compliance-drift-evals

compliance-drift-evals is a skill for Claude Code, Codex from ucsandman/dashclaw-skills. It costs 22 tokens per session (2,034 once invoked), scanned A, a copy of compliance-drift-evals, MIT.

A set of tools for checking whether AI agents follow organisational rules and how their behaviour changes over time. It can create evidence reports for standards such as SOC 2, NIST AI RMF, the EU AI Act, and ISO 42001.

In plain words
What is it for?
Use it to generate or schedule compliance exports, detect changes in agent behaviour, run evaluations, assign scores, and review learning trends.
Why use it?
It reduces the manual work of collecting audit evidence, spotting behaviour drift, scoring agent quality, and tracking improvements.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Use it to generate or schedule compliance exports, detect changes in agent behaviour, run evaluations, assign scores, and review learning trends.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/ucsandman/dashclaw-skills/compliance-drift-evals
Install

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.

Any agent
npx skills add ucsandman/dashclaw-skills --skill compliance-drift-evals
Clone the repo
git clone --depth 1 https://github.com/ucsandman/dashclaw-skills

Made for: Claude Code, Codex.

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 compliance-drift-evals

README.md
[![agentmods](https://agentmods.dev/badge/skills/ucsandman/dashclaw-skills/compliance-drift-evals/github.svg)](https://agentmods.dev/skills/ucsandman/dashclaw-skills/compliance-drift-evals)
Your own site
<a href="https://agentmods.dev/skills/ucsandman/dashclaw-skills/compliance-drift-evals"><img src="https://agentmods.dev/badge/skills/ucsandman/dashclaw-skills/compliance-drift-evals/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 compliance-drift-evals

Your own site · 80×15
<a href="https://agentmods.dev/skills/ucsandman/dashclaw-skills/compliance-drift-evals"><img src="https://agentmods.dev/badge/skills/ucsandman/dashclaw-skills/compliance-drift-evals.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 22 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,034 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. A grade says what 26 rules found in the file — not that it is safe.
Origin 100% copy Near-identical to another mod 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 $0.00022 $0.02034
Opus 5 $0.00011 $0.01017
Sonnet 5 $0.00004 $0.00407
Haiku 4.5 $0.00002 $0.00203

Measured 11d ago against content hash 1bdcfbf46d62, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

compliance-drift-evals scanned grade A with 1 finding 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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

curl -X POST "$DASHCLAW_BASE_URL/api/compliance/exports" \
Origin

This is a copy

100% identical to compliance-drift-evals — 0 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.

skills/compliance-drift-evals/SKILL.md · 322 lines

How it starts

The opening of the file, as written. The whole thing — 322 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Compliance, Drift, Evaluations & Learning

DashClaw's analytical capabilities for governance evidence, behavioral monitoring, and agent quality tracking.


Compliance Exports

Generate audit-ready evidence bundles for regulatory frameworks.

Supported Frameworks

Framework ID Description
SOC 2 soc2 Service Organization Control
NIST AI RMF nist-ai-rmf AI Risk Management Framework
EU AI Act eu-ai-act European AI regulation
ISO 42001 iso42001 AI Management System

Create an Export

// V1 SDK
const exp = await claw.createComplianceExport({
  name: 'Q1 2026 SOC 2 Audit',
  frameworks: ['soc2'],
  format: 'json',        // or 'md'
  window_days: 90,
  include_evidence: true,
  include_remediation: true,
  include_trends: true
});
# API
curl -X POST "$DASHCLAW_BASE_URL/api/compliance/exports" \
  -H "x-api-key: $DASHCLAW_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"name":"Q1 Audit","frameworks":["soc2"],"window_days":90}'

Scheduled Exports

await claw.createComplianceSchedule({
  name: 'Weekly SOC 2',
  frameworks: ['soc2'],
  cron_expression: '0 9 * * 1',  // Every Monday at 9am
  window_days: 7,
  include_evidence: true
});

Gap Analysis

const gaps = await claw.analyzeGaps('soc2');
// Returns: missing controls, partial coverage, recommendations

Coverage Trends

const trends = await claw.getComplianceTrends({ framework: 'soc2', limit: 12 });
// Monthly coverage scores over time

Drift Detection

Statistical behavioral drift detection using z-scores. Pure math — no LLM required.

6 Tracked Metrics

Metric What It Measures
risk_score Are actions getting riskier?
confidence Is agent confidence dropping?
duration_ms Are actions taking longer?
cost_estimate Are costs increasing?
tokens_total Is token usage growing?
learning_score Is the agent learning?

Read the full file on GitHub · 322 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 · 322 lines · 22 tokens per session scan A 1bdcfbf46d62

Subscribe to this mod's changes

compliance-drift-evals is a skill published in the GitHub repository ucsandman/dashclaw-skills (2 stars, last pushed 3d ago), licensed MIT. It adds 22 tokens to every session and 2,034 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). It is 100% identical to compliance-drift-evals, differing in 0 lines, and is treated as a copy.

Related

Other skills, from other repositories

specification-writing

A workflow for writing complete patent specifications from patent claims and an invention disclosure. It adapts the document to a chosen jurisdiction, such as the US, Europe, or China.

wanshuiyin/Auto-claude-code-research-in-sleep · 49 tokens

regulatory-research-fallback

Fallback workflow for regulatory research when web extraction tools fail on government PDFs.

HKUDS/OpenSpace · 20 tokens

x-scorecard

OpenSSF Scorecard for assessing open source project security. Check security best practices and compliance. Dependency: This is an x-cmd module. Install x-cmd first (see x-cmd skill for installation options). see x-cmd skill for installation.

x-cmd/x-cmd · 57 tokens

gesellschaftsrechtliche-satzungen-agb

Für Gesellschaftsrechtliche Satzungen AGB Abgrenzung: ordnet Norm, Beweislast und Gegenargument; Ergebnis: Prüfprodukt mit Risiko und nächstem Schritt. Fachgebiet: AGB-Recht-Prüfer. Route: gesellschaftsrechtliche-satzungen-agb.

Klotzkette/claude-fuer-deutsches-recht · 69 tokens

memstack-business-gdpr

Use this skill when the user says 'GDPR', 'data protection', 'privacy compliance', 'DPA', 'DSAR', 'data subject request', 'cookie consent', 'privacy audit', 'CCPA', or asks 'do I need GDPR for this repo'. Scans the repository to detect what personal data is collected, classifies sensitivity, determines whether GDPR…

cwinvestments/memstack · 121 tokens

nda-review

Use when the user uploads or pastes a non-disclosure agreement and asks for review, redline, risk assessment, or a recommendation on whether to sign. Identifies missing standard protections, one-sided or unusual provisions, and operational issues; produces a structured report with severity ratings and citations to…

LegalQuants/lq-ai · 79 tokens