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-quality-workflowgit 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-quality-workflow)<a href="https://agentmods.dev/instructions/mick-gsk/drift/drift-quality-workflow"><img src="https://agentmods.dev/badge/instructions/mick-gsk/drift/drift-quality-workflow.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 | $0.01887 | $0.01887 |
| Opus 5 | $0.00944 | $0.00944 |
| Sonnet 5 | $0.00377 | $0.00377 |
| Haiku 4.5 | $0.00189 | $0.00189 |
Grade A, and why
drift drift-quality-workflow.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 — 191 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Drift Quality Workflow — Verbindlicher Arbeitsstandard
Dieser Standard gilt workspace-weit für alle nicht-trivialen Änderungen an Code, Architektur, Tests, Refactorings und Features. Er ist kein Vorschlag — er ist bindend.
Geltungsbereich
Dieser Workflow ist Pflicht, wenn mindestens einer dieser Punkte zutrifft:
- neues Feature oder neue Benutzerwirkung
- Refactoring mit möglichem Verhaltenseinfluss
- Bugfix mit nicht-trivialem Impact
- Architektur-, Integrations- oder I/O-Änderung
- Änderung an Tests, CI oder Release-/Packaging-Pfaden
- Änderung an Prompt-, Agenten-, Skill- oder Automationslogik
Dieser Workflow kann reduziert werden bei:
- kleinen Textkorrekturen
- harmlosen Renames ohne Seiteneffekte
- rein mechanischen Änderungen mit nachweislich geringem Risiko
Zweifel → voller Workflow.
Aufgaben-Priorisierungsreihenfolge (Feature-First-Bias vermeiden)
Bevor eine Aufgabe begonnen wird, gilt folgende feste Reihenfolge:
- Kritische Bugfixes
- Audit-Artefakte und Dev-Infrastruktur (Tests, CI) — Voraussetzung für alles andere
- Signal-Features als Tracer Bullet (dünner End-to-End-Slice zuerst)
- Vollständige Feature-Implementierung
- Refactoring und Polish
Agenten wählen ohne explizite Reihenfolge typischerweise die „interessanteste“ Aufgabe und überspringen dabei notwendige Infrastruktur. Diese Reihenfolge verhindert das.
Verbindlicher Standardprozess (7 Stufen)
Stufe 1 — Dual-Agent-Implementierung
Jede relevante Aufgabe wird mit zwei Rollen bearbeitet:
- Implementierer-Rolle: setzt die Änderung um
- Reviewer-Rolle (adversarial): sucht aktiv nach Bugs, Logiklücken, Spezifikationsverletzungen, riskanten Annahmen, Regressionen und fehlenden Tests
Die Reviewer-Rolle nimmt gezielt eine Gegenposition ein. Ziel ist nicht Bestätigung, sondern Schwachstellenfindung.
Stufe 2 — Iterativer Review-Loop
Implementierung und adversarialer Review laufen in Schleifen, bis die Lösung:
- fachlich konsistent ist
- technisch plausibel ist
- hinreichend robust ist
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 · 191 lines · 1,887 tokens per session scan A 531d5a80c505
drift drift-quality-workflow.instructions.md is an instructions file published in the GitHub repository mick-gsk/drift (14 stars, last pushed 1mo ago), licensed MIT. It adds 1,887 tokens to every session, about $0.0094 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 release-checklist.instructions.md
Plan Forge release procedure — auto-loads when editing release-related files. Maintainer-only; NOT shipped to consuming projects.
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.
packmind packmind-changelog.instructions.md
Instructions for PackmindHub/packmind: Maintain a consistent and well-structured CHANGELOG.MD file following the Keep a Changelog format to ensure all releases are properly documented with accurate version links and dates. This standard ap... .
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.