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/instructions/drift-rag-grounding.instructions.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/instructions/mick-gsk/drift/drift-rag-grounding)<a href="https://agentmods.dev/instructions/mick-gsk/drift/drift-rag-grounding"><img src="https://agentmods.dev/badge/instructions/mick-gsk/drift/drift-rag-grounding.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 5.1 | $0.00999 | $0.00999 |
| Opus 5 | $0.00500 | $0.00500 |
| Sonnet 5 | $0.00200 | $0.00200 |
| Haiku 4.5 | $0.00100 | $0.00100 |
Grade A, and why
drift drift-rag-grounding.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 6d 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 — 79 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Drift — RAG Grounding Contract (bindend fuer Agenten-Aussagen ueber drift selbst)
Diese Instruction erzwingt verifizierte Zitation fuer Agenten-Aussagen ueber drifts eigene Entscheidungsgrundlage. Sie ergaenzt die Drift Policy Instruction und ersetzt sie nicht.
Autoritative Quelle: ADR-091 — Drift-Retrieval-RAG.
PFLICHT-GATE: Grounding-Check
Dieses Gate zusaetzlich zum Drift Policy Gate sichtbar ausgeben, sobald eine Agenten-Antwort eine Behauptung ueber drift selbst enthaelt:
### Drift Grounding Gate
- Aussage ueber drift selbst (Policy/Signal/ADR/Audit/Evidence): [JA / NEIN]
- drift_retrieve aufgerufen: [JA / NEIN] → [Query-Text]
- zitierte Fact-IDs: [Liste mit mindestens einer ID oder "KEINE"]
- drift_cite verifiziert: [JA / NEIN / ENTFAELLT]
- Entscheidung: [ZULAESSIG / NACHZITIEREN]
Eine Antwort mit Aussage ueber drift selbst und ohne mindestens eine
zitierte fact_id ist ungueltig und muss vor der Rueckgabe um den
Retrieval-Aufruf ergaenzt werden.
Wann das Gate greift
Das Gate ist verpflichtend fuer Aussagen ueber:
- Policy-Regeln aus
POLICY.md(Zulassung, Ausschluss, Priorisierung, Audit-Pflicht, Telemetrie) - Signal-Rationale, Scoring-Gewichte, Scope (
file_localvs.cross_file) - ADR-Entscheidungen (z. B. „ADR-031 hat kNN-Semantic-Search verworfen")
- Audit-Artefakte (FMEA, STRIDE, Risk Register, Fault Trees)
- Benchmark-Evidence (Precision/Recall, Mutation-Detection, Latenz)
- Roadmap-Phasen und Einordnung von Features in Phasen
Das Gate greift nicht fuer:
- Aussagen ueber den vom User analysierten Ziel-Code (dafuer
drift_scan/drift_brief). - Allgemeine Softwareentwicklungsfragen ohne drift-Bezug.
- Erklaerungen aus
drift_explain, die bereits drifts eigene Doku-Quelle sind.
Operativer Ablauf
- Vor der Antwort
drift_retrieve(query="<Frage in eigenen Worten>", top_k=5)aufrufen. - Optional einschraenken:
kind(policy|roadmap|adr|audit|signal|evidence),signal_id(z. B.pattern_fragmentation). - Aus den Treffern mindestens eine passende
fact_idauswaehlen. - Bei Unsicherheit ueber den genauen Wortlaut
drift_cite(fact_id=...)aufrufen und dentext-Wert wortgetreu zitieren; dersha256-Anker macht die Zitation nachpruefbar. - Fact-ID im Antworttext in Backticks fuehren, z. B.
gemaess `POLICY#S8.p2` ….
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.
- 6d ago First seen · 79 lines · 999 tokens per session scan A 12a8f3b5c15d
drift drift-rag-grounding.instructions.md is an instructions file published in the GitHub repository mick-gsk/drift (15 stars, last pushed 1mo ago), licensed MIT. It adds 999 tokens to every session, about $0.0050 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
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.