drift: Skill for Claude Code

.github/skills/drift-adr-workflow/SKILL.md

drift-adr-workflow is a skill for Claude Code from mick-gsk/drift. It costs 60 tokens per session (1,405 once invoked), scanned A, original, MIT.

A workflow for recording architectural and product decisions in ADRs, short documents that explain what was decided and why, for the Drift project.

In plain words
What is it for?
Use it before adding or materially changing a signal, scoring rule, output contract, input path, output path, or architecture boundary. Agents may draft decisions, while maintainers accept or reject them.
Why use it?
It ensures important changes to signals, scores, output formats, or system boundaries are considered before implementation. Each decision must include checks that can verify the result.

Skill for Claude Code

Written for Claude Code: argument-hint in frontmatter. Also seen: mentions subagents.

This is mick-gsk/drift's own configuration. It tells Claude Code how to work on drift itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything drift configures →

Needs its repository: it runs a file that does not travel with it, so clone the repository first. The line is python scripts/check_risk_audit.py --diff-base origin/main.

Part of the drift plugin — 31 skills, 17 agents shipped together

Reuse

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.

Copy the file
curl -O https://raw.githubusercontent.com/mick-gsk/drift/main/.github/skills/drift-adr-workflow/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/mick-gsk/drift

Made for: Claude Code.

Or install drift, the plugin that ships this one along with the rest of its 31 skills, 17 agents.

Wrote 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.

agentmods badge for drift-adr-workflow

README.md
[![agentmods](https://agentmods.dev/badge/skills/mick-gsk/drift/drift-adr-workflow.svg)](https://agentmods.dev/skills/mick-gsk/drift/drift-adr-workflow)
Your own site
<a href="https://agentmods.dev/skills/mick-gsk/drift/drift-adr-workflow"><img src="https://agentmods.dev/badge/skills/mick-gsk/drift/drift-adr-workflow.svg" alt="Measured on agentmods" height="20"></a>
Per session 60 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,405 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00060 $0.01405
Opus 5 $0.00030 $0.00702
Sonnet 5 $0.00012 $0.00281
Haiku 4.5 $0.00006 $0.00140

Measured 8d ago against content hash 13213cec4a6a, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

drift-adr-workflow 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 8d 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.

.github/skills/drift-adr-workflow/SKILL.md · 169 lines

How it starts

The opening of the file, as written. The whole thing — 169 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Drift ADR Workflow Skill

Use this skill when a Drift change needs a documented architectural or product decision before implementation.

When To Use

  • A signal is added or materially changed
  • Scoring logic or weights are changed
  • Output formats or output contracts are changed
  • An architecture boundary, trust boundary, input path, or output path changes
  • An existing ADR draft must be completed or validated

Core Rules

  1. Run the Drift Policy Gate first. If the task is not admissible, stop.
  2. ADR first, implementation second. For signal, scoring, output-format, or architecture-boundary changes, prepare the ADR before coding.
  3. Agents may draft, not accept. Agents may create or update ADRs with status proposed; only the maintainer changes status to accepted or rejected.
  4. Validation must be testable. Every ADR needs a concrete validation section with measurable checks or outcomes.
  5. Do not blur bugfixes and architectural decisions. Pure bugfixes and pure refactorings do not automatically require a new ADR.

Step 0: Run The Drift Policy Gate

Before drafting an ADR, use the mandatory gate format from .github/instructions/drift-policy.instructions.md.

If the task fails the gate, do not create an ADR to legitimize inadmissible work.

Step 1: Decide Whether An ADR Is Required

Create or update an ADR when the change affects one of these categories:

  • signal design or signal behavior
  • scoring or prioritization logic
  • output schema or result format
  • architecture or trust boundaries

Do not force a new ADR for:

  • typo fixes
  • isolated test-only work
  • pure refactors without behavior change
  • contained bugfixes that preserve the existing design decision without materially changing signal behavior, scoring logic, output contracts, or trust assumptions

If unsure, prefer a draft ADR that states the uncertainty explicitly.

Interface-Design-Tipp: Vor dem Festschreiben eines Signal- oder API-Interface-Designs lohnt es sich, 2–3 Sub-Agenten mit explizit verschiedenen Constraints parallel zu spawnen (z. B. „minimiere das Interface", „maximiere Flexibilität", „optimiere für den häufigsten Caller"). Radikale Constraint-Divergenz erzwingt qualitativ unterschiedliche Designs — parallele Agenten ohne Vorgaben konvergieren meist zu ähnlichen Lösungen. Das subagent-driven-development-Skill liefert den operativen Rahmen.

Read the full file on GitHub · 169 lines

Changes

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.

  1. 8d ago First seen · 169 lines · 60 tokens per session scan A 13213cec4a6a

Subscribe to this mod's changes

drift-adr-workflow is a skill published in the GitHub repository mick-gsk/drift (15 stars, last pushed 1mo ago), licensed MIT. It adds 60 tokens to every session and 1,405 once invoked, about $0.0003 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.

Related

Other skills, from other repositories

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…

taniwhaai/arai · 153 tokens

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…

taniwhaai/arai · 134 tokens

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…

taniwhaai/arai · 137 tokens

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…

taniwhaai/arai · 122 tokens

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"…

taniwhaai/arai · 136 tokens

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…

taniwhaai/arai · 133 tokens