drift: Skill for Claude Code

.github/skills/drift-ground-truth-fixture-development/SKILL.md

drift-ground-truth-fixture-development is a skill for Claude Code from mick-gsk/drift. It costs 89 tokens per session (1,477 once invoked), scanned A, original, MIT.

A Drift-specific workflow for creating and checking ground-truth test fixtures. Ground truth means labeled examples used to measure whether a detection system finds real cases and rejects false ones.

In plain words
What is it for?
Use it when adding true-positive, true-negative, boundary, or confounder fixtures, or when testing behavior that depends on file history.
Why use it?
It makes signal tests small, repeatable, and explicit, including edge cases and harmless examples that could otherwise cause false alarms.

Skill for Claude Code

Written for Claude Code: argument-hint in frontmatter.

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 →

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-ground-truth-fixture-development/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-ground-truth-fixture-development

README.md
[![agentmods](https://agentmods.dev/badge/skills/mick-gsk/drift/drift-ground-truth-fixture-development/github.svg)](https://agentmods.dev/skills/mick-gsk/drift/drift-ground-truth-fixture-development)
Your own site
<a href="https://agentmods.dev/skills/mick-gsk/drift/drift-ground-truth-fixture-development"><img src="https://agentmods.dev/badge/skills/mick-gsk/drift/drift-ground-truth-fixture-development/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for drift-ground-truth-fixture-development

Your own site · 80×15
<a href="https://agentmods.dev/skills/mick-gsk/drift/drift-ground-truth-fixture-development"><img src="https://agentmods.dev/badge/skills/mick-gsk/drift/drift-ground-truth-fixture-development.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 89 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,477 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 $0.00089 $0.01477
Opus 5 $0.00044 $0.00739
Sonnet 5 $0.00018 $0.00295
Haiku 4.5 $0.00009 $0.00148

Measured 10d ago against content hash 1424ebd7b8c0, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

drift-ground-truth-fixture-development 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 10d 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-ground-truth-fixture-development/SKILL.md · 168 lines

How it starts

The opening of the file, as written. The whole thing — 168 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Drift Ground-Truth Fixture Development Skill

Use this skill when Drift needs reproducible fixture coverage for signal behavior.

When To Use

  • A new signal needs baseline TP and TN coverage
  • A false positive or false negative needs to become a regression fixture
  • A threshold or calibration change needs boundary coverage
  • A benign lookalike case needs a confounder fixture
  • A signal depends on history-like data and needs file_history_overrides

Core Rules

  1. Run the Drift Policy Gate first. Fixtures should validate admissible work, not justify inadmissible work.
  2. Keep fixtures minimal and deterministic. No external dependencies, no hidden runtime assumptions.
  3. Every fixture needs explicit expectations. Empty fixtures are invalid.
  4. Prefer source-like realism over size. Small but representative beats large and noisy.
  5. Use fixture kinds intentionally. TP/TN are the baseline; boundary and confounder cases are for calibration and trust hardening.
  6. Fixture und Logik zusammen bauen — nicht alle Fixtures zuerst. Eine TP-Fixture schreiben, die passende Signal-Logik implementieren, dann TN. Horizontales Batch-Schreiben produziert Tests gegen imaginiertes Verhalten.
  7. Nur an echten Systemgrenzen mocken. Externe APIs, Zeit und Dateisystem sind valide Mock-Ziele. Interne Signal-Methoden, AST-Helfer und Scoring-Zwischenwerte nicht — teste ausschließlich den Public-Output von analyze(). Kurzregel: AST/Scoring = in-process, direkt testbar; Git-History = file_history_overrides als lokaler Stand-in; externe HTTP-Calls = an der Interface-Grenze mocken.

Step 0: Run The Drift Policy Gate

Before adding or changing fixtures, use the gate format from .github/instructions/drift-policy.instructions.md.

Step 1: Choose The Right Fixture Type

Use these types deliberately:

  • positive the signal must fire
  • negative the signal must not fire
  • boundary the case sits near a threshold or decision edge
  • confounder the case looks like a real finding but is intentionally benign

Read the full file on GitHub · 168 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. 10d ago First seen · 168 lines · 89 tokens per session scan A 1424ebd7b8c0

Subscribe to this mod's changes

drift-ground-truth-fixture-development is a skill published in the GitHub repository mick-gsk/drift (15 stars, last pushed 1mo ago), licensed MIT. It adds 89 tokens to every session and 1,477 once invoked, about $0.0004 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

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

argot-check

Score your working changes with argot — flag code foreign to this repo's own patterns (unfamiliar dependencies, APIs, constructs), functions the repo already has, code filed in the wrong place, imports that break the repo's layering, and tests weakened, disabled, or deleted alongside a production change — before…

get-tmonier/argot · 110 tokens

refactoring-workflow

Improve the structure of existing code without changing its behaviour, in small verified steps under a green test suite. Use when the user asks to refactor, clean up, restructure or simplify code, wants to reduce duplication or coupling, is preparing a codebase for a feature it cannot currently accommodate, or when…

personamanagmentlayer/pcl · 83 tokens

ralphctl-test-driven-development

Execute-phase skill — write the failing test before the code that makes it pass; for bug fixes, this is the reproduction test itself. Use for any logic change, bug fix, or behavioural modification; for the full root-cause triage pipeline around an unexpected failure, see ralphctl-debugging-and-error-recovery.

lukas-grigis/ralphctl · 72 tokens

layer-check

Three-Layer Enforcement - Production Reality Gate.

samibs/skillfoundry · 11 tokens

gate-keeper

Rigorous quality guardian with auto-fix capability.

samibs/skillfoundry · 13 tokens