Borrowing it
Nothing to install: this file belongs to ucsandman/DashClaw. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/ucsandman/DashClaw/main/.claude/skills/dashclaw-agent/compliance-drift-evals/SKILL.mdgit clone --depth 1 https://github.com/ucsandman/DashClawWrote 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.
[](https://agentmods.dev/skills/ucsandman/dashclaw/compliance-drift-evals)<a href="https://agentmods.dev/skills/ucsandman/dashclaw/compliance-drift-evals"><img src="https://agentmods.dev/badge/skills/ucsandman/dashclaw/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.
<a href="https://agentmods.dev/skills/ucsandman/dashclaw/compliance-drift-evals"><img src="https://agentmods.dev/badge/skills/ucsandman/dashclaw/compliance-drift-evals.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Data Exfiltration · line 47 Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.Fix: Verify the destination URL is trusted and necessary. Remove or replace with documented APIs. Ensure no secrets, tokens, or PII are transmitted.
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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00022 | $0.02034 |
| Opus 5.5 | $0.00009 | $0.00814 |
| Sonnet 5.5 | $0.00004 | $0.00407 |
| Haiku 4.5 | $0.00002 | $0.00203 |
Grade A, and why
compliance-drift-evals scanned grade A with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 1mo ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
curl -X POST "$DASHCLAW_BASE_URL/api/compliance/exports" \ Copies of this mod
1 near-identical copy found in the catalogue:
- compliance-drift-evals — 100% identical, 0 lines differ
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? |
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.
- 1mo ago First seen · 322 lines · 22 tokens per session scan A 1bdcfbf46d62
compliance-drift-evals is a skill published in the GitHub repository ucsandman/DashClaw (313 stars, last pushed yesterday), licensed MIT. It adds 22 tokens to every session and 2,034 once invoked, about $0.0001 per session on Opus 5.5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
text2agent
Creates new agents from user requirements by generating Python implementation and mcpconfig.
optimizer
Analyzes and automatically optimizes existing agents by improving system prompts and tool configuration.
app_evaluator
A professional skill for App Evaluation (evaluating app's performance with score) and App Improvement (giving professional suggestions for improving the app's performance).
ad_video_create
Create ad-ready product video from product images, with or without character/subject images. The workflow leverages AI-powered image composition, scene understanding, and video generation. Video prompts should follow commercial shot language—visual hooks, product presence, hero shots, detail showcase, function…
last_7_days_news
Search and summarize the latest 7 days of AI news and X discussions using public sources plus browser-based X collection. Use for recent AI news, trends, X discussions, industry briefs, and summaries organized into hot topics, viewpoints, and opportunity areas.
self_evolve
Use for framework-gated self-evolve workflows in AWorld: evolve skills, create trajectory-backed proposals, inspect self-evolve run artifacts, run aworld-cli optimize, or prepare verified apply decisions through aworld.selfevolve gates.