Claude-Pipeline: Command for Claude Code

.claude/commands/qb.md

qb is a command for Claude Code from TheAstrelo/Claude-Pipeline. It costs 0 tokens per session (364 once invoked), scanned A, original, MIT.

A command for checking whether implemented software builds, passes its tests, follows its design, and handles reviewed edge cases.

In plain words
What is it for?
Use it to run the project build and tests, compare results with design and critique documents, verify edge cases, and append the outcome to a QA report.
Why use it?
It creates a recorded check against the intended behaviour instead of relying only on the fact that code was written.

Command for Claude Code

Written for Claude Code: installed under .claude/.

This is TheAstrelo/Claude-Pipeline's own configuration. It tells Claude Code how to work on Claude-Pipeline 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 Claude-Pipeline configures →

Reuse

Borrowing it

Nothing to install: this file belongs to TheAstrelo/Claude-Pipeline. 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/TheAstrelo/Claude-Pipeline/main/.claude/commands/qb.md
Clone the repo
git clone --depth 1 https://github.com/TheAstrelo/Claude-Pipeline

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 qb

README.md
[![agentmods](https://agentmods.dev/badge/commands/theastrelo/claude-pipeline/qb/github.svg)](https://agentmods.dev/commands/theastrelo/claude-pipeline/qb)
Your own site
<a href="https://agentmods.dev/commands/theastrelo/claude-pipeline/qb"><img src="https://agentmods.dev/badge/commands/theastrelo/claude-pipeline/qb/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 qb

Your own site · 80×15
<a href="https://agentmods.dev/commands/theastrelo/claude-pipeline/qb"><img src="https://agentmods.dev/badge/commands/theastrelo/claude-pipeline/qb.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 364 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 $0.00000 $0.00364
Opus 5 $0.00000 $0.00182
Sonnet 5 $0.00000 $0.00073
Haiku 4.5 $0.00000 $0.00036

Measured 9d ago against content hash 81f19abc736a, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

qb 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 9d 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/commands/qb.md · 83 lines

What it actually says

Behavior validation - verify tests pass and outputs match design.


Purpose

Verify that implemented code behaves correctly:

  • Build succeeds
  • Tests pass
  • Behavior matches design specifications
  • Edge cases from critique are handled

Execution

Use the quality-behavior agent.

Input:

  • build-report.md — What was built
  • design.md — Expected behavior
  • critique.md — Edge cases to verify

Process:

  1. Run build: npm run build
  2. Run tests: npm test (if tests exist)
  3. Verify specifications:
    • Check behavior against design.md requirements
    • Verify edge cases from critique.md are handled
  4. Append results to qa-report.md

Verification Matrix

Requirement How to Verify
API returns X Check response shape
Handles empty data Check code path
Auth required Check middleware
Multi-tenant Check user_id filter

Output

After validation, report:

## Quality Behavior Complete

**Verdict:** [PASS | FAIL]

### Build
- Status: [PASS | FAIL]
- Warnings: [N]

### Tests
- Status: [PASS | FAIL | NO_TESTS]
- Passed: [N]
- Failed: [N]

### Specification Compliance
[Table of requirements and verification status]

### Edge Cases
[Table of edge cases and handling status]

### Issues Found
[List of behavioral issues]

### Next Step
Run `/qd` for documentation check.

Gate

This command is part of the QA pipeline. Order: /denoise/qf/qb/qd/security-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. 9d ago First seen · 83 lines · 0 tokens per session scan A 81f19abc736a

Subscribe to this mod's changes

qb is a command published in the GitHub repository TheAstrelo/Claude-Pipeline (44 stars, last pushed 4d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 364 tokens. 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.