spec-driven-dev-kit: Skill for Codex

.agents/skills/feature-pruefen/SKILL.md

feature-pruefen is a skill for Codex from trojava/spec-driven-dev-kit. It costs 103 tokens per session (1,432 once invoked), scanned A, original, MIT.

A review procedure for checking a software feature's requirements, plan, tasks, implementation, tests, and documentation. It looks for unclear or conflicting requirements and missing cases.

In plain words
What is it for?
Use it to review a feature before coding or assess a completed feature against its requirements, acceptance criteria, and tests.
Why use it?
It helps find gaps between what a feature should do and what was planned or built before the work is accepted.

Skill for Codex

Written for Codex: agents/openai.yaml present. Also seen: reads .claude/ paths; mentions Claude Code; installed under .agents/ (shared by several agents).

This is trojava/spec-driven-dev-kit's own configuration. It tells Codex how to work on spec-driven-dev-kit 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 spec-driven-dev-kit configures →

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/skills/feature-pruefen/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/trojava/spec-driven-dev-kit

Made for: 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 feature-pruefen

README.md
[![agentmods](https://agentmods.dev/badge/skills/trojava/spec-driven-dev-kit/feature-pruefen/github.svg)](https://agentmods.dev/skills/trojava/spec-driven-dev-kit/feature-pruefen)
Your own site
<a href="https://agentmods.dev/skills/trojava/spec-driven-dev-kit/feature-pruefen"><img src="https://agentmods.dev/badge/skills/trojava/spec-driven-dev-kit/feature-pruefen/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 feature-pruefen

Your own site · 80×15
<a href="https://agentmods.dev/skills/trojava/spec-driven-dev-kit/feature-pruefen"><img src="https://agentmods.dev/badge/skills/trojava/spec-driven-dev-kit/feature-pruefen.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 103 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,432 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 $0.00103 $0.01432
Opus 5.5 $0.00041 $0.00573
Sonnet 5.5 $0.00021 $0.00286
Haiku 4.5 $0.00010 $0.00143

Measured 1mo ago against content hash 5c503134e3b9, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

feature-pruefen 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/skills/feature-pruefen/SKILL.md · 113 lines

How it starts

The opening of the file, as written. The whole thing — 113 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Feature prüfen

Rolle

Du bist ein unabhängiger Reviewer. Du nimmst eine fertige Umsetzung gegen die freigegebenen Dokumente ab und benennst Befunde, ohne sie selbst zu beheben.

Prüfumfang bestimmen

Dieser Skill kennt genau einen Auftrag: die Abnahme eines Features nach der Implementierung. Ist das Feature noch nicht umgesetzt, stoppe und nenne den Schritt, der zuerst fehlt.

Lies AGENTS.md, die Projektdokumente einschließlich docs/ui-ux.md, alle Dateien des Feature-Ordners, den Schnittstellenvertrag unter api/ sowie die Codeänderungen, Tests und Dokumentation des Features. Die Feature-Dokumente und der Vertrag sind der Maßstab, an dem die Umsetzung gemessen wird.

Kennt dein Werkzeug die Rollen als Subagenten (in Claude Code unter .claude/agents/, in OpenCode unter .opencode/agents/), delegiere die gesamte Prüfung an qs-pruefer, nenne den Feature-Ordner und gib dessen Bericht unverändert weiter. Der eigene Kontext der Rolle macht die Prüfung unabhängig vom Verlauf der Umsetzung. Ohne Subagenten prüfst du selbst nach den folgenden Abschnitten, und zwar in einer neuen Sitzung: Wurde das Feature in dieser Sitzung umgesetzt, stoppe und bitte um einen Neustart in einer frischen Sitzung.

Ändere bei einer Prüfung keine Dateien, außer der Benutzer fordert Korrekturen ausdrücklich an oder erteilt die Abnahme des Features. Erteilt er sie, trage sie in plan.md ein und erstelle den Commit des Features nach der Regel in AGENTS.md.

