Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add instructions/mick-gsk/drift/drift-policygit 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/instructions/mick-gsk/drift/drift-policy)<a href="https://agentmods.dev/instructions/mick-gsk/drift/drift-policy"><img src="https://agentmods.dev/badge/instructions/mick-gsk/drift/drift-policy.svg" alt="Measured on agentmods" 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 | $0.00683 | $0.00683 |
| Opus 5 | $0.00342 | $0.00342 |
| Sonnet 5 | $0.00137 | $0.00137 |
| Haiku 4.5 | $0.00068 | $0.00068 |
Grade A, and why
drift drift-policy.instructions.md 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 5d 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 — 54 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Drift — Policy (bindend für alle Dateioperationen)
POLICY.md im Workspace-Root ist die Single Source of Truth fuer Produkt-, Priorisierungs- und Risiko-Regeln.
Diese Instruction wiederholt die Policy nicht, sondern liefert das operative Gate-Format fuer Agenten.
PFLICHT-GATE: Zulässigkeitsprüfung — immer zuerst ausführen und ausgeben
Vor jeder Umsetzung dieses Format sichtbar ausgeben:
### Drift Policy Gate
- Aufgabe: [Kurzbeschreibung in einem Satz]
- Zulassungskriterium erfüllt: [JA / NEIN] → [Unsicherheit / Signal / Glaubwürdigkeit / Handlungsfähigkeit / Trend / Einführbarkeit]
- Ausschlusskriterium ausgelöst: [JA / NEIN] → [falls JA: welches]
- Roadmap-Phase: [1 / 2 / 3 / 4] — blockiert durch höhere Phase: [JA / NEIN]
- Betrifft Signal/Architektur (§18): [JA / NEIN] → falls JA: Audit-Artefakte aktualisiert: [welche]
- Entscheidung: [ZULÄSSIG / ABBRUCH]
- Begründung: [ein Satz]
Bei ABBRUCH: keine Umsetzung, stattdessen Erklärung + Gegenvorschlag.
Eine ZULÄSSIG-Entscheidung ist nur gültig, wenn das erfüllte Kriterium konkret zur Aufgabe passt. Generische Defaults ohne Aufgabenbezug sind ungültig.
Für rein mechanische, verhaltensneutrale Trivialaufgaben wie fix: typo, docs: wording, chore: lockfile refresh oder test: fixture rename ist dieses Kompaktformat zulässig:
### Drift Policy Gate
- Trivialtask: JA
- Zulässig: JA → rein mechanisch, ohne Verhaltens-, Policy-, Architektur- oder Signaleffekt
Nicht trivial sind insbesondere Änderungen an Policy, Instructions, Prompts, Skills, Agents, Signalen, Output-Formaten, CLI-Verhalten, Tests mit Verhaltensabsicherung oder Architekturgrenzen.
Autoritative Verweise in POLICY.md
- Zulassung und Ausschluss:
POLICY.md§8 und §9 - Priorisierung und Reihenfolge:
POLICY.md§6 und §7 - Befund-Qualität:
POLICY.md§13 - Unklare Entscheidungen:
POLICY.md§16 - Risiko-Audit-Pflichten:
POLICY.md§18
Zusatzhinweise fuer Agenten
- Bei Kollision zwischen dieser Datei und
POLICY.mdgilt immerPOLICY.md. - Bei Signalarbeit oder Architekturgrenzen zusaetzlich
.github/instructions/drift-push-gates.instructions.mdund die passenden Audit-/ADR-Workflows lesen. - Diese Datei ist absichtlich knapp, damit das Gate immer im Kontext bleibt, ohne die gesamte Policy zu duplizieren.
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.
- 5d ago First seen · 54 lines · 683 tokens per session scan A 422c738f5538
drift drift-policy.instructions.md is an instructions file published in the GitHub repository mick-gsk/drift (14 stars, last pushed 1mo ago), licensed MIT. It adds 683 tokens to every session, about $0.0034 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 instructions, from other repositories
truecourse CLAUDE.md
Claude Code instructions for truecourse-ai/truecourse, covering truecourse — claude instructions, key files to keep updated, project layout, development commands and storage.
PhpCodeArcheology CLAUDE.md
Instructions for PhpCodeArcheology/PhpCodeArcheology, covering claude.md — phpcodearcheology, project overview, language, tech stack and project structure.
skillfoundry copilot-instructions.md
Copilot instructions for samibs/skillfoundry, covering github copilot — skillfoundry project instructions, identity, non-negotiable rules, code quality and security.
skillfoundry AGENTS.md
AGENTS.md instructions for samibs/skillfoundry, covering what this is, philosophy, how to use skills, available skills by category and core workflow.
plan-forge auth.instructions.md
.NET authentication & authorization — JWT/OIDC, policy-based auth, multi-tenant isolation, API keys, testing.
plan-forge blazor-fluent-ui.instructions.md
Blazor Server + Microsoft Fluent UI patterns — component layering, state, lifecycle, accessibility. Auto-loads when editing .razor / .razor.cs files.