one vertical slice at a time.

Workflow skills guide process. Ownership skills still decide writable boundaries.

Philosophy

Tests should verify observable behavior through public seams, not implementation details.

Prefer tests that survive internal refactors:

  1. service public API or application seam
  2. BFF handler or HTTP route behavior
  3. worker replay, checkpoint, or projection seam
  4. contract compatibility or drift seam
  5. repo-tool CLI or validator seam

Loop

For each behavior:

  1. Pick one observable behavior.
  2. Write one failing test at the correct public seam.
  3. Run it and confirm RED.
  4. Write the smallest correct code to pass.
  5. Run it and confirm GREEN.
  6. Refactor only while GREEN.
  7. Run relevant path-scoped gates.

Anti-Patterns

  1. Do not write all tests first and then all implementation.
  2. Do not test private helpers when a public seam can express the behavior.
  3. Do not mock internal collaborators you own.
  4. Do not add speculative behavior for future tests.
  5. Do not expose internal seams only for test convenience.

Mocking Rule

Mock true externals and hard runtime boundaries. Prefer local substitutes or in-memory adapters for owned seams when they provide better behavioral evidence.

Refactor Check

After GREEN, look for shallow modules, duplicated rules, primitive obsession, hidden coupling, or oversized traits. If the fix reveals architecture friction, hand off to harness-architecture-review.

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. 10d ago First seen · 54 lines · 56 tokens per session scan A 9f3cea726e32

Subscribe to this mod's changes

harness-tdd is a skill published in the GitHub repository openclosed-org/axum-harness (49 stars, last pushed 3mo ago), licensed Apache-2.0. It adds 56 tokens to every session and 378 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 2026-08-30.