drift: Skill for Claude Code

.github/skills/drift-risk-audit-artifact-updates/SKILL.md

drift-risk-audit-artifact-updates is a skill for Claude Code from mick-gsk/drift. It costs 92 tokens per session (1,466 once invoked), scanned A, original, MIT.

A workflow for updating Drift’s required security and risk records after certain code changes. These records include FMEA, fault trees, STRIDE reviews, and a risk register—structured ways to document failures, threats, and risks.

In plain words
What is it for?
Use it to classify a change, select the correct record under `audit_results/`, update it, and verify that the protected audit files remain present.
Why use it?
It helps keep the audit records consistent with changes to signals, data intake, outputs, trust boundaries, or measured accuracy, so the pre-push checks do not fail.

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-risk-audit-artifact-updates/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-risk-audit-artifact-updates

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

Your own site · 80×15
<a href="https://agentmods.dev/skills/mick-gsk/drift/drift-risk-audit-artifact-updates"><img src="https://agentmods.dev/badge/skills/mick-gsk/drift/drift-risk-audit-artifact-updates.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 92 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,466 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 $0.00092 $0.01466
Opus 5 $0.00046 $0.00733
Sonnet 5 $0.00018 $0.00293
Haiku 4.5 $0.00009 $0.00147

Measured 11d ago against content hash 6e2674376016, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

drift-risk-audit-artifact-updates 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-risk-audit-artifact-updates/SKILL.md · 179 lines

How it starts

The opening of the file, as written. The whole thing — 179 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Drift Risk Audit Artifact Updates Skill

Use this skill when a Drift change requires explicit updates to the audit stack under audit_results/.

When To Use

  • A file under src/drift/signals/ changes materially
  • A file under src/drift/ingestion/ changes materially
  • A file under src/drift/output/ changes materially
  • An input path, output path, or trust boundary changes
  • Precision or recall changes by more than 5 percentage points
  • A push would otherwise fail the risk-audit gate

Core Rules

  1. Run the Drift Policy Gate first. Audit updates do not rescue inadmissible work.
  2. Treat audit artifacts as contracts, not optional docs. POLICY §18 makes them mandatory.
  3. Update the right artifact for the change type. Any audit file is not enough.
  4. Never delete the four protected audit artifacts. The gate checks existence.
  5. Use bypasses only with explicit maintainer approval and a documented emergency reason.

Step 0: Run The Drift Policy Gate

Before touching the audit stack, use the gate format from .github/instructions/drift-policy.instructions.md.

Step 1: Classify The Change

Sort the implementation into one of these categories:

A. Signal changed

Examples:

  • new signal
  • materially changed heuristic
  • changed finding criteria
  • changed scoring-readiness behavior

Treat a change as material when it changes detection scope, improves or worsens precision/recall in a meaningful way, alters actionable output, or changes what reviewers must trust about the signal.

B. Input/output or trust boundary changed

Examples:

  • new ingestion path
  • new output channel
  • changed output contract or trust boundary

C. Precision/recall shifted by more than 5 percentage points

Examples:

  • threshold tuning
  • strong FP reduction
  • recall hardening with measurable delta

If more than one category applies, update the union of required artifacts.

Step 2: Map The Change To Required Artifacts

Use this mapping exactly:

  • Signal changed update audit_results/fmea_matrix.md, audit_results/fault_trees.md, and audit_results/risk_register.md
  • Input/output or trust boundary changed update audit_results/stride_threat_model.md and audit_results/risk_register.md
  • Precision/recall delta > 5% update audit_results/fmea_matrix.md and audit_results/risk_register.md

Read the full file on GitHub · 179 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 · 179 lines · 92 tokens per session scan A 6e2674376016

Subscribe to this mod's changes

drift-risk-audit-artifact-updates is a skill published in the GitHub repository mick-gsk/drift (15 stars, last pushed 1mo ago), licensed MIT. It adds 92 tokens to every session and 1,466 once invoked, about $0.0005 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

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

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

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