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 skills add MSApps-Mobile/claude-plugins --skill token-efficiency-auditgit clone --depth 1 https://github.com/MSApps-Mobile/claude-pluginsWrote 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/msapps-mobile/claude-plugins/token-efficiency-audit)<a href="https://agentmods.dev/skills/msapps-mobile/claude-plugins/token-efficiency-audit"><img src="https://agentmods.dev/badge/skills/msapps-mobile/claude-plugins/token-efficiency-audit/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/msapps-mobile/claude-plugins/token-efficiency-audit"><img src="https://agentmods.dev/badge/skills/msapps-mobile/claude-plugins/token-efficiency-audit.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00078 | $0.01105 |
| Opus 5.5 | $0.00031 | $0.00442 |
| Sonnet 5.5 | $0.00016 | $0.00221 |
| Haiku 4.5 | $0.00008 | $0.00111 |
Grade A, and why
token-efficiency-audit 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 yesterday.
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 — 128 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Token Efficiency Audit Skill
Overview
This skill performs a comprehensive token efficiency audit on Claude usage patterns, identifying optimization opportunities and generating actionable recommendations aligned with SOSA Level 3+ requirements.
Metadata
- Skill ID: token-efficiency-audit
- Version: 1.0.0
- SOSA Level: 3 (Secured + Supervised)
- Audit Coverage: Input tokens, output tokens, context window efficiency, cache hit rates
- Optimization Patterns: 11 standard patterns (O6a-O6e categories, including O6c-4 Redundant Context Detection)
Execution Model: Plan → Act → Verify
Phase 1: Plan
Analyze audit scope and establish baseline metrics:
-
Define Audit Boundaries
- Time period (last 30 days, last quarter, custom range)
- User/team scope (individual, department, organization)
- Model coverage (Claude 3 family, multimodal, specific versions)
- Environment (production, staging, development)
-
Establish Baselines
- Current token consumption (daily, weekly, monthly averages)
- Cost per 1M tokens (input, output, cache read/write)
- Context window utilization rate
- Cache effectiveness metrics
-
Define Success Metrics
- Target reduction percentage (typically 15-30%)
- Cost ceiling per operation
- Latency targets
- Quality thresholds (accuracy/helpfulness maintenance)
Phase 2: Act
Execute optimization analysis against 10 standard patterns:
-
Pattern Categories
- O6a: Prompt compression and summarization
- O6b: Context window optimization
- O6c: Batch processing and request consolidation
- O6d: Cache strategy optimization
- O6e: Model selection and routing
-
Analysis Steps
- Extract top 20% highest-cost interactions (80/20 analysis)
- Apply each pattern category to high-cost interactions
- Calculate theoretical token savings
- Identify implementation complexity and risk
- Apply O6c-4 (Redundant Context Detection): check marketplace plugins against built-in features and user commands for duplicates; classify MCP connectors as filterable (
.mcp.json) vs non-filterable (mcp__claude_ai_*)
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- yesterday Changed a030c09bb21d
- 1mo ago First seen · 128 lines · 78 tokens per session scan A 9d090a660b3a
token-efficiency-audit is a skill published in the GitHub repository MSApps-Mobile/claude-plugins (9 stars, last pushed today), licensed MIT. It adds 78 tokens to every session and 1,105 once invoked, about $0.0003 per session on Opus 5.5. 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 2026-09-13.
Other skills, from other repositories
live-preview
Mid-build visual verification loop. Takes screenshots of components during construction, not just after. Catches visual regressions and invisible features before they compound. Requires Playwright or similar screenshot tool.
wiki
Markdown-first knowledge base where the LLM acts as librarian. Ingests raw sources, compiles and interlinks topic files, self-maintains an index. No vector DB or embeddings required -- uses LLM-native navigation over structured markdown up to 400K words.
media-gemini-3-image-prompt
A prompt builder for Gemini 3 Pro Image, also known as Nano Banana Pro, Google's image-generation model. It expands a short request into five parts covering the subject, action, setting, composition, lighting, style, and text constraints.
data-realestate
A lookup tool for reported South Korean property transactions using Ministry of Land data. It covers sales and rental deals for apartments, officetels, multi-family homes, houses, and commercial or office properties.
design-sync-upload
An uploader for design-system files such as DESIGN.md, tokens, logos, fonts, and images into Claude Design. It can either use an authenticated connection or prepare a folder and guide for manual upload.
meta-feedback
A feedback reporter that collects bug reports and feature requests, then formats them as GitHub Issues. GitHub Issues are shared records used by development teams to track work and problems.