drift: Skill for Claude Code

.github/skills/drift-signal-development-full-lifecycle/SKILL.md

drift-signal-development-full-lifecycle is a skill for Claude Code from mick-gsk/drift. It costs 79 tokens per session (1,668 once invoked), scanned A, original, MIT.

A full workflow for creating or substantially changing Drift signals, which are rules that identify patterns in code or data. It covers design, implementation, test evidence, audits, and validation.

In plain words
What is it for?
Use it when adding a signal, changing its detection logic or weights, preparing it for scoring, or checking precision and recall—the shares of results that are correct and of relevant cases that were found.
Why use it?
It prevents signal changes from being made without checking whether they are allowed, reliable, reproducible, and useful. It also makes incomplete work easier to catch before commit.

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 →

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-signal-development-full-lifecycle/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-signal-development-full-lifecycle

README.md
[![agentmods](https://agentmods.dev/badge/skills/mick-gsk/drift/drift-signal-development-full-lifecycle/github.svg)](https://agentmods.dev/skills/mick-gsk/drift/drift-signal-development-full-lifecycle)
Your own site
<a href="https://agentmods.dev/skills/mick-gsk/drift/drift-signal-development-full-lifecycle"><img src="https://agentmods.dev/badge/skills/mick-gsk/drift/drift-signal-development-full-lifecycle/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-signal-development-full-lifecycle

Your own site · 80×15
<a href="https://agentmods.dev/skills/mick-gsk/drift/drift-signal-development-full-lifecycle"><img src="https://agentmods.dev/badge/skills/mick-gsk/drift/drift-signal-development-full-lifecycle.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 79 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,668 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 $0.00079 $0.01668
Opus 5 $0.00039 $0.00834
Sonnet 5 $0.00016 $0.00334
Haiku 4.5 $0.00008 $0.00167

Measured 11d ago against content hash 8e78efe10da0, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

drift-signal-development-full-lifecycle 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 11d 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-signal-development-full-lifecycle/SKILL.md · 189 lines

How it starts

The opening of the file, as written. The whole thing — 189 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Drift Signal Development Full Lifecycle Skill

Use this skill for non-trivial signal work from decision through validation.

When To Use

  • A new signal is being added
  • An existing signal changes materially
  • A signal heuristic is recalibrated in a way that affects trust, precision, or recall
  • A signal is being prepared for scoring readiness or report-only hardening

Core Rules

  1. Run the Drift Policy Gate first. Signal work that fails admissibility should stop before design begins.
  2. ADR before implementation. Non-trivial signal work needs an ADR draft before code changes.
  3. Every signal must be explicit about scope. Declare incremental_scope on the class.
  4. Evidence is mandatory. Signal logic without fixtures, targeted tests, and audit updates is incomplete.
  5. Optimize for credibility before comfort. Precision, reproducibility, and actionability outrank convenience or breadth.

Step 0: Run The Drift Policy Gate

Use the gate format from .github/instructions/drift-policy.instructions.md before doing design or implementation work.

Step 1: Start With Decision And Design

Before coding:

  • decide whether the task is a new signal, a material heuristic change, or a calibration pass
  • draft or update the ADR using the drift-adr-workflow skill
  • use docs/decisions/templates/signal-design-template.md for signal-centric decisions

If a calibration materially changes signal behavior, scoring implications, or reviewer trust expectations, treat it as ADR-worthy even when it is framed as precision/recall hardening.

The design should already state:

  • the problem class
  • heuristic outline
  • expected FP classes
  • expected FN classes
  • fixture plan
  • validation criterion

Step 2: Implement The Signal Class Correctly

New signal code belongs in its own file under src/drift/signals/. For changes to an existing signal, keep the work in that signal's existing file unless there is a separately justified design change.

Implement the class as a BaseSignal subclass and register it with @register_signal.

Read the full file on GitHub · 189 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. 11d ago First seen · 189 lines · 79 tokens per session scan A 8e78efe10da0

Subscribe to this mod's changes

drift-signal-development-full-lifecycle is a skill published in the GitHub repository mick-gsk/drift (15 stars, last pushed 1mo ago), licensed MIT. It adds 79 tokens to every session and 1,668 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