medharness: Skill for Claude Code

.claude/skills/openspec-verify-change/SKILL.md

openspec-verify-change is a skill for Claude Code from charliehzm/medharness. It costs 162 tokens per session (578 once invoked), scanned A, original, Apache-2.0.

A verification workflow for an OpenSpec change, where OpenSpec is a format for describing planned software changes and their tasks. It checks that completed tasks match code, specifications, tests, and file-scope rules.

In plain words
What is it for?
Use it at the verification stage to inspect task checkboxes, compare them with the code and git history, run acceptance smoke tests, and produce a verification report.
Why use it?
It catches tasks marked complete without corresponding implementation or tests. It also exposes missing specification references and acceptance checks before the change moves forward.

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/openspec-verify-change/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 openspec-verify-change

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

Your own site · 80×15
<a href="https://agentmods.dev/skills/charliehzm/medharness/openspec-verify-change"><img src="https://agentmods.dev/badge/skills/charliehzm/medharness/openspec-verify-change.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 162 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 578 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 $0.00162 $0.00578
Opus 5 $0.00081 $0.00289
Sonnet 5 $0.00032 $0.00116
Haiku 4.5 $0.00016 $0.00058

Measured 12d ago against content hash 8f49564f3815, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

openspec-verify-change 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.

.claude/skills/openspec-verify-change/SKILL.md · 56 lines

What it actually says

OpenSpec Verify Change

The "did we actually build what we said" gate.

What it checks (NOT code quality)

Check Pass criterion
Tasks checkbox parity every [x] task has a referenced code change in git
Spec evidence every spec id appears in commit messages / file headers / test names
Acceptance criteria smoke per-spec acceptance criteria runnable on stage-mock data, smoke green
File scope discipline no task exceeded 2 files
Compliance touchpoints every L3/L4-touching task's PR mentions phi-desensitize use

Workflow

  1. Parse tasks.md / tasks/*.md → list of completed tasks + intended files.
  2. Diff against git log / current workspace → identify gaps.
  3. For each gap, mark as one of: missing-file / missing-test / missing-checkbox / scope-overflow.
  4. Run acceptance criteria smoke tests for each spec.
  5. Emit VERIFY_REPORT.md with passes / failures / actions.

Hard gate

If any failure → return to Step 6, fix, re-run. Do not pass to Step 8.

Common failure modes

  1. Checkbox theater — task marked done without code. Mitigation: parity check.
  2. Hidden Steve work — task touched 4 files. Mitigation: scope discipline check.
  3. Spec without test hook — acceptance criteria not executable. Mitigation: hand back to openspec-continue-change to refine.
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. 12d ago First seen · 56 lines · 162 tokens per session scan A 8f49564f3815

Subscribe to this mod's changes

openspec-verify-change is a skill published in the GitHub repository charliehzm/medharness (86 stars, last pushed 3mo ago), licensed Apache-2.0. It adds 162 tokens to every session and 578 once invoked, about $0.0008 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.

Related

Other skills, from other repositories

hipaa-review

Performs a HIPAA Security Rule compliance review against all Administrative, Physical, and Technical Safeguards defined in 45 CFR Part 164, Subpart C. Auto-invoked when discussing healthcare data security, ePHI protection, HIPAA audit readiness, or business associate compliance. Evaluates required and addressable…

UnitOneAI/SecuritySkills · 86 tokens

HIPAA Compliance Testing

Testing HIPAA compliance for healthcare applications including PHI handling, audit logging, access controls, and data encryption verification.

PramodDutta/qaskills · 28 tokens

Healthcare Compliance

HIPAA compliance, healthcare regulations, privacy and security standards for medical organizations and providers.

jmsktm/claude-settings · 19 tokens

review-delta

Review only changes since last commit using impact analysis. Token-efficient delta review with automatic blast-radius detection.

tirth8205/code-review-graph · 24 tokens

pre-landing-review

Pre-landing PR review. Analyzes diff against the base branch for SQL safety, LLM trust boundary violations, conditional side effects, and other structural issues. Use when explicitly asked for the specialized pre-landing workflow. Product /review requests are handled by OpenBitFun's unified Review mechanism instead.…

GCWing/BitFun · 75 tokens

find-simplifications

Use for a periodic repo-wide sweep of qwen-code for accumulated excess surface — dead components and files, orphaned locale keys, exports nothing consumes, added-then-removed scaffolding — filing candidates on a tracking issue and landing only what a maintainer has said yes to. Repo-wide and evidence-first; every…

QwenLM/qwen-code · 103 tokens