Artefakte prüfen

  1. Suche unklare, widersprüchliche oder nicht überprüfbare Anforderungen.
  2. Prüfe Normal-, Fehler- und Randfälle sowie die nichtfunktionalen Anforderungen, die als R-xx aufgenommen wurden.
  3. Prüfe die Verknüpfung Anforderung → Aufgabe → Prüfung. Jede Anforderung muss von mindestens einer Aufgabe getragen werden. Eine Lücke ist ein Befund; eine vollständige Abdeckung wird nicht als Tabelle verlangt.
  4. Prüfe, ob die wesentlichen technischen Entscheidungen in adr.md erfasst und freigegeben sind und ob sie zu docs/architektur.md passen. Nicht gekennzeichnete Abweichungen sind ein Befund.
  5. Prüfe bei Oberflächenarbeit, ob Plan und Aufgaben die Vorgaben U-xx einhalten und ob für jede betroffene Ansicht die fachlich möglichen Zustände geplant sind. Eine nicht gekennzeichnete Abweichung ist ein Befund. Gestalterische Festlegungen, die in einem Feature-Dokument statt in docs/ui-ux.md stehen, sind ebenfalls ein Befund.
  6. Suche fehlende Abhängigkeiten und Rücknahmemöglichkeiten.
  7. Prüfe, ob Aufgaben angemessen geschnitten, geordnet und einzeln prüfbar sind und ob jede Aufgabe, die Backend- oder Frontend-Code ändert, das Tag [Backend] oder [Frontend] im Titel trägt. Ein fehlendes Tag ist ein Befund.
  8. Prüfe, ob eine Schnittstelle des Features im Vertrag unter api/ steht und adr.md die betroffenen Operationen nennt.

Read the full file on GitHub · 113 lines

Files

What ships with it

1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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. 1mo ago Changed · +3 lines 5c503134e3b9
  2. 1mo ago Changed · +16 lines · +24 tokens per session 809841700ee8
  3. 1mo ago Changed · +43 lines · +15 tokens per session 6bc17280bbb9
  4. 2mo ago First seen · 51 lines · 64 tokens per session scan A 07d2e5f8220e

Subscribe to this mod's changes

feature-pruefen is a skill published in the GitHub repository trojava/spec-driven-dev-kit (9 stars, last pushed 1mo ago), licensed MIT. It adds 103 tokens to every session and 1,432 once invoked, about $0.0004 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 2026-08-31.

Related

Other skills, from other repositories

autoreview

Structured code review through the shared OpenClaw agent-skills installation.

openclaw/clawhub · 17 tokens

omh-code-review

This is an OMH code-review workflow skill, projected for Agent Skills hosts (Claude Code, Codex, Cursor, opencode, OpenClaw, pi).

rlaope/oh-my-hermes · 48 tokens

revdiff-plan

Review the last Codex assistant message (plan, analysis, or proposal) with inline annotations in a TUI overlay. Extracts the most recent response from Codex rollout files and opens it in revdiff for review and annotation. Activates on "revdiff-plan", "review plan with revdiff", "annotate plan", "review last response"…

umputun/revdiff · 84 tokens

explore-unknowns

Guide the user through a quadrant walk that maps the unknowns of a task — open by listing the known knowns, then work through known unknowns, unknown knowns, and unknown unknowns one stage at a time, ending with a complete four-quadrant map in the user's hands. Use when a request is ambiguous or underspecified, the…

dzhng/skills · 162 tokens

re0-merge

Review and land an external contribution the way this suite does: gate it against the thesis, land it with the author's credit intact, complete a new skill rather than merging it raw, then approve, credit, and explain before closing. Use when reviewing a pull request, as any collaborator or maintainer, not only the…

LilMGenius/paperthin · 70 tokens

asplos-writing-style

Use when drafting or revising ASPLOS prose — engineering the first two pages that rapid review actually reads, stating the cross-layer insight as one quotable sentence, structuring per-layer mechanism sections, writing bounded claims, and fitting everything into 11 self-contained pages that include figures and…

brycewang-stanford/Awesome-Journal-Skills · 65 tokens