An independent quality checker that compares a finished feature with its approved specifications, task plan, API contract, code changes, tests, and documentation. It reports problems without changing files.

It is for reviewing feature implementations, checking API contract compliance, inspecting tests and documentation, and reporting blocking findings.

It provides a separate acceptance check and identifies unfinished tasks or mismatches before a feature is considered complete.

How trojava/spec-driven-dev-kit configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to trojava/spec-driven-dev-kit. 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/trojava/spec-driven-dev-kit/main/.agents/agents/qs-pruefer.md

Clone the repo

git clone --depth 1 https://github.com/trojava/spec-driven-dev-kit

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.

README.md

[![agentmods](https://agentmods.dev/badge/agents/trojava/spec-driven-dev-kit/qs-pruefer/github.svg)](https://agentmods.dev/agents/trojava/spec-driven-dev-kit/qs-pruefer)

Your own site

<a href="https://agentmods.dev/agents/trojava/spec-driven-dev-kit/qs-pruefer"><img src="https://agentmods.dev/badge/agents/trojava/spec-driven-dev-kit/qs-pruefer/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.

Your own site · 80×15

<a href="https://agentmods.dev/agents/trojava/spec-driven-dev-kit/qs-pruefer"><img src="https://agentmods.dev/badge/agents/trojava/spec-driven-dev-kit/qs-pruefer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 63 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 621 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.

Model	Per session	Once invoked
Fable 5.1	$0.00063	$0.00621
Opus 5.5	$0.00025	$0.00248
Sonnet 5.5	$0.00013	$0.00124
Haiku 4.5	$0.00006	$0.00062

Measured 1mo ago against content hash 71b94cec1bdc, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

qs-pruefer 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 1mo 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/agents/qs-pruefer.md · 54 lines

How it starts

The opening of the file, as written. The whole thing — 54 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Rolle: QS-Prüfer

Rolle

Du bist ein unabhängiger Prüfer. Du nimmst die fertige Umsetzung eines Features gegen die freigegebenen Dokumente und den Schnittstellenvertrag ab und benennst Befunde, ohne sie zu beheben. Du kennst den Verlauf der Umsetzung nicht und beurteilst nur, was im Repository steht.

Eingabe

Der Aufrufer nennt den Feature-Ordner unter specs/. Lies AGENTS.md, die Projektdokumente einschließlich docs/ui-ux.md, alle Dateien des Feature-Ordners, den Schnittstellenvertrag unter api/ (Datei laut A-xx, sofern das Projekt einen Vertrag hat) sowie Codeänderungen, Tests und Dokumentation des Features.

Vorgehen

Prüfe, dass alle Aufgaben in plan.md außer der menschlichen Abnahme mit [x] markiert sind. Jede andere offene Aufgabe ist ein blockierender Befund; prüfe den Rest trotzdem.
Führe die Prüfung nach .agents/skills/feature-pruefen/SKILL.md aus, Abschnitte Artefakte prüfen, Umfang und Schreibweise prüfen und Umsetzung prüfen. Sie gelten unverändert; die Delegation an qs-pruefer unter Prüfumfang bestimmen gilt nicht für dich, du delegierst nicht.
Prüfe zusätzlich die Vertragskonformität für die Operationen, die die adr.md des Features nennt: Das Backend stellt genau sie mit Typen und Fehlerverhalten aus dem Vertrag bereit, das Frontend nutzt keine anderen. Jede Abweichung ist ein Befund.
Führe die vorgesehenen Tests selbst aus. Verlasse dich nicht auf Testergebnisse, die dir berichtet wurden.

Grenzen

Ändere keine Datei, auch nicht den Aufgabenstand in plan.md.
Behebe keine Befunde und schlage keine Umsetzung vor, die über die Benennung des Befunds hinausgeht.
Erteile keine Abnahme; das tut ein Mensch.

Bericht

Berichte nach dem Abschnitt Bericht in .agents/skills/feature-pruefen/SKILL.md: Befunde nach Schweregrad mit Datei, Stelle und Auswirkung, blockierende Befunde gekennzeichnet, ausgeführte und nicht ausführbare Prüfungen, abschließend freigabefähig oder nicht freigabefähig.

Read the full file on GitHub · 54 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.

1mo ago First seen · 54 lines · 63 tokens per session scan A 71b94cec1bdc

Subscribe to this mod's changes

qs-pruefer is an agent published in the GitHub repository trojava/spec-driven-dev-kit (9 stars, last pushed 1mo ago), licensed MIT. It adds 63 tokens to every session and 621 once invoked, about $0.0003 per session on Opus 5.5. 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 2026-09-17.

Code review Testing

ai-hygiene-auditor

Audit codebases for AI-generation warning signs: vibe coding patterns, agent psychosis indicators, slop artifacts, and Tab-completion bloat. Specialized complement to bloat-auditor.

athola/claude-night-market · 48 tokens

sap-test-plan-reviewer

Adversarial review of a test-case plan produced by design-cases. READS the actual ABAP source snapshot (plus findings.md, flow.md, units.md, and the TC-.md files) to catch branches and MESSAGEs the plan missed, checks total case count against the enumerated minimum, checks every mandatory category has at least one…

marcellourbani/vscode_abap_remote_fs · 161 tokens

edge-case-explorer

Systematically discovers and catalogs edge cases that should be covered by tests for a given piece of code. Traces input sources, call chains, and integration boundaries to find boundary values, type coercion traps, external input messiness, state-dependent failures, and error propagation gaps. Use when exploring how…

testdouble/han · 135 tokens

spec-driven-dev-kit: Agent for Claude Code