Borrowing it
Nothing to install: this file belongs to mick-gsk/drift. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/mick-gsk/drift/main/.github/skills/drift-agent-prompt-authoring/SKILL.mdgit clone --depth 1 https://github.com/mick-gsk/driftWrote 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.
[](https://agentmods.dev/skills/mick-gsk/drift/drift-agent-prompt-authoring)<a href="https://agentmods.dev/skills/mick-gsk/drift/drift-agent-prompt-authoring"><img src="https://agentmods.dev/badge/skills/mick-gsk/drift/drift-agent-prompt-authoring/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.
<a href="https://agentmods.dev/skills/mick-gsk/drift/drift-agent-prompt-authoring"><img src="https://agentmods.dev/badge/skills/mick-gsk/drift/drift-agent-prompt-authoring.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00115 | $0.02014 |
| Opus 5 | $0.00057 | $0.01007 |
| Sonnet 5 | $0.00023 | $0.00403 |
| Haiku 4.5 | $0.00012 | $0.00201 |
Grade A, and why
drift-agent-prompt-authoring 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.
How it starts
The opening of the file, as written. The whole thing — 193 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Drift Skill Für Agent-Prompt-Authoring
Verwende diesen Skill, wenn du einen Drift-Prompt unter .github/prompts/ neu schreibst oder überarbeitest.
Wann Verwenden
- Ein neuer Evaluierungs- oder Workflow-Prompt wird benötigt
- Eine bestehende
.prompt.md-Datei soll geschärft oder neu strukturiert werden - Ein Prompt muss zwischen interner Drift-Nutzung und externem Field-Test sauber getrennt werden
- Frontmatter, Phasen, Artefakte oder Report-Struktur eines Prompts sollen standardisiert werden
Kernregeln
- Zuerst das Drift Policy Gate ausführen. Ein gut formulierter Prompt für unzulässige Arbeit bleibt unzulässig.
- Prompts sind modellunabhängig und auf Deutsch. Keine Modellversions-Annahmen oder englische Prompt-Standards einführen.
- Shared Partials wiederverwenden statt Konventionen zu duplizieren. Taxonomie, Issue-Filing und Grundkonventionen haben jeweils eine Single Source of Truth.
- Ein Drift-Prompt muss Erkenntnis erzeugen, nicht Dekoration. Jede Phase soll zu Beobachtung, Artefakt oder Entscheidung führen.
- Vor dem Schreiben die richtige Prompt-Klasse wählen. Interne Prompts und Field-Test-Prompts folgen unterschiedlichen Freshness- und Filing-Regeln.
Schritt 0: Drift Policy Gate Ausführen
Vor dem Drafting des Prompts das verpflichtende Gate aus .github/instructions/drift-policy.instructions.md verwenden.
Schritt 1: Prompt-Scope Festlegen
Zuerst entscheiden, zu welcher Prompt-Familie der neue Prompt gehört:
- Interner Drift-Prompt unter
.github/prompts/verwenden, wenn der Prompt den Drift-Workspace, die Drift-CLI oder Drift-interne Entwicklungsworkflows bewertet - Field-Test-Prompt unter
.github/prompts/field-tests/verwenden, wenn der Prompt Drift gegen beliebige externe Repositories testet
Faustregel fuer die Primitive-Wahl:
- Instruction-Datei, wenn die Regel immer gelten und automatisch angewendet werden soll
- Skill, wenn ein wiederverwendbarer Operator-Workflow on-demand geladen werden soll
- Prompt, wenn ein konkreter mehrphasiger Arbeitsablauf mit Ziel, Artefakten und Bewertung ausgefuehrt werden soll
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.
- 12d ago First seen · 193 lines · 115 tokens per session scan A a14c518a715c
drift-agent-prompt-authoring is a skill published in the GitHub repository mick-gsk/drift (15 stars, last pushed 1mo ago), licensed MIT. It adds 115 tokens to every session and 2,014 once invoked, about $0.0006 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.
Other skills, from other repositories
contract-derivation
Use this skill after a design document exists and before any module is implemented. It takes a design doc and derives per-module contracts (manifests) that are complete enough for an implementor working in isolation to build each module correctly without seeing the rest of the system. Trigger this whenever the user…
design-doc
Use this skill before writing any non-trivial code, especially when starting a new feature, service, or codebase. It produces a structural design document that commits to module boundaries, contracts, and data shapes BEFORE implementation begins. Trigger this whenever the user describes building something new, asks to…
dispatcher
Use this skill when running a Taniwha build from the main Claude Code session. The skill turns the main session into a thin, mechanical executor that follows instructions from ephemeral orchestrator subagents. Trigger this whenever the user wants to start a Taniwha build, resume an interrupted one, or work on a…
verifier
Use this skill when verifying that a completed Taniwha implementation or composition satisfies its contract's acceptance criteria. The verifier reads the contract, the implementation's source files, and the project context, then writes its own tests against the contract's acceptance criteria, runs them, and reports…
composition
Use this skill when wiring two completed modules together to satisfy a parent contract, especially in a compartmentalised setting. Trigger this whenever the user has two implemented modules (each with its manifest) and a parent contract that says how they should compose, when the user asks to "compose these modules"…
leaf-implementation
Use this skill when implementing a single module against a contract manifest, especially in a compartmentalised setting where the implementor should NOT see the rest of the system. Trigger this whenever a manifest exists and the user wants to implement that module, asks to "implement this module", "build against this…