medharness: Skill for Claude Code

.claude/skills/tdd-alignment/SKILL.md

tdd-alignment is a skill for Claude Code from charliehzm/medharness. It costs 190 tokens per session (830 once invoked), scanned A, original, Apache-2.0.

A comparison check between a product requirements document (PRD), which says what to build, and a technical design document (TDD), which explains how it will be tested. It records missing links between requirements, data handling, stages, and verification plans.

In plain words
What is it for?
Use it to create a coverage table, check privacy steps for sensitive data, match each project stage to a validation method, and list gaps by severity.
Why use it?
It prevents promised acceptance criteria or processing stages from reaching implementation without a test, and highlights sensitive fields whose protection is not planned.

Skill for Claude Code

Written for Claude Code: installed under .claude/.

This is charliehzm/medharness's own configuration. It tells Claude Code how to work on medharness 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 medharness configures →

Reuse

Borrowing it

Nothing to install: this file belongs to charliehzm/medharness. 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/charliehzm/medharness/main/.claude/skills/tdd-alignment/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/charliehzm/medharness

Made for: Claude Code.

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 tdd-alignment

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

Your own site · 80×15
<a href="https://agentmods.dev/skills/charliehzm/medharness/tdd-alignment"><img src="https://agentmods.dev/badge/skills/charliehzm/medharness/tdd-alignment.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 190 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 830 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 $0.00190 $0.00830
Opus 5 $0.00095 $0.00415
Sonnet 5 $0.00038 $0.00166
Haiku 4.5 $0.00019 $0.00083

Measured 11d ago against content hash 5bafc76b0e77, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

tdd-alignment 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 11d 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.

.claude/skills/tdd-alignment/SKILL.md · 68 lines

How it starts

The opening of the file, as written. The whole thing — 68 lines — stays where its author put it; the contents beside it link to each section on GitHub.

TDD Alignment (Step 2)

Core mental model

The TDD is the bridge between what (PRD) and how-to-test (later steps). Misalignment here propagates downstream: an acceptance criterion with no test design becomes an acceptance criterion with no test, becomes a feature shipped without proof.

What it produces

TDD_ALIGNMENT.md with:

  • Coverage table: each PRD acceptance criterion → TDD test strategy
  • PHI handling table: each L3/L4 field → desensitization step in TDD
  • Stage validation table: each PRD stage → TDD's stage-level test plan
  • Gaps list (sorted by severity)

Active context bundle

Always load first

  1. This SKILL.md
  2. Final PRD
  3. Submitted TDD
  4. COMPLIANCE_TAG.md (PHI field list)

Load on demand

  • reference/test-strategy-catalog.md (unit / integration / e2e / chaos / compliance / replay)

Workflow

  1. Extract PRD acceptance criteria into a flat list (numbered).
  2. For each criterion, find the TDD section that addresses it; record (criterion → tdd-section + test-strategy).
  3. Any criterion without a target → gap.
  4. For every L3/L4 field in COMPLIANCE_TAG, locate desensitization plan in TDD; missing → gap.
  5. For every PRD stage, locate the corresponding TDD stage validation; missing → gap.
  6. Emit report; if gaps exist, suggest concrete TDD patches.

Hard gate checklist

  • 100% of PRD criteria covered (no gaps)
  • Every L3/L4 field has desensitization step named in TDD
  • Each PRD stage has corresponding TDD stage validation
  • Test strategy named (not just "we'll test it")

Common failure modes

  1. "Tests will be written later" handwave: TDD says "comprehensive testing" without naming approach. Mitigation: require strategy name from reference/test-strategy-catalog.md.
  2. Forgotten staging tests: PRD has 3 stages, TDD only describes final-state tests. Mitigation: per-stage row in alignment table.
  3. PHI assumed handled by infra: developer assumes desensitize happens "somewhere". Mitigation: explicit row per field.

Read the full file on GitHub · 68 lines

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. 11d ago First seen · 68 lines · 190 tokens per session scan A 5bafc76b0e77

Subscribe to this mod's changes

tdd-alignment is a skill published in the GitHub repository charliehzm/medharness (86 stars, last pushed 3mo ago), licensed Apache-2.0. It adds 190 tokens to every session and 830 once invoked, about $0.0010 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.