Borrowing it
Nothing to install: this file belongs to AsiaOstrich/EngramGraph. 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/AsiaOstrich/EngramGraph/main/.agents/skills/audit-assistant/SKILL.mdgit clone --depth 1 https://github.com/AsiaOstrich/EngramGraphWrote 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/asiaostrich/engramgraph/audit-assistant)<a href="https://agentmods.dev/skills/asiaostrich/engramgraph/audit-assistant"><img src="https://agentmods.dev/badge/skills/asiaostrich/engramgraph/audit-assistant/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/asiaostrich/engramgraph/audit-assistant"><img src="https://agentmods.dev/badge/skills/asiaostrich/engramgraph/audit-assistant.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 | $0.00103 | $0.01643 |
| Opus 5.5 | $0.00041 | $0.00657 |
| Sonnet 5.5 | $0.00021 | $0.00329 |
| Haiku 4.5 | $0.00010 | $0.00164 |
Grade A, and why
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 14d 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 — 160 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Audit Assistant | 審計助手
Language: English | 繁體中文
Version: 1.0.0 Last Updated: 2026-03-04
Diagnose UDS installation health, detect development patterns worth standardizing, identify friction with existing standards, and submit structured feedback to the UDS repository.
診斷 UDS 安裝健康狀態、偵測值得規範化的開發模式、識別與現有標準的摩擦點，並向 UDS 儲存庫提交結構化回饋。
Workflow | 工作流程
DIAGNOSE ──► ANALYZE ──► REPORT
診斷健康 分析模式 回報回饋
Phase 1: DIAGNOSE | 診斷
Run health check on UDS installation.
執行 UDS 安裝健康檢查。
| Check | Description | 檢查項目 |
|---|---|---|
.standards/ exists |
Verify directory and files | 驗證目錄與檔案 |
manifest.json valid |
Parse and validate manifest | 解析驗證 manifest |
| File integrity | Compare hashes against manifest | 比對雜湊與 manifest |
| AI config references | Verify AI config files reference .standards/ |
驗證 AI 設定檔引用 |
Phase 2: ANALYZE | 分析
Detect patterns and friction points.
偵測模式與摩擦點。
| Analysis | Method | 分析方法 |
|---|---|---|
| Directory patterns | Scan for known standard categories | 掃描已知標準類別 |
| Commit patterns | Analyze recent 100 commits for recurring topics | 分析近 100 筆 commit |
| Modified standards | Compare file hashes (diff-based) | 比對檔案雜湊 |
| Unused standards | Check AI config references | 檢查 AI 設定引用 |
| Orphaned files | Find untracked files in .standards/ |
找出未追蹤檔案 |
Phase 3: REPORT | 回報
Submit findings as structured GitHub issue.
將發現以結構化 GitHub issue 提交。
| Method | Condition | 方法 |
|---|---|---|
gh issue create |
gh CLI installed |
gh CLI 已安裝 |
| Browser deeplink | Fallback to pre-filled URL | 退回至預填 URL |
| Clipboard copy | Last resort | 最終手段複製至剪貼簿 |
Usage | 使用方式
# Full audit (all layers)
uds audit
# Health check only
uds audit --health
# Pattern detection only
uds audit --patterns
# Friction detection only
uds audit --friction
# JSON output
uds audit --format json
# Summary only (for scripts)
uds audit --quiet
# Submit feedback interactively
uds audit --report
# Preview report without submitting
uds audit --report --dry-run
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.
- 14d ago First seen · 160 lines · 103 tokens per session scan A deaeeec6d8cb
audit is a skill published in the GitHub repository AsiaOstrich/EngramGraph (3 stars, last pushed today), licensed MIT. It adds 103 tokens to every session and 1,643 once invoked, about $0.0004 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 2026-10-16.
Other skills, from other repositories
code-graph
This skill should be used when understanding code structure, finding dependencies between functions/classes, tracing call graphs, or exploring code relationships. Trigger phrases include 'code graph', 'call graph', 'who calls', 'what calls', 'find dependencies', 'code structure', 'inheritance', 'find paths'.
usage
Query LeanKG knowledge graph for code understanding. Use when exploring a codebase, finding functions, tracing dependencies, or calculating impact radius.
kivgraph
Use Kivgraph's local MCP server to search symbols, read their source, and follow references, dependencies, cross-repository consumers and graph status in the indexed code graph.
mushroom
Live graph memory for agents — query and create entities, derive relationships by rule, explain why two things are associated, read the graph at a past commit, ask what a change would do, and answer as one role. Trigger on: memory, remember, recall, relationship, entity, association, why are X and Y related, as of…
potpie-cli
Use when the task is centered on running, explaining, configuring, or troubleshooting the potpie command: doctor, login, pot management, source registration, resolve/search/record, graph workbench reads/writes, resource (document payload) commands, and pot scope behavior.
potpie-debug-memory
Use while debugging or troubleshooting failures, flaky tests, incidents, production alerts, CI failures, local dev setup issues, repeated bugs, prior fixes, failed attempts, and verification history.