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-push-gatesgit 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-push-gates)<a href="https://agentmods.dev/instructions/mick-gsk/drift/drift-push-gates"><img src="https://agentmods.dev/badge/instructions/mick-gsk/drift/drift-push-gates.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 | $0.02980 | $0.02980 |
| Opus 5 | $0.01490 | $0.01490 |
| Sonnet 5 | $0.00596 | $0.00596 |
| Haiku 4.5 | $0.00298 | $0.00298 |
Grade A, and why
drift drift-push-gates.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 — 246 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Drift Pre-Push Gates — Vollständige Checkliste für Agenten
Der Hook in .githooks/pre-push blockiert jeden Push, der eine der folgenden Bedingungen verletzt.
Agenten müssen alle zutreffenden Gates erfüllen, bevor sie git push ausführen.
Diese Datei ist nur fuer Commit-/Push-Vorbereitung relevant, nicht fuer allgemeine Implementierungsarbeit.
Übersicht: Welches Gate gilt bei welcher Änderung?
feat: / fix: / BREAKING: folgen den Conventional-Commit-Regeln aus .github/instructions/drift-release-automation.instructions.md.
| Geänderte Dateien | Erforderliches Gate |
|---|---|
tagesplanung/** |
❌ Immer blockiert — nie pushen |
feat:-Commit vorhanden |
Feature-Evidence-Gate (Gate 2) |
feat: oder fix:-Commit vorhanden |
Changelog-Gate (Gate 3) |
pyproject.toml geändert |
Version-Gate (Gate 4) + Lockfile-Gate (Gate 5) |
src/drift/** geändert |
Docstring-Gate (Gate 6) |
src/drift/signals/**, src/drift/ingestion/** oder src/drift/output/** geändert |
Risk-Audit-Gate (Gate 7) |
| Immer (alle Pushes) | CI-Checks (Gate 8) |
Gate 1 — Blockierte Pfade
Bedingung: Kein Commit darf Dateien unter tagesplanung/ enthalten.
Auslöser: Immer (jeder Push).
Aktion: Diese Pfade niemals committen.
Gate 2 — Feature-Evidence-Gate
Auslöser: Push enthält mindestens einen Commit mit Prefix feat: (oder feat(scope):).
Alle vier Bedingungen müssen gleichzeitig erfüllt sein:
- Tests vorhanden: Mindestens eine Datei unter
tests/muss im Push enthalten sein. - Empirisches Artefakt vorhanden: Mindestens eine Datei unter
benchmark_results/oderaudit_results/muss im Push enthalten sein. - Versioned Evidence-Datei vorhanden: Eine Datei die auf
benchmark_results/vX.Y.Z_feature_evidence.jsonmatcht (oder entsprechendes Muster). - STUDY.md aktualisiert:
docs/STUDY.mdmuss im Push enthalten sein (sofern die Datei existiert).
Gate 2b — Evidence Content Validation (deterministisch)
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 · 246 lines · 2,980 tokens per session scan A b1d19b075e01
drift drift-push-gates.instructions.md is an instructions file published in the GitHub repository mick-gsk/drift (14 stars, last pushed 1mo ago), licensed MIT. It adds 2,980 tokens to every session, about $0.0149 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
plan-forge version.instructions.md
Version management — Semantic versioning, auto-increment, commit-driven version bumps, release tagging.
plan-forge git-workflow.instructions.md
Git workflow and commit conventions — conventional commits, push reminders, version-aware messaging.
Specflow CLAUDE.md
Instructions for Hulupeep/Specflow, covering claude.md, project context, specflow rules, rule 1: no ticket = no code and rule 2: commits must reference an issue.
plan-forge release-checklist.instructions.md
Plan Forge release procedure — auto-loads when editing release-related files. Maintainer-only; NOT shipped to consuming projects.
relay AGENTS.md
AGENTS.md instructions for AgentWorkforce/relay, covering git workflow rules, never push directly to main, correct workflow, ... do work .. and stop here - let user merge.
plan-forge copilot-instructions.md
Copilot instructions for srnichols/plan-forge, covering instructions for copilot, architecture principles, core principles (non-negotiable), cost estimates and talking to forge-master.