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.
npx agentmods add skills/michael-harris/devteam/devteam-design-driftnpx skills add michael-harris/devteam --skill devteam-design-driftgit clone --depth 1 https://github.com/michael-harris/devteamWhat 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 | $0.00031 | $0.00814 |
| Opus 5 | $0.00015 | $0.00407 |
| Sonnet 5 | $0.00006 | $0.00163 |
| Haiku 4.5 | $0.00003 | $0.00081 |
Grade A, and why
devteam-design-drift scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 104 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Current session: !source "${CLAUDE_PLUGIN_ROOT}/scripts/state.sh" && get_current_session 2>/dev/null || echo "No active session"
Active sprint: !source "${CLAUDE_PLUGIN_ROOT}/scripts/state.sh" && get_kv_state "active_sprint" 2>/dev/null || echo "None"
Failure count: !source "${CLAUDE_PLUGIN_ROOT}/scripts/state.sh" && get_kv_state "consecutive_failures" 2>/dev/null || echo "0"
DevTeam Design Drift Command
Command: /devteam:design-drift [scope] [options]
Detect design inconsistencies and drift from the design system. Launches the Design Drift Detector to analyze the codebase for deviations.
Usage
# Full codebase scan
/devteam:design-drift
# Scan specific directory
/devteam:design-drift --scope "src/components/"
# Check specific design aspect
/devteam:design-drift --check colors
/devteam:design-drift --check typography
/devteam:design-drift --check spacing
# Generate remediation plan
/devteam:design-drift --fix
Options
| Option | Description |
|---|---|
--scope <path> |
Limit scan to specific files/directories |
--check <aspect> |
Focus on: colors, typography, spacing, layout, all |
--fix |
Generate remediation tasks for detected drift |
--threshold <level> |
Drift tolerance: strict, normal, relaxed |
Your Process
Phase 0: Initialize Session
source "${CLAUDE_PLUGIN_ROOT}/scripts/state.sh"
source "${CLAUDE_PLUGIN_ROOT}/scripts/events.sh"
SESSION_ID=$(start_session "/devteam:design-drift $*" "design-drift")
log_session_started "/devteam:design-drift $*" "design-drift"
Phase 1: Launch Design Drift Detector
Delegate to the ux:design-drift-detector agent, which will:
- Scan codebase for design token usage
- Compare implementations against design system specifications
- Identify hardcoded values that should use tokens
- Detect inconsistent patterns across components
- Generate a drift report with severity ratings
const result = await Task({
subagent_type: "ux:design-drift-detector",
prompt: `Design drift analysis:
Scope: ${scope || 'full codebase'}
Check: ${aspect || 'all'}
Threshold: ${threshold || 'normal'}
Analyze for:
1. Hardcoded colors/fonts/spacing that should use design tokens
2. Inconsistent component patterns
3. Deviations from established design system
4. Accessibility regressions
5. Cross-platform inconsistencies`
})
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.
- 2d ago First seen · 104 lines · 0 tokens per session scan A 6494436a45f9
devteam-design-drift is a skill published in the GitHub repository michael-harris/devteam (18 stars, last pushed 6mo ago), licensed MIT. It adds 31 tokens to every session and 814 once invoked, about $0.0002 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.
Other skills, from other repositories
hydra
Multi-agent orchestration framework for Claude Code. Automatically delegates tasks to cheaper, faster sub-agents (Haiku, Sonnet) while maintaining Opus-level quality through verification. Use when working on any coding task — Hydra activates automatically to route file exploration, test running, documentation, code…
quality-stack
Scan a project to detect configured quality and testing tools across JVM (Gradle/Maven), Android (AGP/Compose/KMP), Node.js/TypeScript, and Python ecosystems. Cross-reference against research-backed recommendations and assist with setup. Auto-detects project type(s) including monorepos with mixed ecosystems. Use when…
prototype
Rapid UI prototyping — generates 3 visually distinct HTML/CSS components from a text prompt and serves them in a live browser gallery. Use when user runs /prototype, asks to "prototype a UI", "mock up a component", "generate HTML mockups", "create UI variations", "design exploration", "quick UI concept", or wants to…
lyra
Transform vague inputs into precision-optimized AI prompts for Claude, ChatGPT, Gemini, or other LLMs. Use when user mentions "optimize prompt", "improve prompt", "lyra", "prompt engineering", or needs help crafting effective AI prompts.
taskfile-setup
Install Taskfile (task) and scaffold or audit Taskfile.yml configurations with ecosystem-aware templates. Auto-detects Node.js/pnpm, JVM/Gradle, Python/uv, Docker, and recommends single-file or multi-file (includes) patterns based on project complexity. Use when user runs /devtools:taskfile-setup, mentions "taskfile…
sops-add-key
Add a new machine's age public key to .sops.yaml and re-encrypt all files. Use for multi-machine setups. Use when user mentions "add key", "add machine", "sops add key", "new machine", "authorize machine", "share key", "add public key", "multi machine sops".